Estimating nonnegative matrix model activations with deep neural networks to increase perceptual speech quality

Journal of the Acoustical Society of America

Volumn 138, Issue 3, 2015, Pages 1399-1407

  Williamson, Donald S ^a   Wang, Yuxuan ^a   Wang, Deliang ^a  

^a The Ohio State University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

CHEMICAL ACTIVATION; FACTORIZATION; MATRIX ALGEBRA; SEPARATION; SIGNAL TO NOISE RATIO; SOUND REPRODUCTION;

DEEP NEURAL NETWORKS; LOW SIGNAL-TO-NOISE RATIO; NON-NEGATIVE MATRIX; NONNEGATIVE MATRIX FACTORIZATION; PERCEPTUAL EVALUATION OF SPEECH QUALITIES; PERCEPTUAL QUALITY; TIME-FREQUENCY MASKING; TIME-FREQUENCY REPRESENTATIONS;

SPEECH;

ADULT; ALGORITHM; BIOLOGICAL MODEL; FEMALE; HUMAN; MALE; NERVE CELL NETWORK; NOISE; PERCEPTION; PHYSIOLOGY; PROCEDURES; SIGNAL NOISE RATIO; SOUND DETECTION; SPEECH; SPEECH PERCEPTION; TRAFFIC NOISE; YOUNG ADULT;

ADULT; ALGORITHMS; FEMALE; HUMANS; MALE; MODELS, BIOLOGICAL; NERVE NET; NOISE; NOISE, TRANSPORTATION; PERCEPTUAL MASKING; SIGNAL-TO-NOISE RATIO; SOUND SPECTROGRAPHY; SPEECH ACOUSTICS; SPEECH PERCEPTION; YOUNG ADULT;

EID: 84941336645     PISSN: 00014966     EISSN: None     Source Type: Journal    
DOI: 10.1121/1.4928612     Document Type: Article

References (28)

