A statistical approach to Mel-domain mask estimation for missing-feature ASR

IEEE Signal Processing Letters

Volumn 17, Issue 11, 2010, Pages 941-944

  Borgstrom, Bengt J ^a   Alwan, Abeer ^a  

^a University of California   (United States)

Author keywords

2 random variables; mask estimation; missing features; noise robust ASR; speech presence uncertainty

Indexed keywords

AUTOMATIC SPEECH RECOGNITION; CLOSED FORM; DEGREES OF FREEDOM; ESTIMATION ALGORITHM; MISSING FEATURES; POSTERIOR PROBABILITY; RELIABILITY MEASURE; ROBUST ASR; SPECTRAL SUBTRACTIONS; SPEECH DATA; SPEECH MODELS; STATISTICAL APPROACH; TEMPORAL CORRELATIONS; TIME FREQUENCY;

ESTIMATION; FEATURE EXTRACTION; RANDOM VARIABLES; SPEECH PROCESSING;

SPEECH RECOGNITION;

EID: 78149438339     PISSN: 10709908     EISSN: None     Source Type: Journal    
DOI: 10.1109/LSP.2010.2076348     Document Type: Article

References (17)

1. B. Raj and R. Stern, "Missing feature approaches in speech recognition", IEEE Signal Process. Mag., vol. 22, no. 5, pp. 101-116, 2005.
2. M. P. Cooke, A. Morris, and P. D. Green, "Missing data techniques for robust speech recognition", in Proc. ICASSP, 1997, vol. 2, pp. 863-866.
3. W. Kim and R. M. Stern, "Band-independent mask estimation for missing-feature reconstruction in the presence of unknown background noise", in ICASSP, 2006, pp. 305-308.
4. R. J. McAulay and M. L. Malpass, "Speech enhancement using a softdecision noise suppression filter", IEEE Trans. Acoust., Speech, Signal Process., vol. ASSP-28, no. 2, pp. 137-145, 1980.
5. Y. Ephraim and D. Malah, "Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator", IEEE Trans. Acoust., Speech, Signal Process., vol. ASSP-32, no. 6, pp. 1109-1121, 1984.
6. S. Young, D. Kershaw, J. Odell, D. Ollason, V. Valtchev, and P. Woodland, The HTK Book. Redmond, WA: Microsoft, 2004.
7. H. Solomon and M. A. Stephens, "Distribution of a sum of weighted Chi-square variables", Amer. Statist. Assoc., vol. 72, no. 360, pp. 881-885, 1977.
8. R. Martin and T. Lotter, "Optimal recursive smoothing of non-stationary periodograms", in Proc. Int. Workshop on Acoustic Echo Control and Noise Reduction, 2001, pp. 43-46.
9. M. V. Segbroeck and H. V. hamme, "Vector-quantization based mask estimation for missing data automatic speech recognition", Interspeech, pp. 910-913, 2007.
10. A. Vizinho, P. Green, M. Cooke, and L. Josifovski, "Missing data theory, spectral subtraction and signal-to-noise estimation for robust Asr: An integrated study", in EUROSPEECH, 1999, pp. 2407-2410.
11. P. Green, J. Barker, M. Cooke, and L. Josifovski, "Handling missing and unreliable information in speech recognition", in Proc. AISTATS, 2001.
12. M. L. Seltzer, B. Raj, and R. M. Stern, "A Bayesian classifier for spectrographic mask estimation for missing feature speech recognition", Speech Communic., vol. 43, pp. 379-393, 2004.
13. L. R. Rabiner, "A tutorial on hidden Markov models and selected applications in speech recognition", Proc. IEEE, vol. 77, pp. 257-286, 1989.
14. B. J. Borgstrom and A. Alwan, "Utilizing compressibility in reconstructing spectrographic data, with applications to noise robust ASR", IEEE Signal Process. Lett., vol. 16, pp. 398-401, 2009.
15. B. J. Borgstrom and A. Alwan, "Missing feature imputation of logspectral data for noise robust ASR", in Workshop on DSP in Mobile and Vehicular Systems, 2009.
16. J. Sohn, N. S. Kim, and W. Sung, "A statistical model-based VAD", IEEE Signal Process. Lett., vol. 16, pp. 1-3, Jan. 1999.
17. W. Q. Syed and H.-C. Wu, "Speech waveform compression using robust adaptive voice activity detection for nonstationary noise", EURASIP J. Audio, Speech, Music Process., 2008.