default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDSteve Renals
Stephen Renals
Person information
- affiliation: University of Edinburgh, UK
SPARQL queries 
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[i45]Erfan Loweimi, Andrea Carmantini, Peter Bell, Steve Renals, Zoran Cvetkovic:
Phonetic Error Analysis of Raw Waveform Acoustic Models with Parametric and Non-Parametric CNNs. CoRR abs/2406.00898 (2024)- 2023
- [j49]Erfan Loweimi
, Zhengjun Yue, Peter Bell, Steve Renals, Zoran Cvetkovic:
Multi-Stream Acoustic Modelling Using Raw Real and Imaginary Parts of the Fourier Transform. IEEE ACM Trans. Audio Speech Lang. Process. 31: 876-890 (2023) - [j48]Erfan Loweimi, Andrea Carmantini, Peter Bell, Steve Renals, Zoran Cvetkovic:
Phonetic Error Analysis Beyond Phone Error Rate. IEEE ACM Trans. Audio Speech Lang. Process. 31: 3346-3361 (2023) - 2022
- [j47]Dino Oglic, Zoran Cvetkovic, Peter Sollich, Steve Renals, Bin Yu:
Towards Robust Waveform-Based Acoustic Models. IEEE ACM Trans. Audio Speech Lang. Process. 30: 1977-1992 (2022) - [c209]Chau Luu, Steve Renals, Peter Bell:
Investigating the contribution of speaker attributes to speaker separability using disentangled speaker representations. INTERSPEECH 2022: 610-614 - 2021
- [j46]Manuel Sam Ribeiro, Joanne Cleland, Aciel Eshky, Korin Richmond, Steve Renals:
Exploiting ultrasound tongue imaging for the automatic detection of speech articulation errors. Speech Commun. 128: 24-34 (2021) - [j45]Aciel Eshky, Joanne Cleland, Manuel Sam Ribeiro, Eleanor Sugden, Korin Richmond, Steve Renals:
Automatic audiovisual synchronisation for ultrasound tongue imaging. Speech Commun. 132: 83-95 (2021) - [c208]Andrea Carmantini, Steve Renals, Peter Bell:
Leveraging Linguistic Knowledge for Accent Robustness of End-to-End Models. ASRU 2021: 803-810 - [c207]Georg Rehm, Stelios Piperidis, Kalina Bontcheva, Jan Hajic, Victoria Arranz, Andrejs Vasiljevs, Gerhard Backfried, José Manuél Gómez-Pérez, Ulrich Germann, Rémi Calizzano, Nils Feldhus, Stefanie Hegele, Florian Kintzel, Katrin Marheinecke, Julián Moreno Schneider, Dimitris Galanis, Penny Labropoulou, Miltos Deligiannis, Katerina Gkirtzou, Athanasia Kolovou, Dimitris Gkoumas, Leon Voukoutis, Ian Roberts, Jana Hamrlová, Dusan Varis, Lukás Kacena, Khalid Choukri, Valérie Mapelli, Mickaël Rigault, Julija Melnika, Miroslav Jánosík, Katja Prinz, Andrés García-Silva, Cristian Berrio, Ondrej Klejch, Steve Renals:
European Language Grid: A Joint Platform for the European Language Technology Community. EACL (System Demonstrations) 2021: 221-230 - [c206]Shucong Zhang, Cong-Thanh Do, Rama Doddipatla, Erfan Loweimi, Peter Bell, Steve Renals:
Train Your Classifier First: Cascade Neural Networks Training from Upper Layers to Lower Layers. ICASSP 2021: 2750-2754 - [c205]Erfan Loweimi, Zoran Cvetkovic, Peter Bell, Steve Renals:
Speech Acoustic Modelling from Raw Phase Spectrum. ICASSP 2021: 6738-6742 - [c204]Erfan Loweimi, Zoran Cvetkovic, Peter Bell, Steve Renals:
Speech Acoustic Modelling Using Raw Source and Filter Components. Interspeech 2021: 276-280 - [c203]Chau Luu, Peter Bell, Steve Renals:
Leveraging Speaker Attribute Information Using Multi Task Learning for Speaker Verification and Diarization. Interspeech 2021: 491-495 - [c202]Manuel Sam Ribeiro, Aciel Eshky, Korin Richmond, Steve Renals:
Silent versus Modal Multi-Speaker Speech Recognition from Ultrasound and Video. Interspeech 2021: 641-645 - [c201]Shucong Zhang, Erfan Loweimi, Peter Bell, Steve Renals:
Stochastic Attention Head Removal: A Simple and Effective Method for Improving Transformer Based ASR Models. Interspeech 2021: 2541-2545 - [c200]Shucong Zhang, Erfan Loweimi, Peter Bell, Steve Renals:
On The Usefulness of Self-Attention for Automatic Speech Recognition with Transformers. SLT 2021: 89-96 - [c199]Manuel Sam Ribeiro, Jennifer Sanger, Jing-Xuan Zhang, Aciel Eshky, Alan Wrench, Korin Richmond, Steve Renals:
Tal: A Synchronised Multi-Speaker Corpus of Ultrasound Tongue Imaging, Audio, and Lip Videos. SLT 2021: 1109-1116 - [i44]Shucong Zhang, Cong-Thanh Do, Rama Doddipatla, Erfan Loweimi, Peter Bell, Steve Renals:
Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers. CoRR abs/2102.04697 (2021) - [i43]Manuel Sam Ribeiro, Joanne Cleland, Aciel Eshky, Korin Richmond, Steve Renals:
Exploiting ultrasound tongue imaging for the automatic detection of speech articulation errors. CoRR abs/2103.00324 (2021) - [i42]Manuel Sam Ribeiro, Aciel Eshky, Korin Richmond, Steve Renals:
Silent versus modal multi-speaker speech recognition from ultrasound and video. CoRR abs/2103.00333 (2021) - [i41]Aciel Eshky, Joanne Cleland, Manuel Sam Ribeiro, Eleanor Sugden, Korin Richmond, Steve Renals:
Automatic audiovisual synchronisation for ultrasound tongue imaging. CoRR abs/2105.15162 (2021) - [i40]Dino Oglic, Zoran Cvetkovic, Peter Sollich, Steve Renals, Bin Yu:
Towards Robust Waveform-Based Acoustic Models. CoRR abs/2110.08634 (2021) - 2020
- [c198]Alberto Abad, Peter Bell, Andrea Carmantini, Steve Renals:
Cross Lingual Transfer Learning for Zero-Resource Domain Adaptation. ICASSP 2020: 6909-6913 - [c197]Joanna Rownicka, Peter Bell, Steve Renals:
Multi-Scale Octave Convolutions for Robust Speech Recognition. ICASSP 2020: 7019-7023 - [c196]Shucong Zhang, Cong-Thanh Do, Rama Doddipatla, Steve Renals:
Learning Noise Invariant Features Through Transfer Learning For Robust End-to-End Speech Recognition. ICASSP 2020: 7024-7028 - [c195]Chau Luu, Peter Bell, Steve Renals:
Channel Adversarial Training for Speaker Verification and Diarization. ICASSP 2020: 7094-7098 - [c194]Ahmed Ali, Steve Renals:
Word Error Rate Estimation Without ASR Output: e-WER2. INTERSPEECH 2020: 616-620 - [c193]Erfan Loweimi, Peter Bell, Steve Renals:
On the Robustness and Training Dynamics of Raw Waveform Models. INTERSPEECH 2020: 1001-1005 - [c192]Erfan Loweimi, Peter Bell, Steve Renals:
Raw Sign and Magnitude Spectra for Multi-Head Acoustic Modelling. INTERSPEECH 2020: 1644-1648 - [c191]Dino Oglic, Zoran Cvetkovic, Peter Bell, Steve Renals:
A Deep 2D Convolutional Network for Waveform-Based Speech Recognition. INTERSPEECH 2020: 1654-1658 - [c190]Neethu M. Joy, Dino Oglic, Zoran Cvetkovic, Peter Bell, Steve Renals:
Deep Scattering Power Spectrum Features for Robust Speech Recognition. INTERSPEECH 2020: 1673-1677 - [c189]Georg Rehm, Maria Berger, Ela Elsholz, Stefanie Hegele, Florian Kintzel, Katrin Marheinecke, Stelios Piperidis, Miltos Deligiannis, Dimitris Galanis, Katerina Gkirtzou, Penny Labropoulou, Kalina Bontcheva, David Jones, Ian Roberts, Jan Hajic, Jana Hamrlová, Lukás Kacena, Khalid Choukri, Victoria Arranz, Andrejs Vasiljevs, Orians Anvari, Andis Lagzdins, Julija Melnika, Gerhard Backfried, Erinç Dikici, Miroslav Jánosík, Katja Prinz, Christoph Prinz, Severin Stampler, Dorothea Thomas-Aniola, José Manuél Gómez-Pérez, Andrés García-Silva, Cristian Berrio, Ulrich Germann, Steve Renals, Ondrej Klejch:
European Language Grid: An Overview. LREC 2020: 3366-3380 - [c188]Chau Luu, Peter Bell, Steve Renals:
Dropping Classes for Deep Speaker Representation Learning. Odyssey 2020: 357-364 - [i39]Chau Luu, Peter Bell, Steve Renals:
DropClass and DropAdapt: Dropping classes for deep speaker representation learning. CoRR abs/2002.00453 (2020) - [i38]Georg Rehm, Maria Berger, Ela Elsholz, Stefanie Hegele, Florian Kintzel, Katrin Marheinecke, Stelios Piperidis, Miltos Deligiannis, Dimitris Galanis, Katerina Gkirtzou, Penny Labropoulou, Kalina Bontcheva, David Jones, Ian Roberts, Jan Hajic, Jana Hamrlová, Lukás Kacena, Khalid Choukri, Victoria Arranz, Andrejs Vasiljevs, Orians Anvari, Andis Lagzdins, Julija Melnika, Gerhard Backfried, Erinç Dikici, Miroslav Jánosík, Katja Prinz, Christoph Prinz, Severin Stampler, Dorothea Thomas-Aniola, José Manuél Gómez-Pérez, Andrés García-Silva, Cristian Berrio, Ulrich Germann, Steve Renals, Ondrej Klejch:
European Language Grid: An Overview. CoRR abs/2003.13551 (2020) - [i37]Shucong Zhang, Erfan Loweimi, Peter Bell, Steve Renals:
When Can Self-Attention Be Replaced by Feed Forward Layers? CoRR abs/2005.13895 (2020) - [i36]Ahmed Ali, Steve Renals:
Word Error Rate Estimation Without ASR Output: e-WER2. CoRR abs/2008.03403 (2020) - [i35]Peter Bell, Joachim Fainberg, Ondrej Klejch, Jinyu Li, Steve Renals, Pawel Swietojanski:
Adaptation Algorithms for Speech Recognition: An Overview. CoRR abs/2008.06580 (2020) - [i34]Chau Luu, Peter Bell, Steve Renals:
Leveraging speaker attribute information using multi task learning for speaker verification and diarization. CoRR abs/2010.14269 (2020) - [i33]Shucong Zhang, Erfan Loweimi, Peter Bell, Steve Renals:
Stochastic Attention Head Removal: A Simple and Effective Method for Improving Automatic Speech Recognition with Transformers. CoRR abs/2011.04004 (2020) - [i32]Shucong Zhang, Erfan Loweimi, Peter Bell, Steve Renals:
On the Usefulness of Self-Attention for Automatic Speech Recognition with Transformers. CoRR abs/2011.04906 (2020) - [i31]Manuel Sam Ribeiro, Jennifer Sanger, Jing-Xuan Zhang, Aciel Eshky, Alan Wrench, Korin Richmond, Steve Renals:
TaL: a synchronised multi-speaker corpus of ultrasound tongue imaging, audio, and lip videos. CoRR abs/2011.09804 (2020)
2010 – 2019
- 2019
- [c187]Joanna Rownicka, Peter Bell, Steve Renals:
Embeddings for DNN Speaker Adaptive Training. ASRU 2019: 479-486 - [c186]Ondrej Klejch, Joachim Fainberg, Peter Bell, Steve Renals:
Speaker Adaptive Training Using Model Agnostic Meta-Learning. ASRU 2019: 881-888 - [c185]Joachim Fainberg, Ondrej Klejch, Erfan Loweimi, Peter Bell, Steve Renals:
Acoustic Model Adaptation from Raw Waveforms with Sincnet. ASRU 2019: 897-904 - [c184]Ahmed Ali, Suwon Shon, Younes Samih, Hamdy Mubarak, Ahmed Abdelali, James R. Glass, Steve Renals, Khalid Choukri:
The MGB-5 Challenge: Recognition and Dialect Identification of Dialectal Arabic Speech. ASRU 2019: 1026-1033 - [c183]Manuel Sam Ribeiro, Aciel Eshky, Korin Richmond, Steve Renals:
Speaker-independent Classification of Phonetic Segments from Raw Ultrasound in Child Speech. ICASSP 2019: 1328-1332 - [c182]Erfan Loweimi, Peter Bell, Steve Renals:
On the Usefulness of Statistical Normalisation of Bottleneck Features for Speech Recognition. ICASSP 2019: 3862-3866 - [c181]Shucong Zhang, Erfan Loweimi, Peter Bell, Steve Renals:
Windowed Attention Mechanisms for Speech Recognition. ICASSP 2019: 7100-7104 - [c180]Manuel Sam Ribeiro, Aciel Eshky, Korin Richmond, Steve Renals:
Ultrasound Tongue Imaging for Diarization and Alignment of Child Speech Therapy Sessions. INTERSPEECH 2019: 16-20 - [c179]Andrea Carmantini, Peter Bell, Steve Renals:
Untranscribed Web Audio for Low Resource Speech Recognition. INTERSPEECH 2019: 226-230 - [c178]Shucong Zhang, Erfan Loweimi, Yumo Xu, Peter Bell, Steve Renals:
Trainable Dynamic Subsampling for End-to-End Speech Recognition. INTERSPEECH 2019: 1413-1417 - [c177]Joachim Fainberg, Ondrej Klejch, Steve Renals, Peter Bell:
Lattice-Based Lightly-Supervised Acoustic Model Training. INTERSPEECH 2019: 1596-1600 - [c176]Erfan Loweimi, Peter Bell, Steve Renals:
On Learning Interpretable CNNs with Parametric Modulated Kernel-Based Filters. INTERSPEECH 2019: 3480-3484 - [c175]Aciel Eshky, Manuel Sam Ribeiro, Korin Richmond, Steve Renals:
Synchronising Audio and Ultrasound by Learning Cross-Modal Embeddings. INTERSPEECH 2019: 4100-4104 - [i30]Ben Krause, Emmanuel Kahembwe, Iain Murray, Steve Renals:
Dynamic Evaluation of Transformer Language Models. CoRR abs/1904.08378 (2019) - [i29]Joachim Fainberg, Ondrej Klejch, Steve Renals, Peter Bell:
Lattice-based lightly-supervised acoustic model training. CoRR abs/1905.13150 (2019) - [i28]Ondrej Klejch, Joachim Fainberg, Peter Bell, Steve Renals:
Lattice-Based Unsupervised Test-Time Adaptation of Neural Network Acoustic Models. CoRR abs/1906.11521 (2019) - [i27]Aciel Eshky, Manuel Sam Ribeiro, Korin Richmond, Steve Renals:
Synchronising audio and ultrasound by learning cross-modal embeddings. CoRR abs/1907.00758 (2019) - [i26]Manuel Sam Ribeiro, Aciel Eshky, Korin Richmond, Steve Renals:
Ultrasound tongue imaging for diarization and alignment of child speech therapy sessions. CoRR abs/1907.00818 (2019) - [i25]Manuel Sam Ribeiro, Aciel Eshky, Korin Richmond, Steve Renals:
Speaker-independent classification of phonetic segments from raw ultrasound in child speech. CoRR abs/1907.01413 (2019) - [i24]Joanna Rownicka, Peter Bell, Steve Renals:
Embeddings for DNN speaker adaptive training. CoRR abs/1909.13537 (2019) - [i23]Joachim Fainberg, Ondrej Klejch, Erfan Loweimi, Peter Bell, Steve Renals:
Acoustic Model Adaptation from Raw Waveforms with SincNet. CoRR abs/1909.13759 (2019) - [i22]Ondrej Klejch, Joachim Fainberg, Peter Bell, Steve Renals:
Speaker Adaptive Training using Model Agnostic Meta-Learning. CoRR abs/1910.10605 (2019) - [i21]Chau Luu, Peter Bell, Steve Renals:
Channel adversarial training for speaker verification and diarization. CoRR abs/1910.11643 (2019) - [i20]Joanna Rownicka, Peter Bell, Steve Renals:
Multi-scale Octave Convolutions for Robust Speech Recognition. CoRR abs/1910.14443 (2019) - 2018
- [c174]Ahmed Ali, Steve Renals:
Word Error Rate Estimation for Speech Recognition: e-WER. ACL (2) 2018: 20-24 - [c173]Ben Krause, Emmanuel Kahembwe, Iain Murray, Steve Renals:
Dynamic Evaluation of Neural Sequence Models. ICML 2018: 2771-2780 - [c172]Joanna Rownicka, Peter Bell, Steve Renals:
Analyzing Deep CNN-Based Utterance Embeddings for Acoustic Model Adaptation. SLT 2018: 235-241 - [i19]Joanna Rownicka, Peter Bell, Steve Renals:
Analyzing deep CNN-based utterance embeddings for acoustic model adaptation. CoRR abs/1811.04708 (2018) - 2017
