Non-negative matrix factorization for highly noise-robust ASR: To enhance or to recognize?

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

Volumn , Issue , 2012, Pages 4681-4684

  Weninger, Felix ^a   Wöllmer, Martin ^a   Geiger, Jürgen ^a   Schuller, Björn ^a   Gemmeke, Jort F ^b   Hurmalainen, Antti ^c   Virtanen, Tuomas ^c   Rigoll, Gerhard ^a  

^a TECHNICAL UNIVERSITY OF MUNICH   (Germany)

^b UNIVERSITY OF LEUVEN   (Belgium)

^c TAMPERE UNIVERSITY OF TECHNOLOGY   (Finland)

Author keywords

Non Negative Matrix Factorization; Tandem Speech Recognition

Indexed keywords

AUTOMATIC SPEECH RECOGNITION; COMPLEMENTARY ANALYSIS; MULTI-STREAM; MULTI-STREAM HIDDEN MARKOV MODEL; NONNEGATIVE MATRIX FACTORIZATION; REVERBERANT ENVIRONMENT; SHORT TERM MEMORY; SPARSE CLASSIFICATION; SPEECH RECOGNITION SYSTEMS; TEST SETS; WORD PREDICTION;

ACOUSTIC NOISE; RECURRENT NEURAL NETWORKS; SIGNAL PROCESSING; SPEECH ENHANCEMENT; SPEECH RECOGNITION;

FACTORIZATION;

EID: 84867600087     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2012.6288963     Document Type: Conference Paper

References (10)

1. P. Smaragdis, "Convolutive speech bases and their application to supervised speech separation," IEEE Transactions on Audio, Speech and Language Processing, vol. 15, no. 1, pp. 1-14, 2007.
2. J. Gemmeke, T. Virtanen, and A. Hurmalainen, "Exemplar-based sparse representations for noise robust automatic speech recognition," IEEE Transactions on Audio, Speech, and Language Processing, vol. 19, no. 7, pp. 2067-2080, 2011.
3. A. Hurmalainen, K. Mahkonen, J. F. Gemmeke, and T. Virtanen, "Exemplar-based Recognition of Speech in Highly Variable Noise," in Proc. of CHiME Workshop, Florence, Italy, 2011, pp. 1-5.
4. H. Christensen, J. Barker, N. Ma, and P. Green, "The CHiME corpus: a resource and a challenge for Computational Hearing in Multisource Environments," in Proc. of Interspeech, Makuhari, Japan, 2010, pp. 1918-1921.
5. M. Cooke, J. Barker, S. Cunningham, and X. Shao, "An audiovisual corpus for speech perception and automatic speech recognition," The Journal of the Acoustical Society of America, vol. 120, no. 5, pp. 2421-2424, 2006.
6. F. Weninger, J. Geiger, M. Wöllmer, B. Schuller, and G. Rigoll, "The Munich 2011 CHiME Challenge Contribution: NMFBLSTM Speech Enhancement and Recognition for Reverberated Multisource Environments," in Proc. of CHiME Workshop, Florence, Italy, 2011, pp. 24-29.
7. A. Hurmalainen, J. Gemmeke, and T. Virtanen, "Non-negative matrix deconvolution in noise robust speech recognition," in Proc. of ICASSP, Prague, Czech Republic, 2011, pp. 4588-4591.
8. M. Wöllmer, F. Eyben, B. Schuller, and G. Rigoll, "A multistream ASR framework for BLSTM modeling of conversational speech," in Proc. of ICASSP, Prague, Czech Republic, 2011, pp. 4860-4863.
9. S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural Computation, vol. 9, no. 8, pp. 1735-1780, 1997.
10. A. Graves and J. Schmidhuber, "Framewise phoneme classification with bidirectional LSTM and other neural network architectures," Neural Networks, vol. 18, no. 5-6, pp. 602-610, 2005.