Skip to main content
SpringerLink
Log in

Distant Speech Recognition Experiments Using the AMI Corpus

  • Chapter
  • First Online:
New Era for Robust Speech Recognition

Abstract

This chapter reviews distant speech recognition experimentation using the AMI corpus of multiparty meetings. The chapter compares conventional approaches using microphone array beamforming followed by single-channel acoustic modelling with approaches which combine multichannel signal processing with acoustic modelling in the context of convolutional networks.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 149.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 199.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 199.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    Mics 1 and 5 were used in the 2-mic case; mics 1, 3, 5 and 7 in the 4-mic case.

  2. 2.

    However, since the networks were being tasked with additional processing, it may be that deeper architectures would be more suitable.

  3. 3.

    The convolution of two vectors of size X and Y may result either in a vector of size X + Y − 1 for a full convolution with zero-padding of non-overlapping regions, or a vector of size X − Y + 1 for a valid convolution where only the points which overlap completely are considered.

References

  1. Abdel-Hamid, O., Mohamed, A.R., Hui, J., Penn, G.: Applying convolutional neural networks concepts to hybrid NN–HMM model for speech recognition. In: Proceedings of the IEEE ICASSP, pp. 4277–4280 (2012)

    Google Scholar 

  2. Abdel-Hamid, O., Deng, L., Yu, D.: Exploring convolutional neural network structures and optimization techniques for speech recognition. In: Proceedings of the ICSA Interspeech (2013)

    Google Scholar 

  3. Adcock, J., Gotoh, Y., Mashao, D., Silverman, H.: Microphone-array speech recognition via incremental MAP training. In: Proceedings of the IEEE ICASSP, pp. 897–900 (1996)

    Google Scholar 

  4. Anastasakos, T., McDonough, J., Schwartz, R., Makhoul, J.: A compact model for speaker-adaptive training. In: Proceedings of the ICSLP, pp. 1137–1140 (1996)

    Google Scholar 

  5. Anguera, X., Wooters, C., Hernando, J.: Acoustic beamforming for speaker diarization of meetings. IEEE Trans. Audio Speech Lang. Process. 15, 2011–2021 (2007)

    Article  Google Scholar 

  6. Carletta, J., Lincoln, M.: Data collection. In: Renals, S., Bourlard, H., Carletta, J., Popescu-Belis, A. (eds.) Multimodal Signal Processing: Human Interactions in Meetings, chap. 2, pp. 11–27. Cambridge University Press, Cambridge (2012)

    Chapter  Google Scholar 

  7. Carletta, J., Ashby, S., Bourban, S., Flynn, M., Guillemot, M., Hain, T., Kadlec, J., Karaiskos, V., Kraaij, W., Kronenthal, M., Lathoud, G., Lincoln, M., Lisowska, A., McCowan, I., Post, W., Reidsma, D., Wellner, P.: The AMI meeting corpus: a pre-announcement. In: Proceedings of the Machine Learning for Multimodal Interaction (MLMI), pp. 28–39 (2005)

    Google Scholar 

  8. Carletta, J., Evert, S., Heid, U., Kilgour, J.: The NITE XML toolkit: data model and query language. Lang. Resour. Eval. 39, 313–334 (2005)

    Article  Google Scholar 

  9. Fiscus, J., Ajot, J., Radde, N., Laprun, C.: Multiple dimension Levenshtein edit distance calculations for evaluating ASR systems during simultaneous speech. In: Proceedings of the LREC (2006)

    Google Scholar 

  10. Gales, M.: Semi-tied covariance matrices for hidden Markov models. IEEE Trans. Speech Audio Process. 7(3), 272–281 (1999)

    Article  Google Scholar 

  11. Ghoshal, A., Swietojanski, P., Renals, S.: Multilingual training of deep neural networks. In: Proceedings of the IEEE ICASSP (2013)

    Book  Google Scholar 

  12. Grezl, F., Karafiat, M., Kontar, S., Cernocky, J.: Probabilistic and bottle-neck features for LVCSR of meetings. In: Proceedings of IEEE ICASSP, pp. IV-757–IV-760 (2007)

    Google Scholar 

  13. Haeb-Umbach, R., Ney, H.: Linear discriminant analysis for improved large vocabulary continuous speech recognition. In: Proceedings of the IEEE ICASSP, pp. 13–16 (1992). http://dl.acm.org/citation.cfm?id=1895550.1895555

  14. Hain, T., Burget, L., Dines, J., Garner, P., Grézl, F., El Hannani, A., Karafíat, M., Lincoln, M., Wan, V.: Transcribing meetings with the AMIDA systems. IEEE Trans. Audio Speech Lang. Process. 20, 486–498 (2012)

    Article  Google Scholar 

  15. Janin, A., Baron, D., Edwards, J., Ellis, D., Gelbart, D., Morgan, N., Peskin, B., Pfau, T., Shriberg, E., Stolcke, A., Wooters, C.: The ICSI meeting corpus. In: Proceedings of the IEEE ICASSP, pp. I-364–I-367 (2003)

