Edinburgh Research Explorer

Prof Stephen Renals

Chair of Speech Technology

  1. 2016
  2. 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

  3. 2015
  4. 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

  5. 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

  6. 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

  7. 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

  8. 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

  9. A Study of the Recurrent Neural Network Encoder-Decoder for Large Vocabulary Speech Recognition

    Lu, L., Zhang, X., Cho, K. & Renals, S., Sep 2015, INTERSPEECH 2015 16th Annual Conference of the International Speech Communication Association. p. 3249-3253 5 p.

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

  10. Prosodically-enhanced Recurrent Neural Network Language Models

    Gangireddy, S. R., Renals, S., Nankaku, Y. & Lee, A., Sep 2015, INTERSPEECH 2015 16th Annual Conference of the International Speech Communication Association. p. 2390-2394 5 p.

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

  11. Structured Output Layer with Auxiliary Targets for Context-Dependent Acoustic Modelling

    Swietojanski, P., Bell, P. & Renals, S., Sep 2015, INTERSPEECH 2015 16th Annual Conference of the International Speech Communication Association. International Speech Communication Association, p. 3605-3609 5 p.

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

  12. Regularization of context-dependent deep neural networks with context-independent multi-task training

    Bell, P. & Renals, S., 6 Aug 2015, Proc IEEE International Conference on Acoustics, Speech and Signal Processing. Brisbane, QLD, Australia: Institute of Electrical and Electronics Engineers (IEEE), p. 4290-4294 5 p.

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

  13. Multi-Reference Evaluation for Dialectal Speech Recognition System: A Study for Egyptian ASR

    Ali, A., Magdy, W. & Renals, S., 1 Aug 2015, Proceedings of the Second Workshop on Arabic Natural Language Processing. Association for Computational Linguistics, p. 118-126 9 p.

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

  14. Open Challenges in Modelling, Analysis and Synthesis of Human Behaviour in Human--Human and Human--Machine Interactions

    Vinciarelli, A., Esposito, A., André, E., Bonin, F., Chetouani, M., Cohn, J. F., Cristani, M., Fuhrmann, F., Gilmartin, E., Hammal, Z., Heylen, D., Kaiser, R., Koutsombogera, M., Potamianos, A., Renals, S., Riccardi, G. & Salah, A. A., Aug 2015, In : Cognitive Computation. 7, 4, p. 397-413 17 p.

    Research output: Contribution to journalArticle

  15. A system for automatic alignment of broadcast media captions using weighted finite-state transducers

    Bell, P. & Renals, S., 2015, 2015 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2015). Institute of Electrical and Electronics Engineers (IEEE), p. 675-680 6 p.

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

  16. Differentiable pooling for unsupervised speaker adaptation

    Swietojanski, P. & Renals, S., 2015, Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing. 5 p.

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

  17. Modelling acoustic feature dependencies with artificial neural networks: Trajectory-RNADE

    Uria, B., Murray, I., Renals, S., Valentini-Botinhao, C. & Bridle, J., 2015, Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on . IEEE Signal Processing Society Press, p. 4465-4469 5 p.

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

  18. Multi-frame factorisation for long-span acoustic modelling

    Lu, L. & Renals, S., 2015, Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing. 5 p.

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

  19. The MGB Challenge: Evaluating Multi-Genre Broadcast Media Recognition

    Bell, P., Gales, MJF., Hain, T., Kilgour, J., Lanchantin, P., Liu, X., McParland, A., Renals, S., Saz, O., Wester, M. & Woodland, PC., 2015, Automatic Speech Recognition and Understanding (ASRU), 2015 IEEE Workshop on. Institute of Electrical and Electronics Engineers (IEEE), p. 687 - 693 7 p.

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

  20. 2014
  21. Tied Probabilistic Linear Discriminant Analysis for Speech Recognition

    Lu, L. & Renals, S., 30 Nov 2014, (Submitted) 5 p.

    Research output: Working paper

  22. Probabilistic Linear Discriminant Analysis for Acoustic Modeling

    Lu, L. & Renals, S., 1 Jun 2014, In : IEEE Signal Processing Letters. 21, 6, p. 702-706 5 p.

