Reduction of highly nonstationary ambient noise by integrating spectral and locational characteristics of speech and noise for robust ASR

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2011, Pages 1785-1788

  Nakatani, Tomohiro ^a   Araki, Shoko ^a   Delcroix, Marc ^a   Yoshioka, Takuya ^a   Fujimoto, Masakiyo ^a  

^a NTT Communication Science Laboratories   (Japan)

Author keywords

Automatic speech recognition; Direction of arrival; Log power spectrum; Noise reduction; Nonstationary noise

Indexed keywords

AMBIENT NOISE; AUTOMATIC SPEECH RECOGNITION; MICROPHONE ARRAYS; MULTI-CHANNEL; NONSTATIONARY; NONSTATIONARY NOISE; REAL TIME; ROBUST ASR; SPECTRAL FEATURE; SPECTRAL SHAPES; SPEECH QUALITY; TARGET SPEAKER;

ACOUSTIC NOISE; ACOUSTIC NOISE MEASUREMENT; DIRECTION OF ARRIVAL; NOISE ABATEMENT;

SPEECH RECOGNITION;

EID: 84865754161     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (8)

1. P.J. Moreno, B. Raj, and R.M. Stern, "A vector Taylor series approach for environment-independent speech recognition," ICASSP-96, vol. II, pp. 733-736, 1996.
2. M. Fujimoto, S. Watanabe, and T. Nakatani, "Non-stationary noise estimation method based on bias-residual component decomposition for robust speech recognition," to appear ICASSP-2011, 2011.
3. O. Yilmaz and S. Rickard, "Blind separation of speech mixtures via time-frequency masking," IEEE Trans. Signal Processing, vol. 52, no. 7, pp. 1830-1847, 2004.
4. H. Sawada, S. Araki, and S. Makino, "A two-stage frequencydomain blind source separation method for underdetermined convolutive mixtures," Proc. WASPAA-2007, pp. 139-142, 2007.
5. T. Nakatani, S. Araki, T. Yoshioka, and M. Fujimoto, "Joint unsupervized learning of hidden Markov source models and source location models for multichannel source separation, to appear ICASSP-2011, 2011.
6. S.T. Roweis, "Factorial models and refiltering for speech separation and denoising," Proc. EUROSPEECH-2003, pp. 1009-1012, 2003.
7. J. Barker, H. Christensen, N. Ma, P. Green, and E. Vincent, the PASCAL CHiME speech separation challenge website. http://www.dcs.shef.ac.uk/spandh/ chime/challenge.html
8. T. Hori, C. Hori, Y. Minami, and A. Nakamura, "Efficient WFSTbased one-pass decoding with on-the-fly hypothesis rescoring in extremely large vocabulary continuous speech recognitio