- [j44]Hao Tang, Liang Lu, Lingpeng Kong, Kevin Gimpel, Karen Livescu, Chris Dyer, Noah A. Smith, Steve Renals:
End-to-End Neural Segmental Models for Speech Recognition. IEEE J. Sel. Top. Signal Process. 11(8): 1254-1264 (2017) - [j43]Peter Bell, Pawel Swietojanski, Steve Renals:
Multitask Learning of Context-Dependent Targets in Deep Neural Network Acoustic Models. IEEE ACM Trans. Audio Speech Lang. Process. 25(2): 238-247 (2017) - [j42]Liang Lu, Steve Renals:
Small-Footprint Highway Deep Neural Networks for Speech Recognition. IEEE ACM Trans. Audio Speech Lang. Process. 25(7): 1502-1511 (2017) - [c171]Ahmed Ali, Preslav Nakov, Peter Bell, Steve Renals:
WERD: Using social text spelling variants for evaluating dialectal speech recognition. ASRU 2017: 141-148 - [c170]Joanna Rownicka, Steve Renals, Peter Bell:
Simplifying very deep convolutional neural network architectures for robust speech recognition. ASRU 2017: 236-243 - [c169]Ahmed Ali, Stephan Vogel, Steve Renals:
Speech recognition challenge in the wild: Arabic MGB-3. ASRU 2017: 316-322 - [c168]Emiru Tsunoo, Ondrej Klejch, Peter Bell, Steve Renals:
Hierarchical recurrent neural network for story segmentation using fusion of lexical and acoustic features. ASRU 2017: 525-532 - [c167]Renars Liepins, Ulrich Germann, Guntis Barzdins, Alexandra Birch, Steve Renals, Susanne Weber, Peggy van der Kreeft, Hervé Bourlard, João Prieto, Ondrej Klejch, Peter Bell, Alexandros Lazaridis, Afonso Mendes, Sebastian Riedel, Mariana S. C. Almeida, Pedro Balage, Shay B. Cohen, Tomasz Dwojak, Philip N. Garner, Andreas Giefer, Marcin Junczys-Dowmunt, Hina Imran, David Nogueira, Ahmed M. Ali, Sebastião Miranda, Andrei Popescu-Belis, Lesly Miculicich Werlen, Nikos Papasarantopoulos, Abiola Obamuyide, Clive Jones, Fahim Dalvi, Andreas Vlachos, Yang Wang, Sibo Tong, Rico Sennrich, Nikolaos Pappas, Shashi Narayan, Marco Damonte, Nadir Durrani, Sameer Khurana, Ahmed Abdelali, Hassan Sajjad, Stephan Vogel, David Sheppey, Chris Hernon, Jeff Mitchell:
The SUMMA Platform Prototype. EACL (Software Demonstrations) 2017: 116-119 - [c166]Liang Lu, Michelle Guo, Steve Renals:
Knowledge distillation for small-footprint highway networks. ICASSP 2017: 4820-4824 - [c165]Ondrej Klejch, Peter Bell, Steve Renals:
Sequence-to-sequence models for punctuated transcription combining lexical and acoustic features. ICASSP 2017: 5700-5704 - [c164]Ben Krause, Iain Murray, Steve Renals, Liang Lu:
Multiplicative LSTM for sequence modelling. ICLR (Workshop) 2017 - [c163]Joachim Fainberg, Steve Renals, Peter Bell:
Factorised Representations for Neural Network Adaptation to Diverse Acoustic Environments. INTERSPEECH 2017: 749-753 - [c162]Emiru Tsunoo, Peter Bell, Steve Renals:
Hierarchical Recurrent Neural Network for Story Segmentation. INTERSPEECH 2017: 2919-2923 - [p2]Keiichi Tokuda, Akinobu Lee, Yoshihiko Nankaku, Keiichiro Oura, Kei Hashimoto, Daisuke Yamamoto, Ichi Takumi, Takahiro Uchiya, Shuhei Tsutsumi, Steve Renals, Junichi Yamagishi:
User Generated Dialogue Systems: uDialogue. Human-Harmonized Information Technology (2) 2017: 77-114 - [p1]Steve Renals, Pawel Swietojanski:
Distant Speech Recognition Experiments Using the AMI Corpus. New Era for Robust Speech Recognition, Exploiting Deep Learning 2017: 355-368 - [i18]Hao Tang, Liang Lu, Lingpeng Kong, Kevin Gimpel, Karen Livescu, Chris Dyer, Noah A. Smith, Steve Renals:
End-to-End Neural Segmental Models for Speech Recognition. CoRR abs/1708.00531 (2017) - [i17]Ahmed M. Ali, Stephan Vogel, Steve Renals:
Speech Recognition Challenge in the Wild: Arabic MGB-3. CoRR abs/1709.07276 (2017) - [i16]Ben Krause, Emmanuel Kahembwe, Iain Murray, Steve Renals:
Dynamic Evaluation of Neural Sequence Models. CoRR abs/1709.07432 (2017) - [i15]Ahmed M. Ali, Preslav Nakov, Peter Bell, Steve Renals:
WERd: Using Social Text Spelling Variants for Evaluating Dialectal Speech Recognition. CoRR abs/1709.07484 (2017) - 2016
- [j41]Pawel Swietojanski, Jinyu Li, Steve Renals:
Learning Hidden Unit Contributions for Unsupervised Acoustic Model Adaptation. IEEE ACM Trans. Audio Speech Lang. Process. 24(8): 1450-1463 (2016) - [j40]Pawel Swietojanski, Steve Renals:
Differentiable Pooling for Unsupervised Acoustic Model Adaptation. IEEE ACM Trans. Audio Speech Lang. Process. 24(10): 1773-1784 (2016) - [c161]Pawel Swietojanski, Steve Renals:
SAT-LHUC: Speaker adaptive training for learning hidden unit contributions. ICASSP 2016: 5010-5014 - [c160]Liang Lu, Xingxing Zhang, Steve Renals:
On training the recurrent neural network encoder-decoder for large vocabulary end-to-end speech recognition. ICASSP 2016: 5060-5064 - [c159]Liang Lu, Steve Renals:
Small-Footprint Deep Neural Networks with Highway Connections for Speech Recognition. INTERSPEECH 2016: 12-16 - [c158]Liang Lu, Lingpeng Kong, Chris Dyer, Noah A. Smith, Steve Renals:
Segmental Recurrent Neural Networks for End-to-End Speech Recognition. INTERSPEECH 2016: 385-389 - [c157]Joachim Fainberg, Peter Bell, Mike Lincoln, Steve Renals:
Improving Children's Speech Recognition Through Out-of-Domain Data Augmentation. INTERSPEECH 2016: 1598-1602 - [c156]Siva Reddy Gangireddy, Pawel Swietojanski, Peter Bell, Steve Renals:
Unsupervised Adaptation of Recurrent Neural Network Language Models. INTERSPEECH 2016: 2333-2337 - [c155]Ahmed Ali, Najim Dehak, Patrick Cardinal, Sameer Khurana, Sree Harsha Yella, James R. Glass, Peter Bell, Steve Renals:
Automatic Dialect Detection in Arabic Broadcast Speech. INTERSPEECH 2016: 2934-2938 - [c154]Guntis Barzdins, Steve Renals, Didzis Gosko:
Character-Level Neural Translation for Multilingual Media Monitoring in the SUMMA Project. LREC 2016 - [c153]Ahmed Ali, Peter Bell, James R. Glass, Yacine Messaoui, Hamdy Mubarak, Steve Renals, Yifan Zhang:
The MGB-2 challenge: Arabic multi-dialect broadcast media recognition. SLT 2016: 279-284 - [c152]Ondrej Klejch, Peter Bell, Steve Renals:
Punctuated transcription of multi-genre broadcasts using acoustic and lexical approaches. SLT 2016: 433-440 - [i14]Pawel Swietojanski, Jinyu Li, Steve Renals:
Learning Hidden Unit Contributions for Unsupervised Acoustic Model Adaptation. CoRR abs/1601.02828 (2016) - [i13]Liang Lu, Lingpeng Kong, Chris Dyer, Noah A. Smith, Steve Renals:
Segmental Recurrent Neural Networks for End-to-end Speech Recognition. CoRR abs/1603.00223 (2016) - [i12]Pawel Swietojanski, Steve Renals:
Differentiable Pooling for Unsupervised Acoustic Model Adaptation. CoRR abs/1603.09630 (2016) - [i11]Guntis Barzdins, Steve Renals, Didzis Gosko:
Character-Level Neural Translation for Multilingual Media Monitoring in the SUMMA Project. CoRR abs/1604.01221 (2016) - [i10]Liang Lu, Michelle Guo, Steve Renals:
Knowledge Distillation for Small-footprint Highway Networks. CoRR abs/1608.00892 (2016) - [i9]Ahmed Ali, Peter Bell, James R. Glass, Yacine Messaoui, Hamdy Mubarak, Steve Renals, Yifan Zhang:
