Speech Enhancement Based on Analysis–Synthesis Framework with Improved Parameter Domain Enhancement
- 315 Downloads
This paper presents a speech enhancement approach based on analysis–synthesis framework. An improved multi-band summary correlogram (MBSC) algorithm is proposed for pitch estimation and voiced/unvoiced (V/UV) detection. The proposed pitch detection algorithm achieves a lower pitch detection error compared with the reference algorithm. The denoising autoencoder (DAE) is applied to enhance the line spectrum frequencies (LSFs). The reconstruction loss could be decreased compare with the swallow model. The proposed approach is evaluated using the perceptual evaluation of speech quality (PESQ) and the experimental results show that the proposed approach improves the performance of speech enhancement compared with the conventional speech enhancement approach. In addition, it could be applied to parametric speech coding even at low bit rate and low signal-noise ratio (SNR) environments.
KeywordsAnalysis-synthesis framework Multi-band summary correlogram Denoising autoencoder Speech enhancement Speech coding
This work is supported by the National High-Tech Research and Development Program of China(863 Program) (No.2015AA016305), the National Natural Science Foundation of China (NSFC) (No.61425017, No.61403386, No.61305003, No.61332017, No.61375027, No.61273288, No.61233009, No.61203258), the Major Program for the National Social Science Fund of China (13&ZD189) and the Integration and application of basic science data in Chinese information processing field (XXH12504-1-11).
- 8.Xie, F., & Compernolle, D. V. (1994). A family of MLP based nonlinear spectral estimators for noise reduction. In Acoustics, Speech, and Signal Processing (ICASSP) (pp. 53–56). Australia.Google Scholar
- 9.Dahl, G. E., Sainath, T. N., Hinton, G. E. (2013). Improving deep neural networks for LVCSR using rectified linear units and dropout. In Acoustics, Speech, and Signal Processing (ICASSP) (pp. 8609–8613). Canada.Google Scholar
- 10.Chen, R. F., Chan, C. F., So H. C. (2010). Noise suppression based on an analysis–synthesis approach. In Proc. Eur. Signal Process. Conf. (EUSIPCO) (pp. 1539–1543).Google Scholar
- 14.Tan, L. N., Alwan, A. (2011). Noise-robust F0 estimation using SNRweighted summary correlograms from multi-band comb filters. In Proc. IEEE ICASSP (pp. 4464–4467).Google Scholar
- 16.Toda T., Saruwatari, H., Shikano, K. (2001). Voice conversion algorithm based on gaussian mixture model with dynamic frequency warping of straight spectrum. In Proc of ICASSP (pp. 941–944).Google Scholar
- 17.Park, K. Y., & Kim, H. S. (2000). Narrowband to wideband conversion of speech using GMM based transformation. Proceeding of IEEE International Conference on Acoustics, Speech, Signal Processing, 4, 1843–1846.Google Scholar
- 19.Bengio, Y., Yao, L., Alain, G., et al. (2013). Generalized denoising autoencoders as generative models. In Advances in Neural Information Processing Systems (pp: 899–907). USA.Google Scholar
- 20.Tan, L. N., Alwan, A. (2013). Multi-band summary correlogram-based pitch detection for noisy speech. In Speech communication (pp. 841–856).Google Scholar
- 22.Supplee, L. M., Cohn, R. P., Collura, J. S., McCree, A. V. (1997). MELP: the new federal standard at 2400bps. In Acoustics Speech and Signal Processing (1591–1594). Germany.Google Scholar
- 23.Garofolo, J. S. (1993). TIMIT: Acoustic-phonetic Continuous Speech Corpus, Linguistic Data Consortium.Google Scholar
- 24.Rice University, NOISEX-92 Database, [Online] Available: http://spib.rice.edu/spib/select noise.html.
- 25.Chu, W., Alwan, A. (2009). reducing F0 frame error of F0 tracking algorithm under noisy condition with an unvoiced/voiced classification frontend. In Acoustics Speech and Signal Processing (3969-3972). GermanyGoogle Scholar
- 27.Rix, A. W., Beerends, J. G., Hollier, M. P., et al. (2001). Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs. In Acoustics, Speech, and Signal Processing (ICASSP) (pp. 749–752). USA.Google Scholar
- 28.Talkin, D. (1995). Speech Coding and Synthesis. Elsevier (pp. 497–518).Google Scholar
- 29.Kotnik, B., Hoge, H., Kacic, Z. (2006). Evaluation of Pitch Detection Algorithms in Adverse Conditions. Proc. 3rd International Conference on Speech Prosody (pp. 149–152). Dresden, Germany.Google Scholar