Edinburgh Research Explorer

Prof Stephen Renals

Chair of Speech Technology

  1. 2019
  2. Lattice-based lightly-supervised acoustic model training

    Fainberg, J., Klejch, O., Renals, S. & Bell, P., 19 Sep 2019, Proceedings Interspeech 2019. International Speech Communication Association, p. 1596-1600 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  3. On Learning Interpretable CNNs with Parametric Modulated Kernel-based Filters

    Loweimi, E., Bell, P. & Renals, S., 19 Sep 2019, Proceedings Interspeech 2019. International Speech Communication Association, p. 3480-3484 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  4. Synchronising audio and ultrasound by learning cross-modal embeddings

    Eshky, A., Ribeiro, M., Richmond, K. & Renals, S., 19 Sep 2019, INTERSPEECH 2019: Proceedings of the 20th Annual Conference of the International Speech Communication Association (ISCA). Graz, Austria: International Speech Communication Association, p. 4100-4104 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  5. Trainable Dynamic Subsampling for End-to-End Speech Recognition

    Zhang, S., Loweimi, E., Xu, Y., Bell, P. & Renals, S., 19 Sep 2019, Proceedings Interspeech 2019. International Speech Communication Association, p. 1413-1417 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  6. Ultrasound tongue imaging for diarization and alignment of child speech therapy sessions

    Ribeiro, M., Eshky, A., Richmond, K. & Renals, S., 19 Sep 2019, INTERSPEECH 2019: Proceedings of the 20th Annual Conference of the International Speech Communication Association (ISCA). Graz, Austria: International Speech Communication Association, p. 16-20 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  7. Untranscribed web audio for low resource speech recognition

    Carmantini, A., Bell, P. & Renals, S., 19 Sep 2019, Proceedings Interspeech 2019. International Speech Communication Association, p. 226-230 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  8. Acoustic model adaptation from raw waveforms with Sincnet

    Fainberg, J., Klejch, O., Loweimi, E., Bell, P. & Renals, S., 13 Sep 2019, (Accepted/In press) Proceedings of the 2019 IEEE Automatic Speech Recognition and Understanding Workshop. Institute of Electrical and Electronics Engineers (IEEE), 8 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  9. Embeddings for DNN speaker adaptive training

    Równicka, J., Bell, P. & Renals, S., 13 Sep 2019, (Accepted/In press) Proceedings of the 2019 IEEE Automatic Speech Recognition and Understanding Workshop. Institute of Electrical and Electronics Engineers (IEEE), 8 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  10. Speaker adaptive training using model agnostic meta-learning

    Klejch, O., Fainberg, J., Bell, P. & Renals, S., 13 Sep 2019, (Accepted/In press) Proceedings of the 2019 IEEE Automatic Speech Recognition and Understanding Workshop. Institute of Electrical and Electronics Engineers (IEEE), 8 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  11. The MGB-5 Challenge: Recognition and Dialect Identification of Dialectal Arabic Speech

    Ali, A., Shon, S., Samih, Y., Mubarak, H., Abdelali, A., Glass, J., Renals, S. & Choukri, K., 13 Sep 2019, (Accepted/In press) Proceedings of the 2019 IEEE Automatic Speech Recognition and Understanding Workshop. Institute of Electrical and Electronics Engineers (IEEE), 8 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  12. Dynamic Evaluation of Transformer Language Models

    Krause, B., Mbabazi, E., Murray, I. & Renals, S., 17 Apr 2019, 6 p.

    Research output: Working paper

  13. On the Usefulness of Statistical Normalisation of Bottleneck Features for Speech Recognition

    Loweimi, E., Bell, P. & Renals, S., 17 Apr 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Brighton, United Kingdom: Institute of Electrical and Electronics Engineers (IEEE), p. 3862-3866 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  14. Speaker-Independent Classification of Phonetic Segments from Raw Ultrasound in Child Speech

    Ribeiro, M. S., Eshky, A., Richmond, K. & Renals, S., 17 Apr 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Brighton, United Kingdom: Institute of Electrical and Electronics Engineers (IEEE), p. 1328-1332 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  15. Windowed Attention Mechanisms for Speech Recognition

    Zhang, S., Loweimi, E., Bell, P. & Renals, S., 17 Apr 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Brighton, United Kingdom: Institute of Electrical and Electronics Engineers (IEEE), p. 7100-7104 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  16. Analyzing deep CNN-based utterance embeddings for acoustic model adaptation

    Równicka, J., Bell, P. & Renals, S., 14 Feb 2019, 2018 IEEE Spoken Language Technology Workshop (SLT). Institute of Electrical and Electronics Engineers (IEEE), p. 235-241 7 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  17. 2018
  18. Dynamic Evaluation of Neural Sequence Models

    Krause, B., Mbabazi, E., Murray, I. & Renals, S., 1 Oct 2018, Proceedings of the 35th International Conference on Machine Learning. Dy, J. & Krause, A. (eds.). Stockholmsmässan, Stockholm Sweden: PMLR, Vol. 80. p. 2766-2775 10 p. (Proceedings of Machine Learning Research).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  19. Word Error Rate Estimation for Speech Recognition: e-WER