The MGB-2 Challenge: Arabic Multi-Dialect Broadcast Media Recognition. CoRR abs/1609.05625 (2016) - [i8]Sameer Khurana, Ahmed M. Ali, Steve Renals:
Multi-view Dimensionality Reduction for Dialect Identification of Arabic Broadcast Speech. CoRR abs/1609.05650 (2016) - [i7]Ben Krause, Liang Lu, Iain Murray, Steve Renals:
Multiplicative LSTM for sequence modelling. CoRR abs/1609.07959 (2016) - [i6]Liang Lu, Steve Renals:
Small-footprint Highway Deep Neural Networks for Speech Recognition. CoRR abs/1610.05812 (2016) - 2015
- [j39]Alessandro Vinciarelli, Anna Esposito, Elisabeth André, Francesca Bonin, Mohamed Chetouani, Jeffrey F. Cohn, Marco Cristani, Ferdinand Fuhrmann, Emer Gilmartin, Zakia Hammal, Dirk Heylen, Rene Kaiser, Maria Koutsombogera, Alexandros Potamianos, Steve Renals, Giuseppe Riccardi, Albert Ali Salah:
Open Challenges in Modelling, Analysis and Synthesis of Human Behaviour in Human-Human and Human-Machine Interactions. Cogn. Comput. 7(4): 397-413 (2015) - [c151]Ahmed M. Ali, Walid Magdy, Peter Bell, Steve Renals:
Multi-reference WER for evaluating ASR for languages with no orthographic rules. ASRU 2015: 576-580 - [c150]Peter Bell, Steve Renals:
A system for automatic alignment of broadcast media captions using weighted finite-state transducers. ASRU 2015: 675-680 - [c149]Peter Bell, Mark J. F. Gales, Thomas Hain, Jonathan Kilgour, Pierre Lanchantin, Xunying Liu, Andrew McParland, Steve Renals, Oscar Saz, Mirjam Wester, Philip C. Woodland:
The MGB challenge: Evaluating multi-genre broadcast media recognition. ASRU 2015: 687-693 - [c148]Peter Bell, Steve Renals:
Regularization of context-dependent deep neural networks with context-independent multi-task training. ICASSP 2015: 4290-4294 - [c147]Pawel Swietojanski, Steve Renals:
Differentiable pooling for unsupervised speaker adaptation. ICASSP 2015: 4305-4309 - [c146]Benigno Uria, Iain Murray, Steve Renals, Cassia Valentini-Botinhao, John Bridle:
Modelling acoustic feature dependencies with artificial neural networks: Trajectory-RNADE. ICASSP 2015: 4465-4469 - [c145]Liang Lu, Steve Renals:
Multi-frame factorisation for long-span acoustic modelling. ICASSP 2015: 4595-4599 - [c144]Zhizheng Wu, Pawel Swietojanski, Christophe Veaux, Steve Renals, Simon King:
A study of speaker adaptation for DNN-based speech synthesis. INTERSPEECH 2015: 879-883 - [c143]Siva Reddy Gangireddy, Steve Renals, Yoshihiko Nankaku, Akinobu Lee:
Prosodically-enhanced recurrent neural network language models. INTERSPEECH 2015: 2390-2394 - [c142]Liang Lu, Steve Renals:
Feature-space speaker adaptation for probabilistic linear discriminant analysis acoustic models. INTERSPEECH 2015: 2862-2866 - [c141]Liang Lu, Xingxing Zhang, Kyunghyun Cho, Steve Renals:
A study of the recurrent neural network encoder-decoder for large vocabulary speech recognition. INTERSPEECH 2015: 3249-3253 - [c140]Pawel Swietojanski, Peter Bell, Steve Renals:
Structured output layer with auxiliary targets for context-dependent acoustic modelling. INTERSPEECH 2015: 3605-3609 - [c139]Peter Bell, Steve Renals:
Complementary tasks for context-dependent deep neural network acoustic models. INTERSPEECH 2015: 3610-3614 - [c138]Ahmed M. Ali, Walid Magdy, Steve Renals:
Multi-Reference Evaluation for Dialectal Speech Recognition System: A Study for Egyptian ASR. ANLP@ACL 2015: 118-126 - [i5]Ahmed M. Ali, Peter Bell, Steve Renals:
Automatic Dialect Detection in Arabic Broadcast Speech. CoRR abs/1509.06928 (2015) - [i4]Liang Lu, Steve Renals:
Small-footprint Deep Neural Networks with Highway Connections for Speech Recognition. CoRR abs/1512.04280 (2015) - 2014
- [j38]João P. Cabral, Korin Richmond, Junichi Yamagishi, Steve Renals:
Glottal Spectral Separation for Speech Synthesis. IEEE J. Sel. Top. Signal Process. 8(2): 195-208 (2014) - [j37]Liang Lu, Steve Renals:
Probabilistic Linear Discriminant Analysis for Acoustic Modeling. IEEE Signal Process. Lett. 21(6): 702-706 (2014) - [j36]Pawel Swietojanski, Arnab Ghoshal, Steve Renals:
Convolutional Neural Networks for Distant Speech Recognition. IEEE Signal Process. Lett. 21(9): 1120-1124 (2014) - [j35]Li Deng, Steve Renals, Marcello Federico, Mari Ostendorf:
Editorial: Expanding the Technical Reach of our Transactions. IEEE ACM Trans. Audio Speech Lang. Process. 22(1): 5 (2014) - [j34]Liang Lu, Arnab Ghoshal, Steve Renals:
Cross-Lingual Subspace Gaussian Mixture Models for Low-Resource Speech Recognition. IEEE ACM Trans. Audio Speech Lang. Process. 22(1): 17-27 (2014) - [c137]Steve Renals, Pawel Swietojanski:
Neural networks for distant speech recognition. HSCMA 2014: 172-176 - [c136]Oliver Watts, Siva Reddy Gangireddy, Junichi Yamagishi, Simon King, Steve Renals, Adriana Stan, Mircea Giurgiu:
Neural net word representations for phrase-break prediction without a part of speech tagger. ICASSP 2014: 2599-2603 - [c135]Steve Renals, Jean Carletta, Keith Edwards, Hervé Bourlard, Philip N. Garner, Andrei Popescu-Belis, Dietrich Klakow, Andrey Girenko, Volha Petukhova, Philippe Wacker, Andrew Joscelyne, Costis Kompis, Simon Aliwell, William Stevens, Youssef Sabbah:
ROCKIT: Roadmap for Conversational Interaction Technologies. RFMIR@ICMI 2014: 39-42 - [c134]Peter Bell, Joris Driesen, Steve Renals:
Cross-lingual adaptation with multi-task adaptive networks. INTERSPEECH 2014: 21-25 - [c133]Liang Lu, Steve Renals:
Probabilistic linear discriminant analysis with bottleneck features for speech recognition. INTERSPEECH 2014: 910-914 - [c132]Catherine Lai, Steve Renals:
Incorporating lexical and prosodic information at different levels for meeting summarization. INTERSPEECH 2014: 1875-1879 - [c131]Joris Driesen, Alexandra Birch, Simon Grimsey, Saeid Safarfashandi, Juliet Gauthier, Matt Simpson, Steve Renals:
Automated production of true-cased punctuated subtitles for weather and news broadcasts. INTERSPEECH 2014: 2146-2147 - [c130]Siva Reddy Gangireddy, Fergus McInnes, Steve Renals:
Feed forward pre-training for recurrent neural network language models. INTERSPEECH 2014: 2620-2624 - [c129]Peter Bell, Pawel Swietojanski, Joris Driesen, Mark Sinclair, Fergus McInnes, Steve Renals:
The UEDIN ASR systems for the IWSLT 2014 evaluation. IWSLT (Evaluation Campaign) 2014 - [c128]Pawel Swietojanski, Steve Renals:
Learning hidden unit contributions for unsupervised speaker adaptation of neural network acoustic models. SLT 2014: 171-176 - [i3]Liang Lu, Steve Renals:
Tied Probabilistic Linear Discriminant Analysis for Speech Recognition. CoRR abs/1411.0895 (2014) - 2013
- [j33]Christian Geng, Alice Turk, James M. Scobbie, Cedric Macmartin, Philip Hoole, Korin Richmond, Alan Wrench, Marianne Pouplier, Ellen Gurman Bard, Ziggy Campbell, Catherine Dickie, Eddie Dubourg, William J. Hardcastle, Evia Kainada, Simon King, Robin J. Lickley, Satsuki Nakai, Steve Renals, Kevin White, Ronny Wiegand:
Recording speech articulation in dialogue: Evaluating a synchronized double electromagnetic articulography setup. J. Phonetics 41(6): 421-431 (2013) - [j32]Liang Lu, K. K. Chin, Arnab Ghoshal, Stephen Renals:
Joint Uncertainty Decoding for Noise Robust Subspace Gaussian Mixture Models. IEEE Trans. Speech Audio Process. 21(9): 1791-1804 (2013) - [j31]Marcello Federico, Steve Renals:
Editorial. ACM Trans. Speech Lang. Process. 10(4): 14:1 (2013) - [c127]Pawel Swietojanski, Arnab Ghoshal, Steve Renals:
Hybrid acoustic models for distant and multichannel large vocabulary speech recognition. ASRU 2013: 285-290 - [c126]Liang Lu, Arnab Ghoshal, Steve Renals:
Acoustic data-driven pronunciation lexicon for large vocabulary speech recognition. ASRU 2013: 374-379 - [c125]Joris Driesen, Steve Renals:
Lightly supervised automatic subtitling of weather forecasts. ASRU 2013: 452-457 - [c124]Pawel Swietojanski, Arnab Ghoshal, Steve Renals:
Revisiting hybrid and GMM-HMM system combination techniques. ICASSP 2013: 6744-6748 - [c123]Peter Bell, Pawel Swietojanski, Steve Renals:
Multi-level adaptive networks in tandem and hybrid ASR systems. ICASSP 2013: 6975-6979 - [c122]Erich Zwyssig, Friedrich Faubel, Steve Renals, Mike Lincoln:
Recognition of overlapping speech using digital MEMS microphone arrays. ICASSP 2013: 7068-7072 - [c121]Arnab Ghoshal, Pawel Swietojanski, Steve Renals:
Multilingual training of deep neural networks. ICASSP 2013: 7319-7323 - [c120]Hervé Bourlard, Marc Ferras, Nikolaos Pappas, Andrei Popescu-Belis, Steve Renals, Fergus McInnes, Peter Bell, Sandy Ingram, Maël Guillemot:
Processing and Linking Audio Events in Large Multimedia Archives: The EU inEvent Project. SLAM@INTERSPEECH 2013: 3-8 - [c119]Pierre Lanchantin, Peter Bell, Mark J. F. Gales, Thomas Hain, Xunying Liu, Yanhua Long, Jennifer Quinnell, Steve Renals, Oscar Saz, Matthew Stephen Seigel, Pawel Swietojanski, Philip C. Woodland:
Automatic Transcription of Multi-genre Media Archives. SLAM@INTERSPEECH 2013: 26-31 - [c118]Catherine Lai, Jean Carletta, Steve Renals:
Detecting summarization hot spots in meetings using group level involvement and turn-taking features. INTERSPEECH 2013: 2723-2727 - [c117]Peter Bell, Hitoshi Yamamoto, Pawel Swietojanski, Youzheng Wu, Fergus McInnes, Chiori Hori, Steve Renals:
A lecture transcription system combining neural network acoustic and language models. INTERSPEECH 2013: 3087-3091 - [c116]Liang Lu, Arnab Ghoshal, Steve Renals:
Noise adaptive training for subspace Gaussian mixture models. INTERSPEECH 2013: 3492-3496 - [c115]Peter Bell, Fergus McInnes, Siva Reddy Gangireddy, Mark Sinclair, Alexandra Birch, Steve Renals:
The UEDIN English ASR system for the IWSLT 2013 evaluation. IWSLT (Evaluation Campaign) 2013 - [c114]Joris Driesen, Peter Bell, Mark Sinclair, Steve Renals:
Description of the UEDIN system for German ASR. IWSLT (Evaluation Campaign) 2013 - 2012
- [j30]Martha A. Larson, Franciska de Jong, Wessel Kraaij, Steve Renals:
Special issue on searching speech. ACM Trans. Inf. Syst. 30(3): 15:1-15:2 (2012) - [c113]Erich Zwyssig, Steve Renals, Mike Lincoln:
On the effect of snr and superdirective beamforming in speaker diarisation in meetings. ICASSP 2012: 4177-4180 - [c112]Erich Zwyssig, Steve Renals, Mike Lincoln:
Determining the number of speakers in a meeting using microphone array features. ICASSP 2012: 4765-4768 - [c111]Liang Lu, Arnab Ghoshal, Steve Renals:
Maximum a posteriori adaptation of subspace Gaussian mixture models for cross-lingual speech recognition. ICASSP 2012: 4877-4880 - [c110]Liang Lu, Arnab Ghoshal, Steve Renals:
Joint uncertainty decoding with unscented transform for noise robust subspace Gaussian mixture models. SAPA@INTERSPEECH 2012: 40-45 - [c109]Korin Richmond, Steve Renals:
Ultrax: An Animated Midsagittal Vocal Tract Display for Speech Therapy. INTERSPEECH 2012: 74-77 - [c108]Liang Lu, K. K. Chin, Arnab Ghoshal, Steve Renals:
Noise Compensation for Subspace Gaussian Mixture Models. INTERSPEECH 2012: 306-309 - [c107]Benigno Uria, Iain Murray, Steve Renals, Korin Richmond:
Deep Architectures for Articulatory Inversion. INTERSPEECH 2012: 867-870 - [c106]Eva Hasler, Peter Bell, Arnab Ghoshal, Barry Haddow, Philipp Koehn, Fergus McInnes, Steve Renals, Pawel Swietojanski:
The UEDIN systems for the IWSLT 2012 evaluation. IWSLT 2012: 46-53 - [c105]Pawel Swietojanski, Arnab Ghoshal, Steve Renals:
Unsupervised cross-lingual knowledge transfer in DNN-based LVCSR. SLT 2012: 246-251 - [c104]Peter Bell, Mark J. F. Gales, Pierre Lanchantin, Xunying Liu, Yanhua Long, Steve Renals, Pawel Swietojanski, Philip C. Woodland:
Transcription of multi-genre media archives using out-of-domain data. SLT 2012: 324-329 - 2011
- [j29]Liang Lu, Arnab Ghoshal, Steve Renals:
Regularized Subspace Gaussian Mixture Models for Speech Recognition. IEEE Signal Process. Lett. 18(7): 419-422 (2011) - [c103]Liang Lu, Arnab Ghoshal, Steve Renals:
Regularized subspace Gaussian mixture models for cross-lingual speech recognition. ASRU 2011: 365-370 - [c102]João P. Cabral, Steve Renals, Junichi Yamagishi, Korin Richmond:
HMM-based speech synthesiser using the LF-model of the glottal source. ICASSP 2011: 4704-4707 - 2010
- [j28]Heriberto Cuayáhuitl, Steve Renals, Oliver Lemon, Hiroshi Shimodaira:
Evaluation of a hierarchical reinforcement learning spoken dialogue system. Comput. Speech Lang. 24(2): 395-429 (2010) - [j27]Ravichander Vipperla, Steve Renals, Joe Frankel:
Ageing Voices: The Effect of Changes in Voice Parameters on ASR Performance. EURASIP J. Audio Speech Music. Process. 2010 (2010) - [j26]Songfang Huang, Steve Renals:
Hierarchical Bayesian Language Models for Conversational Speech Recognition. IEEE Trans. Speech Audio Process. 18(8): 1941-1954 (2010) - [c101]Erich Zwyssig, Mike Lincoln, Steve Renals:
A digital microphone array for distant speech recognition. ICASSP 2010: 5106-5109 - [c100]Songfang Huang, Steve Renals:
Power law discounting for n-gram language models. ICASSP 2010: 5178-5181 - [c99]Jonathan Kilgour, Jean Carletta, Steve Renals:
The Ambient Spotlight: personal multimodal search without query. ICMI-MLMI 2010: 12:1-12:2 - [c98]Ravichander Vipperla, Steve Renals, Joe Frankel:
Augmentation of adaptation data. INTERSPEECH 2010: 530-533 - [c97]Jonathan Kilgour, Jean Carletta, Steve Renals:
The ambient spotlight: queryless desktop search from meeting speech. SSCS@MM 2010: 49-52 - [c96]Steve Renals:
Invited Talk: Recognition and Understanding of Meetings. HLT-NAACL 2010: 1-9 - [c95]Maria K. Wolters, Karl Isaac, Steve Renals:
Evaluating speech synthesis intelligibility using Amazon Mechanical Turk. SSW 2010: 136-141 - [c94]João P. Cabral, Steve Renals, Korin Richmond, Junichi Yamagishi:
An HMM-based speech synthesiser using glottal post-filtering. SSW 2010: 365-370
