Multi-objective learning and mask-based post-processing for deep neural network based speech enhancement

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

Volumn 2015-January, Issue , 2015, Pages 1508-1512

  Xu, Yong ^a   Du, Jun ^a   Huang, Zhen ^b   Dai, Li Rong ^a   Lee, Chin Hui ^b  

^a UNIVERSITY OF SCIENCE AND TECHNOLOGY OF CHINA   (China)

^b GEORGIA INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

Binary mask; Deep neural network; Minimum mean square error; Multi objective learning; Speech enhancement

Indexed keywords

BINS; MEAN SQUARE ERROR; SPEECH; SPEECH ENHANCEMENT; SPEECH RECOGNITION;

BINARY MASKS; DEEP NEURAL NETWORKS; IDEAL BINARY MASK (IBM); JOINT OPTIMIZATION; LISTENING QUALITIES; MEL-FREQUENCY CEPSTRAL COEFFICIENTS; MINIMUM MEAN SQUARE ERRORS; MULTI-OBJECTIVE LEARNING;

SPEECH COMMUNICATION;

EID: 84959100788     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (40)

1. S. Boll, "Suppression of acoustic noise in speech using spectralsubtraction, " IEEE Transactions on Acoustics, Speech and SignalProcessing, vol. 27, no. 2, pp. 113-120, 1979.
2. Y. Ephraim and D. Malah, "Speech enhancement using aminimum-mean square error short-time spectral amplitude esti-mator, " IEEE Transactions on Acoustics, Speech and Signal Pro-cessing, vol. 32, no. 6, pp. 1109-1121, 1984.
3. -, "Speech enhancement using a minimum mean-square errorlog-spectral amplitude estimator, " IEEE Transactions on Acous-tics, Speech and Signal Processing, vol. 33, no. 2, pp. 443-445, 1985.
4. I. Cohen and B. Berdugo, "Speech enhancement for non-stationary noise environments, " Signal processing, vol. 81, no. 11, pp. 2403-2418, 2001.
5. I. Cohen, "Noise spectrum estimation in adverse environments: Improved minima controlled recursive averaging, " IEEE Transac-tions on Acoustics, Speech and Signal Processing, vol. 11, no. 5, pp. 466-475, 2003.
6. A. Varga and H. J. Steeneken, "Assessment for automatic speechrecognition: II. noisex-92: A database and an experiment tostudy the effect of additive noise on speech recognition systems, "Speech communication, vol. 12, no. 3, pp. 247-251, 1993.
7. N. Mohammadiha, P. Smaragdis, and A. Leijon, "Supervised and unsupervised speech enhancement using nonnegative matrix fac-torization, " IEEE Transactions on Acoustics, Speech and SignalProcessing, vol. 21, no. 10, pp. 2140-2151, 2013.
8. K. W. Wilson, B. Raj, and P. Smaragdis, "Regularized non-negative matrix factorization with temporal dependencies forspeech denoising. " in INTERSPEECH, 2008, pp. 411-414.
9. G. Hinton, L. Deng, D. Yu, G. E. Dahl, A.-R. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. N. Sainath et al., "Deepneural networks for acoustic modeling in speech recognition: Theshared views of four research groups, " IEEE Signal ProcessingMagazine, vol. 29, no. 6, pp. 82-97, 2012.
10. G. E. Dahl, D. Yu, L. Deng, and A. Acero, "Context-dependentpre-trained deep neural networks for large-vocabulary speechrecognition, " IEEE Transactions on Audio, Speech, and LanguageProcessing, vol. 20, no. 1, pp. 30-42, 2012.
11. X.-L. Zhang and J. Wu, "Denoising deep neural networks basedvoice activity detection, " in ICASSP, 2013, pp. 853-857.
12. Y. Xu, J. Du, L.-R. Dai, and C.-H. Lee, "A regression approachto speech enhancement based on deep neural networks, " IEEETransactions on Acoustics, Speech and Signal Processing, vol. 23, no. 1, pp. 7-19, 2015.
13. -, "An experimental study on speech enhancement based ondeep neural networks, " IEEE Signal Processing Letters, vol. 21, no. 1, pp. 65-68, 2014.
14. -, "Dynamic noise aware training for speech enhancementbased on deep neural networks. " in INTERSPEECH, 2014, pp. 2670-2674.
15. J. Du and Q. Huo, "A speech enhancement approach using piece-wise linear approximation of an explicit model of environmentaldistortions. " in INTERSPEECH, 2008, pp. 569-572.
16. X. Lu, Y. Tsao, S. Matsuda, and C. Hori, "Speech enhancementbased on deep denoising autoencoder. " in INTERSPEECH, 2013, pp. 436-440.
