Comparative performance evaluation of MMSE-based speech enhancement techniques through simulation and real-time implementation
- 12 Downloads
In this article, a generic model of minimum mean square error (MMSE) based speech enhancement technique has been presented and implemented on the hardware. Models for different MMSE-based methods were obtained by changing the gain function in the generic model. In all the methods, modified cascaded median-based noise estimation method has been used for noise estimation. Performances of all these MMSE-based methods were compared, among themselves and also with the spectral subtraction method for speech enhancement. The results have been evaluated using objective measures, subjective measure and composite objective measures for different noisy speech files. Results, in terms of objective evaluation parameters, indicated that the adaptive β-order MMSE method yielded better performance than the other methods. In subjective quality test (according to MOS listening test), β-order MMSE and adaptive β-order MMSE method yielded high scores. Real-time implementation has been carried out using TMS320C6416T DSP starter kit and code composer studio software. Estimation of memory consumption and execution time has been done for all the methods.
KeywordsSpectral subtraction β-Order MMSE Speech enhancement Modified cascaded median based noise estimation TMS320C6416T DSK
I would like to thank Prof. Subrata Bhattacharya, Department of Electronics Engineering, Indian Institute of Technology (ISM), Dhanbad for his guidance and encouragement. I would also like to thank the Indian Institute of Technology (Indian School of Mines), Dhanbad for providing the financial support.
- Cohen, I. (2004). On the decision-directed estimation approach of Ephraim and Malah. In IEEE International Conference on Acoustics, Speech, and Signal Processing, 2004. Proceedings.(ICASSP-04), Montreal, Canada.Google Scholar
- Kumar, B. (2015). Spectral subtraction using modified cascaded median based noise estimation for speech enhancement. In ACM, 6th International Conference on Computer and Communication (ICCCT-15), MNNIT, Allahabad, India, 25–27 September 2015.Google Scholar
- Kumar, B. (2016). Mean-median based noise estimation method using spectral subtraction for speech enhancement technique. Indian Journal of Science and Technology, 9, 35.Google Scholar
- Pandey, P. C., & Tiwari, N. (2015). Speech enhancement using noise estimation based on dynamic quantile tracking for hearing impaired listeners. In IEEE, Proc. 21th National Conference on Communications (NCC 2015., IIT Mumbai, 2015).Google Scholar
- Rix, A. W., et al. (2001) Perceptual evaluation of speech quality, an objective method for end-to-end speech quality assessment of narrowband telephone networks and speech codecs. ITU-T Recommendation.862.Google Scholar
- Rix, A. W. (2003). Comparison between subjective listening quality and P. 862 PESQ score. In Proc. Meas. Speech Qual. Net.(MESAQIN) (pp. 17–25).Google Scholar
- Kumar, S. (2016). Performance evaluation of novel AMDF-based pitch detection scheme. ETRI Journal, 38(3), 425–434.Google Scholar
- Waddi, S. K., Pandey, T. C., & Tiwari N. (2013). Speech enhancement using spectral subtraction and cascaded-median based noise estimation for hearing impaired listeners. In IEEE, Twentieth National Conference on Communications (NCC), IIT Delhi.Google Scholar
- You, C. H., et al. (2003) Adaptive/spl beta/-order MMSE speech enhancement application for mobile communication in a car environment. In Fourth Pacific Rim Conference on Multimedia in Information, Communications and Signal Processing, vol. 3, IEEE.Google Scholar