1. Arehart, K. H., Kates, J. M., Anderson, M. C., and Harvey, L. O., Jr. (2007). " Effects of noise and distortion on speech quality judgments in normal-hearing and hearing-impaired listeners," J. Acoust. Soc. Am. 122, 1150-1164. 10.1121/1.2754061
2. Duchi, J., Hazan, E., and Singer, Y. (2010). " Adaptive subgradient methods for online learning and stochastic optimization," J. Mach. Learn. Res. 12, 2121-2159.
3. Eggert, J., and Korner, E. (2004). " Sparse coding and NMF," IEEE Conf. Neural Netw. 4, 2529-2533. 10.1109/IJCNN.2004.1381036
4. Févotte, C., Bertin, N., and Durrieu, J-L. (2009). " Nonnegative matrix factorization with the Itakura-Saito divergence: With application to music analysis," Neural Comput. 21, 793-830. 10.1162/neco.2008.04-08-771
5. Han, K., Wang, Y., and Wang, D. L. (2014). " Learning spectral mapping for speech dereverberation," in Proceedings of ICASSP, pp. 4661-4665.
6. Healy, E. W., Yoho, S. E., Wang, Y., and Wang, D. L. (2013). " An algorithm to improve speech recognition in noise for hearing-impaired listeners," J. Acoust. Soc. Am. 134, 3029-3038. 10.1121/1.4820893
7. IEEE (1969). " IEEE recommended practice for speech quality measurements," IEEE Trans. Audio Electroacoust. 17, 225-246. 10.1109/TAU.1969.1162058
8. ITU-R (2001). " Perceptual evaluation of speech quality (PESQ), an objective method for end-to-end speech quality assessment of narrowband telephone networks and speech codecs," p. 862.
9. Kim, G., Lu, Y., Hu, Y., and Loizou, P. (2009). " An algorithm that improves speech intelligibility in noise for normal-hearing listeners," J. Acoust. Soc. Am. 126, 1486-1494. 10.1121/1.3184603
10. Koning, R., Madhu, N., and Wouters, J. (2015). " Ideal time-frequency masking algorithms lead to different speech intelligibility and quality in normal-hearing and cochlear implant listeners," IEEE Trans. Biomed. Eng. 62, 331-341. 10.1109/TBME.2014.2351854
11. Lee, D., and Seung, H. S. (1999). " Learning the parts of objects by non-negative matrix factorization," Nature 401, 788-791. 10.1038/44565
12. Mysore, G. J., and Smaragdis, P. (2011). " A non-negative approach to semi-supervised separation of speech from noise with the use of temporal dynamics," in Proceedings of ICASSP, pp. 17-20.
13. Mysore, G. J., Smaragdis, P., and Raj, B. (2010). " Non-negative hidden Markov modeling of audio with application to source separation," in Proceedings of LVA/ICA, pp. 1-8.
14. Nair, V., and Hinton, G. E. (2010). " Rectified linear units improve restricted Boltzmann machines," in Proceedings of International Conference on Machine Learning, pp. 807-814.
15. Narayanan, A., and Wang, D. L. (2013). " Ideal ratio mask estimation using deep neural networks for robust speech recognition," in Proceedings of ICASSP, pp. 7092-7096.
16. Seung, H. S., and Lee, D. (2001). " Algorithms for non-negative matrix factorization," Adv. Neural Inf. Process. Syst. 13, 556-562.
17. Smaragdis, P. (2007). " Convolutive speech bases and their application to supervised speech separation," IEEE Trans. Audio Speech Lang. Process. 15, 1-12. 10.1109/TASL.2006.876726
18. Taal, C. H., Hendriks, R. C., Heusdens, R., and Jensen, J. (2011). " An algorithm for intelligibility prediction of time frequency weighted noisy speech," IEEE Trans. Audio Speech Lang. Process. 19, 2125-2136. 10.1109/TASL.2011.2114881
19. Virtanen, T. (2007). " Monaural sound source separation by nonnegative matrix factorization with temporal continuity and sparseness criteria," IEEE Trans. Audio Speech Lang. Process. 15, 1066-1074. 10.1109/TASL.2006.885253
20. Wang, Y., Han, K., and Wang, D. L. (2013). " Exploring monaural features for classification-based speech segregation," IEEE Trans. Audio Speech Lang. Process. 21, 270-279. 10.1109/TASL.2012.2221459
21. Wang, Y., and Wang, D. L. (2013). " Towards scaling up classification-based speech separation," IEEE Trans. Audio Speech Lang. Process. 21, 1381-1390. 10.1109/TASL.2013.2250961
22. Wang, Y., Narayanan, A., and Wang, D. L. (2014). " On training targets for supervised speech separation," IEEE Trans. Audio Speech Lang. Process. 22, 1849-1858. 10.1109/TASLP.2014.2352935
23. Williamson, D. S., Wang, Y., and Wang, D. L. (2014a). " A two-stage approach for improving the perceptual quality of separated speech," in Proceedings of ICASSP, pp. 7084-7088.
24. Williamson, D. S., Wang, Y., and Wang, D. L. (2014b). " Reconstruction techniques for improving the perceptual quality of binary masked speech," J. Acoust. Soc. Am. 136, 892-902. 10.1121/1.4884759
25. Williamson, D. S., Wang, Y., and Wang, D. L. (2015). " Deep neural networks for estimating speech model activations," in Proceedings of ICASSP, pp. 5113-5117.
26. Wilson, K., Raj, B., Smaragdis, P., and Divakaran, A. (2008). " Speech denoising using nonnegative matrix factorization with priors," in Proceedings of ICASSP, pp. 4029-4032.
27. Xu, Y., Du, J., Dai, L., and Lee, C. (2014). " An experimental study on speech enhancement based on deep neural networks," IEEE Sign. Process. Lett. 21, 65-68. 10.1109/LSP.2013.2291240
28. Zhang, X.-L., and Wang, D. L. (2014). " Boosted deep neural networks and multi-resolution cochleagram features for voice activity detection," in Proceedings of INTERSPEECH, pp. 1534-1538.