    Google Scholar 

  16. Lang, K., Waibel, A., Hinton, G.: A time-delay neural network architecture for isolated word recognition. Neural Netw. 3, 23–43 (1990)

    Article  Google Scholar 

  17. LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998)

    Article  Google Scholar 

  18. Lincoln, M., McCowan, I., Vepa, J., Maganti, H.: The multi-channel Wall Street Journal audio visual corpus (MC-WSJ-AV): specification and initial experiments. In: Proceedings of the IEEE ASRU (2005)

    Google Scholar 

  19. Marino, D., Hain, T.: An analysis of automatic speech recognition with multiple microphones. In: Proceedings of the Interspeech, pp. 1281–1284 (2011)

    Google Scholar 

  20. Omologo, M., Matassoni, M., Svaizer, P., Giuliani, D.: Microphone array based speech recognition with different talker-array positions. In: Proceedings of the IEEE ICASSP, pp. 227–230 (1997)

    Google Scholar 

  21. Povey, D., Woodland, P.: Minimum phone error and I-smoothing for improved discriminative training. In: Proceedings of the IEEE ICASSP, pp. 105–108 (2002)

    Google Scholar 

  22. Renals, S., Swietojanski, P.: Neural networks for distant speech recognition. In: Proceedings of the HSCMA (2014)

    Book  Google Scholar 

  23. Sainath, T., Kingsbury, B., Mohamed, A., Dahl, G., Saon, G., Soltau, H., Beran, T., Aravkin, A., Ramabhadran, B.: Improvements to deep convolutional neural networks for LVCSR. In: Proceedings of the IEEE ASRU (2013)

    Book  Google Scholar 

  24. Seltzer, M., Stern, R.: Subband likelihood-maximizing beamforming for speech recognition in reverberant environments. IEEE Trans. Audio Speech Lang. Process. 14, 2109–2121 (2006)

    Article  Google Scholar 

  25. Seltzer, M., Raj, B., Stern, R.: Likelihood-maximizing beamforming for robust hands-free speech recognition. IEEE Trans. Speech Audio Process. 12, 489–498 (2004)

    Article  Google Scholar 

  26. Stolcke, A., Anguera, X., Boakye, K., Cetin, O., Janin, A., Magimai-Doss, M., Wooters, C., Zheng, J.: The SRI-ICSI spring 2007 meeting and lecture recognition system. In: Stiefelhagen, R., Bowers, R., Fiscus, J. (eds.) Multimodal Technologies for Perception of Humans. Lecture Notes in Computer Science, vol. 4625, pp. 373–389. Springer, New York (2008)

    Chapter  Google Scholar 

  27. Swietojanski, P., Ghoshal, A., Renals, S.: Hybrid acoustic models for distant and multichannel large vocabulary speech recognition. In: Proceedings of the IEEE ASRU (2013). doi:10.1109/ASRU.2013.6707744

    Google Scholar 

  28. Swietojanski, P., Ghoshal, A., Renals, S.: Convolutional neural networks for distant speech recognition. IEEE Signal Process. Lett. 21, 1120–1124 (2014)

    Article  Google Scholar 

  29. Van Compernolle, D., Ma, W., Xie, F., Van Diest, M.: Speech recognition in noisy environments with the aid of microphone arrays. Speech Commun. 9, 433–442 (1990)

    Article  Google Scholar 

  30. Wölfel, M., McDonough, J.: Distant Speech Recognition. Wiley, Chichester (2009)

    Book  Google Scholar 

  31. Zwyssig, E., Lincoln, M., Renals, S.: A digital microphone array for distant speech recognition. In: Proceedings of the IEEE ICASSP, pp. 5106–5109 (2010). doi:10.1109/ICASSP.2010.5495040

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK

    Steve Renals & Pawel Swietojanski

Authors
  1. Steve Renals
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Pawel Swietojanski
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Steve Renals .

Editor information

Editors and Affiliations

  1. Mitsubishi Electric Research Laboratories (MERL), Cambridge, Massachusetts, USA

    Shinji Watanabe

  2. NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan

    Marc Delcroix

  3. Language Technologies Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA

    Florian Metze

  4. Mitsubishi Electric Research Laboratories (MERL), Cambridge, Massachusetts, USA

    John R. Hershey

Rights and permissions

Reprints and permissions

Copyright information

© 2017 Springer International Publishing AG

About this chapter

Cite this chapter

Renals, S., Swietojanski, P. (2017). Distant Speech Recognition Experiments Using the AMI Corpus. In: Watanabe, S., Delcroix, M., Metze, F., Hershey, J. (eds) New Era for Robust Speech Recognition. Springer, Cham. https://doi.org/10.1007/978-3-319-64680-0_16

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-64680-0_16

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-64679-4

  • Online ISBN: 978-3-319-64680-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation