Enhanced Robot Speech Recognition Based on Microphone Array Source Separation and Missing Feature Theory
Authors:
- S. YamamotoSYS. Yamamoto
- J.-M. ValinJVJ.-M. Valin
- K. NakadaiKNK. Nakadai
- J. RouatJRJ. Rouat
- F. MichaudFMF. Michaud
- T. OgataTOT. Ogata
- H.G. OkunoHOH.G. Okuno
- 18 January 2006
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10504729,p. 1477-1482
Abstract
A humanoid robot under real-world environments usually hears mixtures of sounds, and thus three capabilities are essential for robot audition; sound source localization, separation, and recognition of separated sounds. While the first two are frequently addressed, the last one has not been studied so much. We present a system that gives a humanoid robot the ability to localize, separate and recognize simultaneous sound sources. A microphone array is used along with a real-time dedicated implementation of Geometric Source Separation (GSS) and a multi-channel post-filter that gives us a further reduction of interferences from other sources. An automatic speech recognizer (ASR) based on the Missing Feature Theory (MFT) recognizes separated sounds in real-time by generating missing feature masks automatically from the post-filtering step. The main advantage of this approach for humanoid robots resides in the fact that the ASR with a clean acoustic model can adapt the distortion of separated sound by consulting the post-filter feature masks. Recognition rates are presented for three simultaneous speakers located at 2m from the robot. Use of both the post-filter and the missing feature mask results in an average reduction in error rate of 42% (relative).Keywords
This publication has 13 references indexed in Scilit:
- A spectral subtraction algorithm for suppression of acoustic noise in speech2005
- Localization of simultaneous moving sound sources for mobile robot using a frequency- domain steered beamformer approach2004
- Improvement of robot audition by interfacing sound source separation and automatic speech recognition with Missing Feature Theory2004
- A microphone array with adaptive post-filtering for noise reduction in reverberant rooms2003
- Geometric source separation: merging convolutive source separation with geometric beamformingIEEE Transactions on Speech and Audio Processing, 2002
- Microphone array post-filter for diffuse noise field2002
- Microphone array post-filtering for non-stationary noise suppression2002
- Speech enhancement for non-stationary noise environmentsSignal Processing, 2001
- Speech enhancement using a minimum mean-square error log-spectral amplitude estimatorIEEE Transactions on Acoustics, Speech, and Signal Processing, 1985
- Speech enhancement using a minimum-mean square error short-time spectral amplitude estimatorIEEE Transactions on Acoustics, Speech, and Signal Processing, 1984