Signal ProcessingNo Access

Speech Enhancement Using Modified MMSE-LSA and Phase Reconstruction in Voiced and Unvoiced Speech

College of Information and Computer, Taiyuan University of Technology, 209, University Street, Yuci District, Jinzhong 030600, P. R. China

E-mail Address: helenjia722@163.com

Corresponding author.

Search for more papers by this author

Weimei Wang

College of Information and Computer, Taiyuan University of Technology, 209, University Street, Yuci District, Jinzhong 030600, P. R. China

E-mail Address: wangweimei1010@163.com

Search for more papers by this author

Dong Wang

College of Information and Computer, Taiyuan University of Technology, 209, University Street, Yuci District, Jinzhong 030600, P. R. China

E-mail Address: 1083116426@qq.com

Search for more papers by this author

, and

Xueying Zhang

College of Information and Computer, Taiyuan University of Technology, 209, University Street, Yuci District, Jinzhong 030600, P. R. China

E-mail Address: tyzhangxy@163.com

Search for more papers by this author

https://doi.org/10.1142/S0218001419580023Cited by:3 (Source: Crossref)

Abstract

Aiming at the problem of auditory negative enhancement of typical phase reconstruction method, an improved method of phase reconstruction and MMSE-LSA estimation is proposed. First, the geometric relationship between noisy speech and clean speech in unvoiced segment is used to estimate the phase of the clean speech; Second, considering the randomness of speech appearance in the actual noise environment, a modified MMSE-LSA amplitude estimation is proposed by using the binary hypothesis model. Finally, the new phase reconstruction in voiced and unvoiced speech is combined with the modified MMSE-LSA. The simulation results show that the performance of the algorithm proposed in this paper is better than typical phase reconstruction method in terms of the SegSNR and PESQ.

Keywords:

References

1. J. B. Allen, How do humans process and recognize speech? J. Acoust. Soc. Am. 93 (1994) 567–577. Google Scholar
2. W. R. Antony et al., Perceptual evaluation of speech quality (pesq) — A, J. Audio Eng. Soc. 50 (2001) 755–764. Web of Science, Google Scholar
3. S. Y. Barysenka, V. I. Vorobiov and P. Mowlaee, Single-channel speech enhancement using inter-component phase relations, Speech Commun. 99 (2018) 144–160. Web of Science, Google Scholar
4. A. Bhowmick and M. Chandra, Speech enhancement using voiced speech probability based wavelet decomposition, Computers & Electrical Engineering 62 (2017) 706–718. Web of Science, Google Scholar
5. A. Brandt and R. Brincker, Integrating time signals in frequency domain — Comparison with time domain integration, Measurement 58 (2014) 511–519. Web of Science, Google Scholar
6. R. Chappel, B. Schwerin and K. Paliwal, Phase distortion resulting in a just noticeable difference in the perceived quality of speech, Speech Commun. 81 (2016) 138–147. Web of Science, Google Scholar
7. S. H. Chen, Y. S. Lee and J. C. Wang, Phase-incorporating Speech Enhancement Based on Complex-valued Gaussian Process Latent Variable Model (2016). Google Scholar
8. M. Djendi and P. Scalart, Reducing over- and under-estimation of the a priori, SNR in speech enhancement techniques, Digital Signal Process. 32 (2014) 124–136. Web of Science, Google Scholar
9. Y. Ephraim and D. Malah, Speech enhancement using a minimum mean-square error log-spectral amplitude estimator, IEEE Trans. Acoust. Speech Signal Process. 32 (1984) 443–445. Google Scholar
10. N. Faraji and A. Kohansal, MMSE and MAP estimators for speech enhancement in additive noise assuming a t-location-scale clean speech prior, Let Signal Processing 12 (2018) 532–543. Web of Science, Google Scholar
11. T. Gerkmann and R. C. Hendriks, Noise power estimation based on the probability of speech presence, Applications of Signal Processing to Audio and Acoustics IEEE 53 (2011) 145–148. Google Scholar
12. S. Gonzalez and M. Brookes, PEFAC — A pitch estimation algorithm robust to high levels of noise, IEEE/ACM Trans. Audio Speech & Language Process. 22 (2014) 518–530. Google Scholar
13. K. K. Hong and R. C. Rose, Cepstrum-domain model combination based on decomposition of speech and noise using MMSE-LSA for ASR in noisy environments, IEEE Trans. on Audio Speech & Language Process. 17 (2009) 704–713. Google Scholar
14. S. Kammi and M. R. K. Mollaei, Noisy speech enhancement with sparsity regularization, Speech Commun. 87 (2017) 58–69. Web of Science, Google Scholar
15. R. K. Kandagatla and P. V. Subbaiah, Speech enhancement using MMSE estimation of amplitude and complex speech spectral coefficients under phase-uncertainty, Speech Commun. 96 (2017) 10–27. Web of Science, Google Scholar
16. M. Krawczyk and T. Gerkmann, STFT phase reconstruction in voiced speech for an improved single-channel speech enhancement, IEEE/ACM Trans. Audio Speech & Language Process. 22 (2014) 1931–1940. Google Scholar
17. J. Kulmer and P. Mowlaee, Phase estimation in single channel speech enhancement using phase decomposition, IEEE Signal Process. Lett. 22 (2015) 598–602. Web of Science, Google Scholar
18. S. Lee, D. K. Han and H. Ko, Single-channel speech enhancement method using reconstructive NMF with spectrotemporal speech presence probabilities, Appl. Acoust. 117 (2016) 257–262. Web of Science, Google Scholar
19. Y. Liu, N. Nower, S. Morita and M. Unoki, Speech enhancement of instantaneous amplitude and phase for applications in noisy reverberant environments, Speech Commun. 84 (2016) 1–14. Web of Science, Google Scholar
20. T. Lohrenz and T. Fingscheidt, Turbo fusion of magnitude and phase information for DNN-based phoneme recognition, Automatic Speech Recognition and Understanding Workshop, IEEE (2018), doi: 10.1109/ASRU.2017.8268925. Google Scholar
21. P. C. Loizou, Speech Enhancement: Theory and Practice (CRC Press, New York, 2007). Google Scholar
22. P. Mowlaee and J. Kulmer, Harmonic phase estimation in single-channel speech enhancement using phase decomposition and SNR information, in IEEE/ACM Trans. on Audio, Speech and Language Process. Vol. 23 (2015), pp. 1521–1532. Google Scholar
23. K. K. Paliwal and L. D. Alsteris, On the usefulness of STFT phase spectrum in human listening tests, Speech Commun. 45 (2005) 153–170. Web of Science, Google Scholar
24. R. Rehr and T. Gerkmann, Normalized Features for Improving the Generalization of DNN Based Speech Enhancement (2017). Google Scholar
25. J. C. Saldanha, Speech enhancement using filtering techniques, National Conference on Emerging Trends in Electronics and Communication (2016). Google Scholar
26. M. B. Trawicki and M. T. Johnson, Distributed multichannel speech enhancement with minimum mean-square error short-time spectral amplitude, log-spectral amplitude, and spectral phase estimation, Signal Process. 92 (2012) 345–356. Web of Science, Google Scholar