2000 – 2009
- 2009
- [j25]Yasser Hifny, Steve Renals:
Speech Recognition Using Augmented Conditional Random Fields. IEEE Trans. Speech Audio Process. 17(2): 354-365 (2009) - [j24]Junichi Yamagishi, Takashi Nose, Heiga Zen, Zhen-Hua Ling, Tomoki Toda, Keiichi Tokuda, Simon King, Steve Renals:
Robust Speaker-Adaptive HMM-Based Text-to-Speech Synthesis. IEEE Trans. Speech Audio Process. 17(6): 1208-1230 (2009) - [j23]Gabriel Murray, Thomas Kleinbauer, Peter Poller, Tilman Becker, Steve Renals, Jonathan Kilgour:
Extrinsic summarization evaluation: A decision audit task. ACM Trans. Speech Lang. Process. 6(2): 2:1-2:29 (2009) - [c93]Ravichander Vipperla, Maria Klara Wolters, Kallirroi Georgila, Steve Renals:
Speech Input from Older Users in Smart Environments: Challenges and Perspectives. HCI (6) 2009: 117-126 - [c92]Maria Klara Wolters, Ravichander Vipperla, Steve Renals:
Age recognition for spoken dialogue systems: do we need it? INTERSPEECH 2009: 1435-1438 - [c91]Songfang Huang, Steve Renals:
A parallel training algorithm for hierarchical pitman-yor process language models. INTERSPEECH 2009: 2695-2698 - 2008
- [j22]Le Zhang, Stephen Renals:
Acoustic-Articulatory Modeling With the Trajectory HMM. IEEE Signal Process. Lett. 15: 245-248 (2008) - [j21]Heidi Christensen, Yoshihiko Gotoh, Steve Renals:
A Cascaded Broadcast News Highlighter. IEEE Trans. Speech Audio Process. 16(1): 151-161 (2008) - [j20]Giulia Garau, Steve Renals:
Combining Spectral Representations for Large-Vocabulary Continuous Speech Recognition. IEEE Trans. Speech Audio Process. 16(3): 508-518 (2008) - [j19]Alfred Dielmann, Steve Renals:
Recognition of Dialogue Acts in Multiparty Meetings Using a Switching DBN. IEEE Trans. Speech Audio Process. 16(7): 1303-1314 (2008) - [c90]Songfang Huang, Steve Renals:
Unsupervised language model adaptation based on topic and role information in multiparty meetings. INTERSPEECH 2008: 833-836 - [c89]João P. Cabral, Steve Renals, Korin Richmond, Junichi Yamagishi:
Glottal spectral separation for parametric speech synthesis. INTERSPEECH 2008: 1829-1832 - [c88]Chao Qin, Miguel Á. Carreira-Perpiñán, Korin Richmond, Alan Wrench, Steve Renals:
Predicting tongue shapes from a few landmark locations. INTERSPEECH 2008: 2306-2309 - [c87]Giulia Garau, Steve Renals:
Pitch adaptive features for LVCSR. INTERSPEECH 2008: 2402-2405 - [c86]Ravichander Vipperla, Steve Renals, Joe Frankel:
Longitudinal study of ASR performance on ageing voices. INTERSPEECH 2008: 2550-2553 - [c85]Gabriel Murray, Steve Renals:
Detecting Action Items in Meetings. MLMI 2008: 208-213 - [c84]Songfang Huang, Steve Renals:
Modeling Topic and Role Information in Meetings Using the Hierarchical Dirichlet Process. MLMI 2008: 214-225 - [c83]Gabriel Murray, Steve Renals:
Meta Comments for Summarizing Meeting Speech. MLMI 2008: 236-247 - [c82]Gabriel Murray, Thomas Kleinbauer, Peter Poller, Steve Renals, Jonathan Kilgour, Tilman Becker:
Extrinsic Summarization Evaluation: A Decision Audit Task. MLMI 2008: 349-361 - [e4]Andrei Popescu-Belis, Steve Renals, Hervé Bourlard:
Machine Learning for Multimodal Interaction , 4th International Workshop, MLMI 2007, Brno, Czech Republic, June 28-30, 2007, Revised Selected Papers. Lecture Notes in Computer Science 4892, Springer 2008, ISBN 978-3-540-78154-7 [contents] - 2007
- [j18]Alfred Dielmann, Steve Renals:
Automatic Meeting Segmentation Using Dynamic Bayesian Networks. IEEE Trans. Multim. 9(1): 25-36 (2007) - [c81]Songfang Huang, Steve Renals:
Hierarchical Pitman-Yor language models for ASR in meetings. ASRU 2007: 124-129 - [c80]Steve Renals, Thomas Hain, Hervé Bourlard:
Recognition and understanding of meetings the AMI and AMIDA projects. ASRU 2007: 238-247 - [c79]Alfred Dielmann, Steve Renals:
DBN Based Joint Dialogue Act Recognition of Multiparty Meetings. ICASSP (4) 2007: 133-136 - [c78]Heriberto Cuayáhuitl, Steve Renals, Oliver Lemon, Hiroshi Shimodaira:
Hierarchical dialogue optimization using semi-Markov decision processes. INTERSPEECH 2007: 2693-2696 - [c77]Gabriel Murray, Steve Renals:
Towards online speech summarization. INTERSPEECH 2007: 2785-2788 - [c76]Gabriel Murray, Steve Renals:
Term-Weighting for Summarization of Multi-party Spoken Dialogues. MLMI 2007: 156-167 - [c75]Songfang Huang, Steve Renals:
Using Prosodic Features in Language Models for Meetings. MLMI 2007: 192-203 - [c74]Gabriel Murray, Pei-Yun Hsueh, Simon Tucker, Jonathan Kilgour, Jean Carletta, Johanna D. Moore, Steve Renals:
Automatic Segmentation and Summarization of Meeting Speech. HLT-NAACL (Demonstrations) 2007: 9-10 - [c73]João P. Cabral, Steve Renals, Korin Richmond, Junichi Yamagishi:
Towards an improved modeling of the glottal source in statistical parametric speech synthesis. SSW 2007: 113-118 - [c72]Junichi Yamagishi, Takao Kobayashi, Steve Renals, Simon King, Heiga Zen, Tomoki Toda, Keiichi Tokuda:
Improved average-voice-based speech synthesis using gender-mixed modeling and a parameter generation algorithm considering GV. SSW 2007: 125-130 - 2006
- [c71]Pei-Yun Hsueh, Johanna D. Moore, Steve Renals:
Automatic Segmentation of Multiparty Dialogue. EACL 2006 - [c70]Heriberto Cuayáhuitl, Steve Renals, Oliver Lemon, Hiroshi Shimodaira:
Learning multi-goal dialogue strategies using reinforcement learning with reduced state-action spaces. INTERSPEECH 2006 - [c69]Gabriel Murray, Steve Renals:
Dialogue act compression via pitch contour preservation. INTERSPEECH 2006 - [c68]Le Zhang, Steve Renals:
Phone recognition analysis for trajectory HMM. INTERSPEECH 2006 - [c67]Marc A. Al-Hames, Thomas Hain, Jan Cernocký, Sascha Schreiber, Mannes Poel, Ronald Müller, Sébastien Marcel, David A. van Leeuwen, Jean-Marc Odobez, Sileye O. Ba, Hervé Bourlard, Fabien Cardinaux, Daniel Gatica-Perez, Adam Janin, Petr Motlícek, Stephan Reiter, Steve Renals, Jeroen van Rest, Rutger Rienks, Gerhard Rigoll, Kevin Smith, Andrew H. C. Thean, Pavel Zemcík:
Audio-Visual Processing in Meetings: Seven Questions and Current AMI Answers. MLMI 2006: 24-35 - [c66]Alfred Dielmann, Steve Renals:
Multistream Recognition of Dialogue Acts in Meetings. MLMI 2006: 178-189 - [c65]Gabriel Murray, Steve Renals, Jean Carletta, Johanna D. Moore:
Incorporating Speaker and Discourse Features into Speech Summarization. HLT-NAACL 2006 - [c64]Heriberto Cuayáhuitl, Steve Renals, Oliver Lemon, Hiroshi Shimodaira:
Reinforcement Learning of Dialogue Strategies with Hierarchical Abstract Machines. SLT 2006: 182-185 - [e3]Steve Renals, Samy Bengio:
Machine Learning for Multimodal Interaction, Second International Workshop, MLMI 2005, Edinburgh, UK, July 11-13, 2005, Revised Selected Papers. Lecture Notes in Computer Science 3869, Springer 2006, ISBN 3-540-32549-2 [contents] - [e2]Steve Renals, Samy Bengio, Jonathan G. Fiscus:
Machine Learning for Multimodal Interaction, Third International Workshop, MLMI 2006, Bethesda, MD, USA, May 1-4, 2006, Revised Selected Papers. Lecture Notes in Computer Science 4299, Springer 2006, ISBN 3-540-69267-3 [contents] - 2005
- [j17]Jerry Goldman, Steve Renals, Steven Bird, Franciska de Jong, Marcello Federico, Carl Fleischhauer, Mark Kornbluh, Lori Lamel, Douglas W. Oard, Claire Stewart, Richard Wright:
Accessing the spoken word. Int. J. Digit. Libr. 5(4): 287-298 (2005) - [j16]Konstantinos Koumpis, Steve Renals:
Content-based access to spoken audio. IEEE Signal Process. Mag. 22(5): 61-69 (2005) - [j15]Stuart N. Wrigley, Guy J. Brown, Vincent Wan, Steve Renals:
Speech and crosstalk detection in multichannel audio. IEEE Trans. Speech Audio Process. 13(1): 84-91 (2005) - [j14]Vincent Wan, Steve Renals:
Speaker verification using sequence discriminant support vector machines. IEEE Trans. Speech Audio Process. 13(2): 203-210 (2005) - [j13]Konstantinos Koumpis, Steve Renals:
Automatic summarization of voicemail messages using lexical and prosodic features. ACM Trans. Speech Lang. Process. 2(1): 1-24 (2005) - [c63]Gabriel Murray, Steve Renals, Jean Carletta, Johanna D. Moore:
Evaluating Automatic Summaries of Meeting Recordings. IEEvaluation@ACL 2005: 33-40 - [c62]Heidi Christensen, BalaKrishna Kolluru, Yoshihiko Gotoh, Steve Renals:
Maximum entropy segmentation of broadcast news. ICASSP (1) 2005: 1029-1032 - [c61]Giulia Garau, Steve Renals, Thomas Hain:
Applying vocal tract length normalization to meeting recordings. INTERSPEECH 2005: 265-268 - [c60]Gabriel Murray, Steve Renals, Jean Carletta:
Extractive summarization of meeting recordings. INTERSPEECH 2005: 593-596 - [c59]Thomas Hain, John Dines, Giulia Garau, Martin Karafiát, Darren Moore, Vincent Wan, Roeland Ordelman, Steve Renals:
Transcription of conference room meetings: an investigation. INTERSPEECH 2005: 1661-1664 - [c58]Yasser Hifny, Steve Renals, Neil D. Lawrence:
A hybrid Maxent/HMM based ASR system. INTERSPEECH 2005: 3017-3020 - [c57]Marc A. Al-Hames, Alfred Dielmann, Daniel Gatica-Perez, Stephan Reiter, Steve Renals, Gerhard Rigoll, Dong Zhang:
Multimodal Integration for Meeting Group Action Segmentation and Recognition. MLMI 2005: 52-63 - [c56]Thomas Hain, Lukás Burget, John Dines, Iain McCowan, Giulia Garau, Martin Karafiát, Mike Lincoln, Darren Moore, Vincent Wan, Roeland Ordelman, Steve Renals:
The Development of the AMI System for the Transcription of Speech in Meetings. MLMI 2005: 344-356 - [c55]Thomas Hain, Lukás Burget, John Dines, Giulia Garau, Martin Karafiát, Mike Lincoln, Iain McCowan, Darren Moore, Vincent Wan, Roeland Ordelman, Steve Renals:
The 2005 AMI System for the Transcription of Speech in Meetings. MLMI 2005: 450-462 - 2004
- [c54]Heidi Christensen, BalaKrishna Kolluru, Yoshihiko Gotoh, Steve Renals:
From Text Summarisation to Style-Specific Summarisation for Broadcast News. ECIR 2004: 223-237 - [c53]Alfred Dielmann, Steve Renals:
Dynamic Bayesian networks for meeting structuring. ICASSP (5) 2004: 629-632 - [c52]Yasser H. Abdel-Haleem, Steve Renals, Neil D. Lawrence:
Acoustic space dimensionality selection and combination using the maximum entropy principle. ICASSP (5) 2004: 637-640 - [c51]Alfred Dielmann, Steve Renals:
Multistream Dynamic Bayesian Network for Meeting Segmentation. MLMI 2004: 76-86 - [c50]Alfred Dielmann, Steve Renals:
Multi-stream segmentation of meetings. MMSP 2004: 167-170 - 2003
- [c49]Vincent Wan, Steve Renals:
SVMSVM: support vector machine speaker verification methodology. ICASSP (2) 2003: 221-224 - [c48]Steve Renals, Dan Ellis:
Audio information access from meeting rooms. ICASSP (4) 2003: 744-747 - [c47]Stuart N. Wrigley, Guy J. Brown, Vincent Wan, Steve Renals:
Feature selection for the classification of crosstalk in multi-channel audio. INTERSPEECH 2003: 469-472 - [c46]Konstantinos Koumpis, Steve Renals:
Multi-class extractive voicemail summarization. INTERSPEECH 2003: 2785-2788 - [e1]Steve Renals, Gregory Grefenstette:
Text- and Speech-Triggered Information Access, 8th ELSNET Summer School, Chios Island, Greece, July 15-30, 2000, Revised Lectures. Lecture Notes in Computer Science 2705, Springer 2003, ISBN 3-540-40635-2 [contents] - 2002
- [j12]Anthony J. Robinson, Gary D. Cook, Daniel P. W. Ellis, Eric Fosler-Lussier, Steve Renals, D. A. G. Williams:
Connectionist speech recognition of Broadcast News. Speech Commun. 37(1-2): 27-45 (2002) - [c45]Olivier Pietquin, Steve Renals:
ASR system modeling for automatic evaluation and optimization of dialogue systems. ICASSP 2002: 45-48 - [c44]Vincent Wan, Steve Renals:
Evaluation of kernel methods for speaker verification and identification. ICASSP 2002: 669-672 - 2001
- [c43]Konstantinos Koumpis, Charalampos V. Ladas, Steve Renals:
An Advanced Integrated Architecture for Wireless Voicemail Data Retrieval. ICOIN 2001: 403-410 - [c42]Konstantinos Koumpis, Steve Renals, Mahesan Niranjan:
Extractive summarization of voicemail using lexical and prosodic feature subset selection. INTERSPEECH 2001: 2377-2380 - 2000
- [j11]Miguel Á. Carreira-Perpiñán, Steve Renals:
Practical Identifiability of Finite Mixtures of Multivariate Bernoulli Distributions. Neural Comput. 12(1): 141-152 (2000) - [j10]Steve Renals, Tony Robinson:
Accessing information in spoken audio. Speech Commun. 32(1-2): 1-3 (2000) - [j9]Steve Renals, Dave Abberley, David Kirby, Tony Robinson:
Indexing and retrieval of broadcast news. Speech Commun. 32(1-2): 5-20 (2000) - [c41]Gregory Grefenstette, Steve Renals:
Text- and Speech-Triggered Information Access: Introduction. ELSNET Summer School 2000: 1-5 - [c40]Yoshihiko Gotoh, Steve Renals:
Statistical Language Modelling. ELSNET Summer School 2000: 78-105 - [c39]Yoshihiko Gotoh, Steve Renals:
Variable word rate N-grams. ICASSP 2000: 1591-1594 - [c38]Konstantinos Koumpis, Steve Renals:
Transcription and summarization of voicemail speech. INTERSPEECH 2000: 688-691 - [c37]Steve Renals, Dave Abberley:
The Thisl SDR System at TREC-9. TREC 2000 - [i2]Yoshihiko Gotoh, Steve Renals:
Variable Word Rate N-grams. CoRR cs.CL/0003081 (2000) - [i1]Yoshihiko Gotoh, Steve Renals:
Information Extraction from Broadcast News. CoRR cs.CL/0003084 (2000)
1990 – 1999
- 1999
- [j8]Gethin Williams, Steve Renals:
Confidence measures from local posterior probability estimates. Comput. Speech Lang. 13(4): 395-411 (1999) - [j7]Yoshihiko Gotoh, Steve Renals:
Topic-based mixture language modelling. Nat. Lang. Eng. 5(4): 355-375 (1999) - [j6]Steve Renals, Mike Hochberg:
Start-synchronous search for large vocabulary continuous speech recognition. IEEE Trans. Speech Audio Process. 7(5): 542-553 (1999) - [c36]Yoshihiko Gotoh, Steve Renals, Gethin Williams:
Named entity tagged language models. ICASSP 1999: 513-516 - [c35]Steve Renals:
The THISL Spoken Document Retrieval Project. ICMCS, Vol. 2 1999: 1049-1051 - [c34]Steve Renals, Yoshihiko Gotoh:
Integrated transcription and identification of named entities in broadcast speech. EUROSPEECH 1999: 1039-1042 - [c33]Tony Robinson, Dave Abberley, David Kirby, Steve Renals:
Recognition, indexing and retrieval of british broadcast news with the THISL system. EUROSPEECH 1999: 1267-1270 - [c32]Steve Renals, Dave Abberley, David Kirby, Tony Robinson:
The THISL system for indexing and retrieval of broadcast news. MMSP 1999: 77-82 - [c31]Dave Abberley, Steve Renals, Dan Ellis, Anthony J. Robinson:
The THISL SDR System At TREC-8. TREC 1999 - 1998
- [j5]Miguel Á. Carreira-Perpiñán, Steve Renals:
Dimensionality reduction of electropalatographic data using latent variable models. Speech Commun. 26(4): 259-282 (1998) - [c30]David C. Abberley, Steve Renals, Gary D. Cook:
Retrieval of broadcast news documents with the THISL system. ICASSP 1998: 3781-3784 - [c29]Jon Barker, Gethin Williams, Steve Renals:
Acoustic confidence measures for segmenting broadcast news. ICSLP 1998 - [c28]Gethin Williams, Steve Renals:
Confidence measures derived from an acceptor HMM. ICSLP 1998 - [c27]Dave Abberley, Steve Renals, Gary D. Cook, Anthony J. Robinson:
Retrieval Of Broadcast News Documents With the THISL System. TREC 1998: 128-137 - 1997
- [c26]Yoshihiko Gotoh, Steve Renals:
Document space models using latent semantic analysis. EUROSPEECH 1997: 1443-1446 - [c25]Jean Hennebert, Christophe Ris, Hervé Bourlard, Steve Renals, Nelson Morgan:
Estimation of global posteriors and forward-backward training of hybrid HMM/ANN systems. EUROSPEECH 1997: 1951-1954 - [c24]Gethin Williams, Steve Renals:
Confidence measures for hybrid HMM/ANN speech recognition. EUROSPEECH 1997: 1955-1958 - [c23]Dave Abberley, Steve Renals, Gary D. Cook, Anthony J. Robinson:
The THISL Spoken Document Retrieval System. TREC 1997: 747-752 - 1996
- [j4]Steve Renals:
Phone deactivation pruning in large vocabulary continuous speech recognition. IEEE Signal Process. Lett. 3(1): 4-6 (1996) - [c22]Steve Renals, Mike Hochberg:
Efficient evaluation of the LVCSR search space using the NOWAY decoder. ICASSP 1996: 149-152 - [c21]Dan J. Kershaw, Tony Robinson, Steve Renals:
The 1995 abbot LVCSR system for multiple unknown microphones. ICSLP 1996: 1325-1328 - 1995
- [c20]Michael M. Hochberg, Steve Renals, Anthony J. Robinson, Gary D. Cook:
Recent improvements to the ABBOT large vocabulary CSR system. ICASSP 1995: 69-72 - [c19]Tony Robinson, Jeroen Fransen, David Pye, Jonathan Foote, Steve Renals:
WSJCAMO: a British English speech corpus for large vocabulary continuous speech recognition. ICASSP 1995: 81-84 - [c18]Steve Renals, Mike Hochberg:
Efficient search using posterior phone probability estimates. ICASSP 1995: 596-599 - [c17]João Paulo Neto, Luís B. Almeida, Mike Hochberg, Ciro Martins, Luís Nunes, Steve Renals, Tony Robinson:
Speaker-adaptation for hybrid HMM-ANN continuous speech recognition system. EUROSPEECH 1995: 2171-2174 - 1994
- [j3]Steve Renals, Nelson Morgan, Hervé Bourlard, Michael Cohen, Horacio Franco:
Connectionist probability estimators in HMM speech recognition. IEEE Trans. Speech Audio Process. 2(1): 161-174 (1994) - [c16]Tony Robinson, Mike Hochberg, Steve Renals:
IPA: improved phone modelling with recurrent neural networks. ICASSP (1) 1994: 37-40 - [c15]Steve Renals, Mike Hochberg:
Using gamma filters to model temporal dependencies in speech. ICSLP 1994: 1491-1494 - [c14]Mike Hochberg, Steve Renals, Anthony J. Robinson, Dan J. Kershaw:
Large vocabulary continuous speech recognition using a hybrid connectionist-HMM system. ICSLP 1994: 1499-1502 - 1993
- [j2]Nelson Morgan, Hervé Bourlard, Steve Renals, Michael Cohen, Horacio Franco:
Hybrid Neural Network/Hidden Markov Model Systems for Continuous Speech Recognition. Int. J. Pattern Recognit. Artif. Intell. 7(4): 899-916 (1993) - [c13]Steve Renals, David J. C. MacKay:
Bayesian regularisation methods in a hybrid MLP-HMM system. EUROSPEECH 1993: 1719-1722 - [c12]Tony Robinson, Luís B. Almeida, Jean-Marc Boite, Hervé Bourlard, Frank Fallside, Mike Hochberg, Dan J. Kershaw, Phil Kohn, Yochai Konig, Nelson Morgan, João Paulo Neto, Steve Renals, Marco Saerens, Chuck Wooters:
A neural network based, speaker independent, large vocabulary, continuous speech recognition system: the WERNICKE project. EUROSPEECH 1993: 1941-1944 - [c11]Steve Renals, Mike Hochberg, Anthony J. Robinson:
Learning Temporal Dependencies in Connectionist Speech Recognition. NIPS 1993: 1051-1058 - 1992
- [j1]Hervé Bourlard, Nelson Morgan, Steve Renals:
Neural nets and hidden Markov models: Review and generalizations. Speech Commun. 11(2-3): 237-246 (1992) - [c10]Hervé Bourlard, Nelson Morgan, Chuck Wooters, Steve Renals:
CDNN: a context dependent neural network for continuous speech recognition. ICASSP 1992: 349-352 - [c9]Steve Renals, Nelson Morgan, Michael Cohen, Horacio Franco:
Connectionist probability estimation in the DECIPHER speech recognition system. ICASSP 1992: 601-604 - 1991
- [c8]Steve Renals, David McKelvie, Fergus McInnes:
A comparative study of continuous speech recognition using neural networks and hidden Markov models. ICASSP 1991: 369-372 - [c7]Steve Renals, Nelson Morgan, Hervé Bourlard, Horacio Franco, Michael Cohen:
Connectionist Optimisation of Tied Mixture Hidden Markov Models. NIPS 1991: 167-174 - 1990
- [b1]Stephen Renals:
Speech and neural network dynamics. University of Edinburgh, UK, 1990 - [c6]Steve Renals:
Chaos in Neural Networks. EURASIP Workshop 1990: 90-99
1980 – 1989
- 1989
- [c5]Steve Renals, Richard Rohwer:
Learning phoneme recognition using neural networks. ICASSP 1989: 413-416 - [c4]Steve Renals, Jonathan Dalby:
Analysis of a neural network model for speech recognition. EUROSPEECH 1989: 1333-1336 - 1988
- [c3]Richard Rohwer, Stephen Renals, Mark Terry:
Unstable connectionist networks in speech recognition. ICASSP 1988: 426-428 - [c2]Mark Terry, Stephen Renals, Richard Rohwer, Jonathan Harrington:
A connectionist approach to speech recognition using peripheral auditory modelling. ICASSP 1988: 699-702 - 1987
- [c1]Stephen Renals, Mark Terry:
Automatic speech recognition using peripheral auditory modelling and a PDP approach to classification. ECST 1987: 2077
Coauthor Index
[i45] [j49] [j48] [c209] [c208] [c206] [c205] [c204] [c203] [c201] [c200] [i44] [c198] [c197] [c195] [c193] [c192] [c191] [c190] [c188] [i39] [i37] [i35] [i34] [i33] [i32] [c187] [c186] [c185] [c182] [c181] [c179] [c178] [c177] [c176] [i29] [i28] [i24] [i23] [i22] [i21] [i20] [c172] [i19] [j43] [c171] [c170] [c168] [c167] [c165] [c163] [c162] [i15] [c157] [c156] [c155] [c153] [c152] [i9] [c151] [c150] [c149] [c148] [c140] [c139] [i5] [c134] [c129] [c123] [c120] [c119] [c117] [c115] [c114] [c106] [c104]
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-10-07 22:07 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
