Non-negative matrix factorization as noise-robust feature extractor for speech recognition

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2010, Pages 4562-4565

  Schuller, Björn ^a   Weninger, Felix ^a   Wöllmer, Martin ^a   Sun, Yang ^a   Rigoll, Gerhard ^a  

^a TECHNICAL UNIVERSITY OF MUNICH   (Germany)

Author keywords

Dynamic bayesian networks; Long short term memory; Noise robustness; Non negative matrix factorization; Speech recognition

Indexed keywords

BAYESIAN NETWORKS; BRAIN; LONG SHORT-TERM MEMORY; MATRIX ALGEBRA; MAXIMUM LIKELIHOOD ESTIMATION; SPEECH RECOGNITION;

DYNAMIC BAYESIAN NETWORKS; FEATURE EXTRACTOR; MATRIX FACTORIZATIONS; NOISE ROBUST; NOISE ROBUSTNESS; NONNEGATIVE MATRIX FACTORIZATION; ROBUST FEATURE EXTRACTIONS; SPEECH DENOISING; TIME VARYING; UNSUPERVISED ALGORITHMS;

NON-NEGATIVE MATRIX FACTORIZATION;

EID: 78049362257     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2010.5495567     Document Type: Conference Paper

References (16)

1. M. N. Schmidt and R. K. Olsson, "Single-channel speech separation using sparse non- negative matrix factorization," in Proc. of Interspeech, Pittsburgh, Pennsylvania, 2006.
2. P. D. O'Grady and B. A. Pearlmutter, "Discovering convolutive speech phones using sparseness and non-negativity constraints," in Proc. of ICA, London, UK, 2007.
3. S. J. Rennie, J. R. Hershey, and P. A. Olsen, "Efficient model-based speech separation and denoising using non-negative sub-space analysis," in Proc. of ICASSP, Las Vegas, USA, 2008.
4. K. W. Wilson, B. Raj, P. Smaragdis, and A. Divakaran, "Speech denoising using nonnegative matrix factorization with priors," in Proc. of ICASSP, Las Vegas, USA, 2008.
5. K. W. Wilson, B. Raj, and P. Smaragdis, "Regularized non-negative matrix factorization with temporal dependencies for speech denoising," in Proc. of Interspeech, Brisbane, Australia, 2008.
6. T. Virtanen and A. T. Cemgil, "Mixtures of gamma priors for non-negative matrix factorization based speech separation," in Proc. of ICA, Paraty, Brazil, 2009.
7. T. Virtanen, "Spectral covariance in prior distributions of non-negative matrix factorization based speech separation," in Proc. of EUSIPCO, Glasgow, Scotland, 2009.
8. Y.-C. Cho, S. Choi, and S.-Y. Bang, "Non-negative component parts of sound for classification," in Proc. of ISSPIT, Darmstadt, Germany, 2003, pp. 633-636.
9. B. Schuller, M. Wöllmer, T. Moosmayr, and G. Rigoll, "Recognition of noisy speech: A comparative survey of robust model architectures and feature enhancement," EURASIP Journal on Audio, Speech, and Music Processing, 2009, id 942617.
10. M. Wöllmer, F. Eyben, B. Schuller, Y. Sun, T. Moosmayr, and N. Nguyen-Thien, "Robust in-car spelling recognition - A Tandem BLSTM-HMM approach," in Proc. of Interspeech, Brighton, UK, 2009.
11. A. Graves, S. Fernandez, and J. Schmidhuber, "Bidirectional LSTM networks for improved phoneme classification and recognition," in Proc. of ICANN,Warsaw, Poland, 2005, pp. 602-610.
12. T. Virtanen, "Monaural sound source separation by nonnegative matrix factorization with temporal continuity and sparseness criteria," IEEE Transactions on Audio, Speech and Language Processing, vol. 15, no. 3, March 2007.
13. B. Schuller, A. Lehmann, F. Weninger, F. Eyben, and G. Rigoll, "Blind enhancement of the rhythmic and harmonic sections by NMF: Does it help?," in Proc. of the International Conference on Acoustics (NAG/DAGA 2009), Rotterdam, The Netherlands, 2009.
14. D. D. Lee and H. S. Seung, "Algorithms for non-negative matrix factorization," in Proc. of NIPS, Vancouver, Canada, 2001, pp. 556-562.
15. S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural Computation, vol. 9(8), pp. 1735-1780, 1997.
16. J. A. Bilmes and C. Bartels, "Graphical model architectures for speech recognition," IEEE Signal Processing Magazine, vol. 22, no. 5, pp. 89-100, 2005.