Discriminative piecewise linear transformation based on deep learning for noise robust automatic speech recognition

2013 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2013 - Proceedings

Volumn , Issue , 2013, Pages 350-355

  Kashiwagi, Yosuke ^a   Saito, Daisuke ^a   Minematsu, Nobuaki ^a   Hirose, Keikichi ^a  

^a UNIVERSITY OF TOKYO   (Japan)

Author keywords

Automatic speech recognition; Deep learning; feature enhancement; Noise robustness

Indexed keywords

AUTOMATIC SPEECH RECOGNITION; DEEP LEARNING; FEATURE ENHANCEMENT; NOISE ROBUSTNESS; NOISE-ROBUST AUTOMATIC SPEECH RECOGNITION; NON-LINEAR RELATIONSHIPS; PIECEWISE-LINEAR TRANSFORMATION; PROBABILISTIC DISTRIBUTION;

IMAGE SEGMENTATION; LINEAR TRANSFORMATIONS; NEURAL NETWORKS; PIECEWISE LINEAR TECHNIQUES; PROBABILITY DISTRIBUTIONS;

SPEECH RECOGNITION;

EID: 84893709342     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ASRU.2013.6707755     Document Type: Conference Paper

References (14)

1. Gales, Mark JF, "Model-based approaches to handling uncertainty, " Robust Speech Recognition of Uncertain or Missing Data-Theory and Applications. Springer, Berlin, Germany, pp. 101-125, 2011.
2. Droppo, Jasha and Deng, Li and Acero, Alex, "Evaluation of SPLICE on the Aurora 2 and 3 tasks, " International Conference on Spoken Language Processing, pp. 29-32, 2002.
3. Vincent, Pascal and Larochelle, Hugo and Bengio, Yoshua and Manzagol, Pierre-Antoine, "Extracting and compos- ing robust features with denoising autoencoders, " Proceedings of the 25th international conference on Machine learning, pp. 1096-1103, 2008.
4. Li, Jinyu and Seltzer, Michael L and Gong, Yifan, "Improvements to VTS feature enhancement, " Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on, pp. 4677-4680, 2012.
5. Afify, Mohamed and Cui, Xiaodong and Gao, Yuqing, "Stereo-based stochastic mapping for robust speech recognition, " Audio, Speech, and Language Processing, IEEE Transactions on, vol. 17, no. 7, pp. 1325-1334, 2009.
6. Gemmeke, Jort F and Virtanen, Tuomas and Hurmalainen, Antti, "Exemplar-based sparse representations for noise robust automatic speech recognition, " Audio, Speech, and Language Processing, IEEE Transactions on, vol. 19, no. 7, pp. 2067-2080, 2011.
7. Senior, Andrew and Cho, Youngmin and Weston, Jason "Learning improved linear transforms for speech recognition., " Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on, pp. 1957-1960, 2012.
8. Suzuki, Masayuki and Yoshioka, Takuya and Watanabe, Shinji and Minematsu, Nobuaki and Hirose, Keikichi "MFCC enhancement using joint corrupted and noise feature space for highly non-stationary noise environments, " Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on, pp. 4109-4112, 2012.
9. Suzuki Masayuki, Yoshioka Takuya, Watanabe Shinji, Minematsu Nobuaki, and Hirose Keikichi "Feature Enhancement With Joint Use of Consecutive Corrupted and Noise Feature Vectors With Discriminative Region Weighting, " IEEE TASLP, (to appear).
10. http://eurospeech2001.org/ese/NoiseRobust/index.html, http://www.elda.fr/proj/aurora1.html, http://www.elda.fr/proj/aurora2.html.
11. Hinton, Geoffrey E and Osindero, Simon and Teh, Yee- Whye "A fast learning algorithm for deep belief nets, " Neural computation, vol. 18, no. 7, pp. 1527-1554, 2006. (Pubitemid 44024729)
12. Maas, Andrew L and Le, Quoc V and O'Neil, Tyler M and Vinyals, Oriol and Nguyen, Patrick and Ng, Andrew Y, "Recurrent Neural Networks for Noise Reduction in Ro- bust ASR, " INTERSPEECH, 2012.
13. http://htk.eng.cam.ac.uk/.
14. Povey, Daniel and Ghoshal, Arnab and Boulianne, Gilles and Burget, Lukas and Glembek, Ondrej and Goel, Nagendra and Hannemann, Mirko and Motlicek, Petr and Qian, Yanmin and Schwarz, Petr and others "The kaldi speech recognition toolkit, " IEEE 2011 workshop on automatic speech recognition and understanding, 2011.