    Research output: Contribution to journalArticle

  23. Neural net word representations for phrase-break prediction without a part of speech tagger

    Watts, O., Gangireddy, S., Yamagishi, J., King, S., Renals, S., Stan, A. & Giurgiu, M., 4 May 2014, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 2599-2603 5 p. 6854070

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

  24. Glottal spectral separation for speech synthesis

    Cabral, J., Richmond, K., Yamagishi, J. & Renals, S., Apr 2014, In : IEEE Journal of Selected Topics in Signal Processing. 8, 2, p. 195-208

    Research output: Contribution to journalArticle

  25. Automated Production of True-Cased Punctuated Subtitles for Weather and News Broadcasts

    Driesen, J., Birch, A., Grimsey, S., Safarfashandi, S., Gauthier, J., Simpson, M. & Renals, S., 2014, INTERSPEECH 2014 15th Annual Conference of the International Speech Communication Association. International Speech Communication Association, p. 2146-2147 2 p.

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

  26. Convolutional Neural Networks for Distant Speech Recognition

    Swietojanski, P., Ghoshal, A. & Renals, S., 2014, In : IEEE Signal Processing Letters. 21, 9, p. 1120-1124 5 p.

    Research output: Contribution to journalArticle

  27. Cross-Lingual Adaptation with Multi-Task Adaptive Networks

    Bell, P., Driesen, J. & Renals, S., 2014, INTERSPEECH 2014 15th Annual Conference of the International Speech Communication Association. International Speech Communication Association, p. 21-25 5 p.

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

  28. Cross-Lingual Subspace Gaussian Mixture Models for Low-Resource Speech Recognition

    Lu, L., Ghoshal, A. & Renals, S., 2014, In : IEEE/ACM Transactions on Audio, Speech, and Language Processing. 22, 1, p. 17-27 11 p.

    Research output: Contribution to journalArticle

  29. Feed Forward Pre-training for Recurrent Neural Network Language Models

    Gangireddy, S. R., McInnes, F. & Renals, S., 2014, INTERSPEECH 2014 15th Annual Conference of the International Speech Communication Association. International Speech Communication Association, p. 2620-2624 5 p.

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

  30. Incorporating Lexical and Prosodic Information at Different Levels for Meeting Summarization

    Lai, C. & Renals, S., 2014, Proceedings of Interspeech 2014. 5 p.

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

  31. Learning Hidden Unit Contributions for Unsupervised Speaker Adaptation of Neural Network Acoustic Models

    Swietojanski, P. & Renals, S., 2014, Spoken Language Technology Workshop (SLT), 2014 IEEE. Institute of Electrical and Electronics Engineers (IEEE), p. 171-176 6 p.

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

  32. Neural networks for distant speech recognition

    Renals, S. & Swietojanski, P., 2014, Proceedings 2014 Workshop on Hands-Free Speech Communication and Microphone Arrays . Institute of Electrical and Electronics Engineers (IEEE), p. 172-176 5 p.

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

  33. Probabilistic Linear Discriminant Analysis with Bottleneck Features for Speech Recognition

    Lu, L. & Renals, S., 2014, INTERSPEECH-2014. International Speech Communication Association, p. 910-914 5 p.

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

  34. ROCKIT: Roadmap for Conversational Interaction Technologies

    Renals, S., Carletta, J., Edwards, K., Bourlard, H., Garner, P. N., Popescu-Belis, A., Klakow, D., Girenko, A., Petukhova, V., Wacker, P., Joscelyne, A., Kompis, C., Aliwell, S., Stevens, W. & Sabbah, Y., 2014, RFMIR '14 Proceedings of the 2014 Workshop on Roadmapping the Future of Multimodal Interaction Research including Business Opportunities and Challenges. p. 39-42 4 p.

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

  35. The UEDIN ASR Systems for the IWSLT 2014 Evaluation

    Bell, P., Swietojanski, P., Driesen, J., Sinclair, M., McInnes, F. & Renals, S., 2014, 11th International Workshop on Spoken Language Translation (IWSLT 2014). 8 p.

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

  36. 2013
  37. Lightly supervised automatic subtitling of weather forecasts

    Driesen, J. & Renals, S., 1 Dec 2013, Automatic Speech Recognition and Understanding (ASRU), 2013 IEEE Workshop on. Institute of Electrical and Electronics Engineers (IEEE), p. 452-457 6 p.

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

  38. Recording speech articulation in dialogue: Evaluating a synchronized double electromagnetic articulography setup

    Geng, C., Turk, A., Scobbie, J. M., Macmartin, C., Hoole, P., Richmond, K., Wrench, A., Pouplier, M., Bard, E., Campbell, Z., Dickie, C., Dubourg, E., Hardcastle, W., Kainada, E., King, S., Lickley, R., Nakai, S., Renals, S., White, K. & Wiegand, R., Nov 2013, In : Journal of Phonetics. 41, 6, p. 421-431 11 p.

