Speech and Crosstalk Detection for Robust Speech Recognition Using a Dual Microphone System

  • Mikhail Stolbov
  • Marina Tatarnikova
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8113)

Abstract

This paper proposes a practical speech detection technique for robust automatic speech recognition, suitable for use under various interference conditions. This technique consists of a dual microphone system and an algorithm for processing their signals. The microphone module is placed in the workplace of the target speaker. The module consists of two symmetrical supercardioid microphones directed in opposite directions. The algorithm of target speaker detection is proposed for this scheme. This algorithm makes it possible to implement spatial filtering of speakers. Experiments with real recordings demonstrate a significant reduction of speech recognition errors for the target speaker due to suppression of acoustic crosstalk. The main advantage of the proposed technique is simplicity of its use in a wide range of practical situations.

Keywords

speech activity detection multi-channel audio crosstalk 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Nasu, Y., Shinoda, K., Furui, S.: Cross-Channel Spectral Subtraction for meeting speech recognition. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011, Prague Congress Center, Prague, Czech Republic, May 22-27, pp. 4812–4815. IEEE (2011)Google Scholar
  2. 2.
    Cao, Y., Sridman, S., Moody, M.: Multichannel Speech Separation by Eigendecomposition and Its Application to Co-Talker Interference Removal. IEEE Trans. on SAP 5(3) (1997)Google Scholar
  3. 3.
    Morgan, P., George, E., Lee, T., Kay, M.: Co-Channel Speaker Separation. In: ICASSP, Part 1, May 9-12, vol. 1, pp. 828–831 (1995)Google Scholar
  4. 4.
    Wrigley, S.N., Brown, G.J., Wan, V., Renals, S.: Speech and Crosstalk Detection in Multichannel Audio. IEEE Trans. on SAP 13(1) (2005)Google Scholar
  5. 5.
    Chakraborty, R., Nadeu, C., Butko, T.: Detection and positioning of overlapped sounds in a room environment. In: Proc. Interspeech 2012 (2012)Google Scholar
  6. 6.
    Boakye, K., Stolcke, A.: Improved Speech Activity Detection Using Cross-Channel Features for Recognition of Multi-party Meetings. In: Proc. Interspeech 2006 (2006)Google Scholar
  7. 7.
    Yakoyama, R., et al.: Overlapped Speech Detection in Meeting Using Cross-Channel Spectral Subtraction and Spectrum Similarity. In: Proc. Interspeech 2012 (2012)Google Scholar
  8. 8.
    Yen, K.-C., Zhao, Y.: Robust Automatic Speech Recognition using a multi-channel signal separation front-end. In: Proc. ICLSP 1996 (1996)Google Scholar
  9. 9.
    Laskowski, K., Schulttz, T.: A geometric interpretation of non-target-normalized maximum cross-channel correlation for vocal activity detection in meetings. In: Proc. of NAACL HLT 2007, pp. 89–92 (2007)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  • Mikhail Stolbov
    • 1
  • Marina Tatarnikova
    • 1
  1. 1.Speech Technology Center LimitedSt. PetersburgRussia

Personalised recommendations