    Ali, A. & Renals, S., Jul 2018, Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Melbourne, Australia : Association for Computational Linguistics (ACL), p. 20-24 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  20. Hierarchical recurrent neural network for story segmentation using fusion of lexical and acoustic features

    Tsunoo, E., Klejch, O., Bell, P. & Renals, S., 25 Jan 2018, 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). Institute of Electrical and Electronics Engineers (IEEE), p. 525-532 9 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  21. Simplifying very deep convolutional neural network architectures for robust speech recognition

    Rownicka, J., Renals, S. & Bell, P., 25 Jan 2018, IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2017). Institute of Electrical and Electronics Engineers (IEEE), p. 236-243 9 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  22. Speech Recognition Challenge in the Wild: Arabic MGB-3

    Ali, A., Vogel, S. & Renals, S., 25 Jan 2018, IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2017). Institute of Electrical and Electronics Engineers (IEEE), p. 316-322 7 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  23. WERd: Using Social Text Spelling Variants for Evaluating Dialectal Speech Recognition

    Ali, A., Nakov, P., Bell, P. & Renals, S., 25 Jan 2018, IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2017). Institute of Electrical and Electronics Engineers (IEEE), p. 141-148 8 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  24. 2017
  25. Distant Speech Recognition Experiments Using the AMI Corpus

    Renals, S. & Swietojanski, P., 30 Oct 2017, New Era for Robust Speech Recognition: Exploiting Deep Learning. Springer, p. 355-368 14 p.

    Research output: Chapter in Book/Report/Conference proceedingChapter (peer-reviewed)

  26. End-to-end neural segmental models for speech recognition

    Hao, T., Lu, L., Kong, L., Gimpel, K., Livescu, K., Dyer, C., Smith, N. A. & Renals, S., 14 Sep 2017, In : IEEE Journal of Selected Topics in Signal Processing. 11, 8, p. 1254-1264 11 p.

    Research output: Contribution to journalArticle

  27. Factorised representations for neural network adaptation to diverse acoustic environments

    Fainberg, J., Renals, S. & Bell, P., 24 Aug 2017, Proceedings Interspeech 2017. p. 749-753 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  28. Hierarchical Recurrent Neural Network for Story Segmentation

    Tsunoo, E., Bell, P. & Renals, S., 24 Aug 2017, Proceedings Interspeech 2017. p. 2919-2923 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  29. Small-footprint highway deep neural networks for speech recognition

    LU, L. & Renals, S., Jul 2017, In : IEEE/ACM Transactions on Audio, Speech, and Language Processing. 25, 7, p. 1502-1511 10 p.

    Research output: Contribution to journalArticle

  30. Knowledge Distillation for Small-footprint Highway Networks

    Lu, L., Guo, M. & Renals, S., 19 Jun 2017, 2017 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP 2017). Institute of Electrical and Electronics Engineers (IEEE), p. 4280-4284 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  31. Sequence-to-Sequence Models for Punctuated Transcription Combing Lexical and Acoustic Features

    Klejch, O., Bell, P. & Renals, S., 19 Jun 2017, The 42nd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017). Institute of Electrical and Electronics Engineers (IEEE), p. 5700-5704 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  32. Multiplicative LSTM for sequence modelling

    Krause, B., Murray, I., Renals, S. & LU, L., 26 Apr 2017, International Conference on Learning Representations - ICLR 2017 - Workshop Track. p. 2872-2880 9 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  33. User Generated Dialogue Systems: uDialogue

    Tokuda, K., Lee, A., Nankaku, Y., Oura, K., Hashimoto, K., Yamamoto, D., Takumi, I., Uchiya, T., Tsutsumi, S., Renals, S. & Yamagishi, J., 21 Apr 2017, Human-Harmonized Information Technology, Volume 2: Horizontal Expansion. Nishida, T. (ed.). Tokyo: Springer Japan, p. 77-114 38 p.

    Research output: Chapter in Book/Report/Conference proceedingChapter

  34. The SUMMA Platform Prototype

    Liepins, R., Germann, U., Barzdins, G., Birch, A., Renals, S., Weber, S., Kreeft, P. V. D., Bourlard, H., Prieto, J., Klejch, O., Bell, P., Lazaridis, A., Mendes, A., Riedel, S., Almeida, M. S. C., Balage, P., Cohen, S., Dwojak, T., Garner, P., Giefer, A. & 25 others, Junczys-Dowmunt, M., Imrani, H., Nogueira, D., Ali, A., Miranda, S., Popescu-Belis, A., Werlen, L. M., Papasarantopoulos, N., Obamuyide, A., Jones, C., Dalvi, F., Vlachos, A., Wang, Y., Tong, S., Sennrich, R., Pappas, N., Narayan, S., Damonte, M., Durrani, N., Khurana, S., Abdelali, A., Sajjad, H., Vogel, S., Sheppey, D. & Hernon, C., 7 Apr 2017, Proceedings of the EACL 2017 Software Demonstrations. London. UK: Association for Computational Linguistics (ACL), p. 116–119 4 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  35. Punctuated Transcription of Multi-genre Broadcasts Using Acoustic and Lexical Approaches

    Klejch, O., Bell, P. & Renals, S., 9 Feb 2017, 2016 IEEE Workshop on Spoken Language Technology. Institute of Electrical and Electronics Engineers (IEEE), p. 433-440 8 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  36. The MGB-2 Challenge: Arabic Multi-Device Broadcast Media Recognition

    Ali, A., Bell, P., Glass, J., Messaoui, Y., Mubarak, H., Renals, S. & Zhang, Y., 9 Feb 2017, 2016 IEEE Workshop on Spoken Language Technology. Institute of Electrical and Electronics Engineers (IEEE), p. 279-284 6 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  37. Multitask learning of context-dependent targets in deep neural network acoustic models

    Bell, P., Swietojanski, P. & Renals, S., Feb 2017, In : IEEE/ACM Transactions on Audio, Speech, and Language Processing. 25, 2, p. 238 - 247 10 p.

    Research output: Contribution to journalArticle

  38. 2016
  39. Automatic Dialect Detection in Arabic Broadcast Speech

    Ali, A., Dehak, N., Cardinal, P., Khurana, S., Yella, S. H., Glass, J., Bell, P. & Renals, S., 12 Sep 2016, Interspeech 2016. p. 2934-2938 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  40. Improving Children's Speech Recognition through Out-of-Domain Data Augmentation

    Fainberg, J., Bell, P., Lincoln, M. & Renals, S., 12 Sep 2016, Interspeech 2016. p. 1598-1602 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  41. Just-in-time prepared captioning for live transmissions

    Simpson, M. N., Barrett, J., Bell, P. & Renals, S., 12 Sep 2016, IBC 2016 Conference. Amsterdam, Netherlands: IET, 9 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  42. Segmental Recurrent Neural Networks for End-to-end Speech Recognition

    Lu, L., Kong, L., Dyer, C., Smith, N. A. & Renals, S., 12 Sep 2016, Proceedings of Interspeech 2016. San Francisco, United States, p. 385-389 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  43. Small-footprint Deep Neural Networks with Highway Connections for Speech Recognition

    Lu, L. & Renals, S., 12 Sep 2016, Proceedings of Interspeech 2016. San Francisco, United States, 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  44. Unsupervised Adaptation of Recurrent Neural Network Language Models

    Gangireddy, S. R., Swietojanski, P., Bell, P. & Renals, S., 8 Sep 2016, Interspeech 2016. p. 2333-2337 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  45. Differentiable Pooling for Unsupervised Acoustic Model Adaptation

    Swietojanski, P. & Renals, S., Aug 2016, In : IEEE/ACM Transactions on Audio, Speech, and Language Processing. 24, 10, p. 1773-1784 12 p.

    Research output: Contribution to journalArticle

  46. Learning Hidden Unit Contributions for Unsupervised Acoustic Model Adaptation

    Swietojanski, P., Li, J. & Renals, S., May 2016, In : IEEE/ACM Transactions on Audio, Speech, and Language Processing. 24, 8, p. 1450-1463 14 p.

    Research output: Contribution to journalArticle

  47. SAT-LHUC: Speaker adaptive training for learning hidden unit contributions

    Swietojanski, P. & Renals, S., 1 Mar 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers (IEEE), p. 5010-5014 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  48. On training the recurrent neural network encoder-decoder for large vocabulary end-to-end speech recognition

    Lu, L., Zhang, X. & Renals, S., Mar 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers (IEEE), p. 5060-5064 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  49. Character-level neural translation for multilingual media monitoring in the SUMMA project

    Barzdins, G., Renals, S. & Gosko, D., 2016, Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016. European Language Resources Association (ELRA), p. 1789-1793 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  50. 2015
  51. Multi-reference WER for evaluating ASR for languages with no orthographic rule

    Ali, A., Magdy, W., Bell, P. & Renals, S., 13 Dec 2015, Proceedings of 2015 IEEE Automatic Speech Recognition and Understanding Workshop. Institute of Electrical and Electronics Engineers (IEEE), p. 576-580 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  52. On the Efficiency of Recurrent Neural Network Optimization Algorithms

    Krause, B., Lu, L., Murray, I. & Renals, S., Dec 2015, OPT2015 Optimization for Machine Learning at the Neural Information Processing Systems Conference, 2015. 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  53. Complementary tasks for context-dependent deep neural network acoustic models

    Bell, P. & Renals, S., 11 Sep 2015, INTERSPEECH 2015 16th Annual Conference of the International Speech Communication Association. p. 3610-3614 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  54. Feature-space Speaker Adaptation for Probabilistic Linear Discriminant Analysis Acoustic Models

    Lu, L. & Renals, S., 11 Sep 2015, INTERSPEECH 2015 16th Annual Conference of the International Speech Communication Association. p. 2862-2866 5 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  55. A study of speaker adaptation for DNN-based speech synthesis

    Wu, Z., Swietojanski, P., Veaux, C., Renals, S. & King, S., 6 Sep 2015, Proceedings of Interspeech 2015. International Speech Communication Association

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

Previous 1 2 3 4 5 Next