    Research output: Contribution to journalArticle

  39. Recognition of overlapping speech using digital MEMS microphone arrays

    Zwyssig, E., Faubel, F., Renals, S. & Lincoln, M., 21 Oct 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. p. 7068-7072 5 p. 6639033

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

  40. Joint Uncertainty Decoding for Noise Robust Subspace Gaussian Mixture Models

    Lu, L., Chin, K. K., Ghoshal, A. & Renals, S., Sep 2013, In : IEEE Transactions on Audio, Speech and Language Processing. 21, 9, p. 1791-1804 14 p.

    Research output: Contribution to journalArticle

  41. Noise adaptive training for subspace Gaussian mixture models

    Lu, L., Ghoshal, A. & Renals, S., 1 Aug 2013, Proceedings of Interspeech 2013. ISCA

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

  42. Processing and Linking Audio Events in Large Multimedia Archives: The EU inEvent Project

    Bourlard, H., Ferras, M., Pappas, N., Popescu-Belis, A., Renals, S., McInnes, F., Bell, P., Ingram, S. & Guillemot, M., Aug 2013, Proceedings of SLAM 2013 (First Workshop on Speech, Language and Audio in Multimedia). CEUR Workshop Proceedings, p. 3-8 6 p. (CEUR Workshop Proceedings; vol. 1012).

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

  43. Grapheme-to-phoneme conversion methods for minority language conditions

    Cao, M., Renals, S., Bell, P., Li, A. & Fang, Q., 1 Feb 2013, Proceedings of the 2012 International Conference on Speech Database and Assessments, Oriental COCOSDA 2012. Institute of Electrical and Electronics Engineers (IEEE), p. 151-156 6 p. 6422470

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

  44. A lecture transcription system combining neural network acoustic and language models

    Bell, P., Yamamoto, H., Swietojanski, P., Wu, Y., McInnes, F., Hori, C. & Renals, S., 2013, In Proc. Interspeech 2013.

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

  45. Acoustic Data-driven Pronunciation Lexicon for Large Vocabulary Speech Recognition

    Lu, L., Ghoshal, A. & Renals, S., 2013, Automatic Speech Recognition and Understanding (ASRU), 2013 IEEE Workshop on. Institute of Electrical and Electronics Engineers (IEEE)

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

  46. Automatic Transcription of Multi-genre Media Archives

    Lanchantin, P., Bell, P., Gales, M., Hain, T., Liu, X., Long, Y., Quinnell, J., Renals, S., Saz, O., Seigel, M., Swietojanski, P. & Woodland, P., 2013, SLAM 2013 Speech, Language and Audio in Multimedia: Proceedings of the First Workshop on Speech, Language and Audio in Multimedia. CEUR Workshop Proceedings, Vol. 1012. p. 26-31 6 p.

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

  47. Description of the UEDIN System for German ASR

    Driesen, J., Bell, P., Sinclair, M. & Renals, S., 2013, Proceedings of the 10th International Workshop on Spoken Language Translation (IWSLT 2013). 6 p.

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

  48. Detecting Summarization Hot Spots in Meetings Using Group Level Involvement and Turn-Taking Features

    Lai, C., Carletta, J. & Renals, S., 2013, Proceedings of Interspeech 2013. ISCA, p. 2723-2727 5 p.

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

  49. Hybrid acoustic models for distant and multichannel large vocabulary speech recognition

    Swietojanski, P., Ghoshal, A. & Renals, S., 2013, Automatic Speech Recognition and Understanding (ASRU), 2013 IEEE Workshop on. Institute of Electrical and Electronics Engineers (IEEE), p. 285-290 6 p.

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

  50. Modelling Participant Affect in Meetings with Turn-Taking Features

    Lai, C., Carletta, J. & Renals, S., 2013, Proceedings of WASSS 2013.

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

  51. Multi-level adaptive networks in tandem and hybrid ASR systems

    Bell, P., Swietojanski, P. & Renals, S., 2013, Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on. Institute of Electrical and Electronics Engineers (IEEE), p. 6975-6979 5 p.

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

  52. Multilingual training of deep neural networks

    Ghoshal, A., Swietojanski, P. & Renals, S., 2013, Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on. Institute of Electrical and Electronics Engineers (IEEE), p. 7319-7323 5 p.

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

  53. Revisiting Hybrid and GMM-HMM system combination techniques

    Swietojanski, P., Ghoshal, A. & Renals, S., 2013, Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers (IEEE), p. 6744-6748 5 p.

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

  54. Socio-material design for computer mediated social sensemaking

    Hartswood, M., Anderson, S., Wolters, M., Pagliari, C. & Renals, S., 2013, CHI’13 CHI Conference on Human Factors in Computing Systems. ACM, (Proc. CHI Workshop on Explorations in Social Interaction Design).

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