Exploiting Uncertainties for Binaural Speech Recognition
- 1 April 2007
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4 (15206149) , IV-789-789
Abstract
Recently several algorithms have been proposed to enhance noisy speech by estimating the signal-to-noise ratio (SNR) within a local time-frequency region based on binaural cues of interaural time and intensity differences (ITD and IID). However, the accuracy of the estimated SNR often varies widely across time and frequency, causing uncertainties in the enhanced speech features. We estimate this uncertainty based on statistics of ITD and IID and show that it can be effectively exploited to improve robust speech recognition. Systematic evaluations using the estimated uncertainty show significant improvement in recognition performance compared to the baseline performance.Keywords
This publication has 9 references indexed in Scilit:
- Binary and ratio time-frequency masks for robust speech recognitionSpeech Communication, 2006
- A Supervised Learning Approach to Uncertainty Decoding for Robust Speech Recognition2006
- Dynamic compensation of HMM variances using the feature enhancement uncertainty computed from a parametric model of speech distortionIEEE Transactions on Speech and Audio Processing, 2005
- A database for speaker-independent digit recognition2005
- A binaural processor for missing data speech recognition in the presence of noise and small-room reverberationSpeech Communication, 2004
- Speech segregation based on sound localizationThe Journal of the Acoustical Society of America, 2003
- Robust automatic speech recognition with missing and unreliable acoustic dataSpeech Communication, 2001
- Assessment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systemsSpeech Communication, 1993
- Speech enhancement using a soft-decision noise suppression filterIEEE Transactions on Acoustics, Speech, and Signal Processing, 1980