17. B. Xia and C. Bao, "Wiener filtering based speech enhancementwith weighted denoising auto-encoder and noise classification, "Speech Communication, vol. 60, pp. 13-29, 2014.
18. P. S. Huang, M. Kim, M. Hasegawa-Johnson, and P. Smaragdis, "Deep learning for monaural speech separation, " in ICASSP, 2014, pp. 1562-1566.
19. D. Liu, P. Smaragdis, and M. Kim, "Experiments on deep learningfor speech denoising, " in INTERSPEECH, 2014, pp. 2685-2689.
20. S. Kullback, Information theory and statistics. Courier Corpo-ration, 1997.
21. F. Itakura and S. Saito, "Analysis synthesis telephony based on themaximum likelihood method, " in Proceedings of the 6th Interna-tional Congress on Acoustics, 1968, pp. 17-20.
22. Y. X. Wang, A. Narayanan, and D. L. Wang, "On training tar-gets for supervised speech separation, " IEEE/ACM Transactionson Acoustics, Speech and Signal Processing, vol. 22, no. 12, pp. 1849-1858, 2014.
23. D. L. Wang and G. J. Brown, Computational auditory scene anal-ysis: Principles, algorithms, and applications. Wiley-IEEEPress, 2006.
24. Y. X. Wang and D. L. Wang, "Towards scaling up classification-based speech separation, " IEEE Transactions on Acoustics, Speech and Signal Processing, vol. 21, no. 7, pp. 1381-1390, 2013.
25. A. Narayanan and D. L. Wang, "Ideal ratio mask estimation usingdeep neural networks for robust speech recognition, " in ICASSP, 2013, pp. 7092-7096.
26. R. Caruna, "Multitask learning: A knowledge-based source of in-ductive bias, " in ICML, 1993, pp. 41-48.
27. M. L. Seltzer and J. Droppo, "Multi-task learning in deep neuralnetworks for improved phoneme recognition, " in ICASSP, 2013, pp. 6965-6969.
28. Z. Huang, J. Li, S. M. Siniscalchi, I.-F. Chen, J. Wu, and C.-H. Lee, "Rapid adaptation for deep neural networks through multi-task learning, " 2015, submitted to INTERSPEECH.
29. R. Vergin, D. O'shaughnessy, and A. Farhat, "Generalizedmel frequency cepstral coefficients for large-vocabulary speaker-independent continuous-speech recognition, " IEEE Transactionson Speech and Audio Processing, vol. 7, no. 5, pp. 525-532, 1999.
30. K. S. R. Murty and B. Yegnanarayana, "Combining evidence fromresidual phase and mfcc features for speaker recognition, " IEEESignal Processing Letters, vol. 13, no. 1, pp. 52-55, 2006.
31. B. Logan et al., "Mel frequency cepstral coefficients for musicmodeling. " in ISMIR, 2000.
32. N. Ahmed, T. Natarajan, and K. R. Rao, "Discrete cosine trans-form, " IEEE Transactions on Computers, vol. 100, no. 1, pp. 90-93, 1974.
33. Y. X. Wang, K. Han, and D. L. Wang, "Exploring monaural fea-tures for classification-based speech segregation, " IEEE Transac-tions on Acoustics, Speech and Signal Processing, vol. 21, no. 2, pp. 270-279, 2013.
34. G. Hu, "100 nonspeech environmental sounds, 2004 [on-line], " http: //web. cse. ohio-state. edu/pnl/corpus/HuNonspeech/HuCorpus. html, 2004.
35. J. S. Garofolo et al., "Getting started with the darpa timit cd-rom: An acoustic phonetic continuous speech database, " National In-stitute of Stand ards and Technology (NIST), Gaithersburgh, MD, vol. 107, 1988.
36. A. W. Rix, J. G. Beerends, M. P. Hollier, and A. P. Hekstra, "Perceptual evaluation of speech quality (pesq)-a new method forspeech quality assessment of telephone networks and codecs, " inICASSP, 2001, pp. 749-752.
37. C. H. Taal, R. C. Hendriks, R. Heusdens, and J. Jensen, "An al-gorithm for intelligibility prediction of time-frequency weightednoisy speech, " IEEE Transactions on Acoustics, Speech and Sig-nal Processing, vol. 19, no. 7, pp. 2125-2136, 2011.
38. G. E. Dahl, T. N. Sainath, and G. E. Hinton, "Improving deepneural networks for lvcsr using rectified linear units and dropout, "in ICASSP, 2013, pp. 8609-8613.
39. N. Srivastava, G. E. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, "Dropout: A simple way to prevent neural net-works from overfitting, " The Journal of Machine Learning Re-search, vol. 15, no. 1, pp. 1929-1958, 2014.
40. M. L. Seltzer, D. Yu, and Y. Wang, "An investigation of deepneural networks for noise robust speech recognition, " in ICASSP, 2013, pp. 7398-7402.