Copyright © 2008 The Institute of Electronics, Information and Communication Engineers
Special Section on Robust Speech Processing in Realistic Environments -- Papers -- ASR under Reverberant Conditions |
Robust Speech Recognition by Combining Short-Term and Long-Term Spectrum Based Position-Dependent CMN with Conventional CMN
1 The authors are with Toyohashi University of Technology, Toyohashi-shi, 441–8580 Japan. E-mail: wang{at}slp.ics.tut.ac.jp, 2 The author is with Nagoya University, Nagoya-shi, 464–8603 Japan.
 |
Abstract |
|---|
In a distant-talking environment, the length of channel impulse response is longer than the short-term spectral analysis window. Conventional short-term spectrum based Cepstral Mean Normalization (CMN) is therefore, not effective under these conditions. In this paper, we propose a robust speech recognition method by combining a short-term spectrum based CMN with a long-term one. We assume that a static speech segment (such as a vowel, for example) affected by reverberation, can be modeled by a long-term cepstral analysis. Thus, the effect of long reverberation on a static speech segment may be compensated by the long-term spectrum based CMN. The cepstral distance of neighboring frames is used to discriminate the static speech segment (long-term spectrum) and the non-static speech segment (short-term spectrum). The cepstra of the static and non-static speech segments are normalized by the corresponding cepstral means. In a previous study, we proposed an environmentally robust speech recognition method based on Position-Dependent CMN (PDCMN) to compensate for channel distortion depending on speaker position, and which is more efficient than conventional CMN. In this paper, the concept of combining short-term and long-term spectrum based CMN is extended to PDCMN. We call this Variable Term spectrum based PDCMN (VT-PDCMN). Since PDCMN/VT-PDCMN cannot normalize speaker variations because a position-dependent cepstral mean contains the average speaker characteristics over all speakers, we also combine PDCMN/VT-PDCMN with conventional CMN in this study. We conducted the experiments based on our proposed method using limited vocabulary (100 words) distant-talking isolated word recognition in a real environment. The proposed method achieved a relative error reduction rate of 60.9% over the conventional short-term spectrum based CMN and 30.6% over the short-term spectrum based PDCMN.
Key Words: robust speech recognition, distant-talking environment, CMN, long-term spectrum
Manuscript received July 2, 2007. Manuscript revised September 6, 2007.