Open Access Open Access  Restricted Access Subscription or Fee Access

A Technical Review on Comparison of Speech Enhancement Algorithms

Rajesh Kumar, Vinay Gupta

Abstract


The use of mobile speech communication devices has increased by manifold. Mobile communication technology is providing us the mobility and exhibility to communicate irrespective of place and time. The result is that the mobile voice communication systems are often used in high acoustic background noise environment. In such circumstances speech communication suffers from lack of pleasantness and/ intelligibility. To make voice communication intelligible and pleasant in such noisy environments, we investigate new methods of enhancing background noise corrupted speech signal in this report. We consider that the noisy speech signal is recorded using a close talking microphone (like the case of a mobile phone). Various SE methods have been proposed over the last two decades differing in statistical model used for the clean speech signal. The existing SE methods do not exploit the dependency of among the transform domain coefficients. They enhance each coefficient independent of the others. We compare the SE performances of the developed SE methods with that of the state-of-art SE algorithms.

Keywords: noisy speech, reverberant speech, speech enhancement, spectral processing, temporal processing

Full Text:

PDF

References


Boll S. Suppression of acoustic noise in speech using spectral subtraction. IEEE Trans. Acoust., Speech, Signal process. 1979; ASSP-27: 113-20p.

Cohen I. Speech Signal Processing. 2002; 208–11p.

Optimal speech enhancement under signal presence uncertainty using log-spectral amplitude estimator. IEEE Signal Process. Lett. 9: 113–6p.

Nakatani, Miyoshi M. Blind dereverberation of single channel speech signal based on harmonic structure. In Proc. IEEE Int. Conf. Acoust., Speech, Signal process. Hong Kong, China PR. 2003; 1: 9–5p.

Ephraim Y., Malah D. Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator. IEEE Trans. Acoust. Speech Signal Process. 1984; ASSP-32: 1109–21p.

Ephraim Y., Malah D. Speech enhancement using a minimum mean-square error log-spectral amplitude estimator. IEEE Trans. Acoust. Speech Signal Process. 1985; ASSP-33: 443–5p.

Yegnanarayana B., Avendano C., Hermansky H. et al. Speech enhancement using linear prediction residual. Speech Communication. 1999; 28: 25-42p.

Stubbs R. J., Summerfield Q. Algorithms for separating the speech of interfering talkers: Evaluations with voiced sentences, and normal-hearing and hearing-impaired listeners. J. Acoust. Soc. Am. 1990; 87(1): 359-72p.

Oppenheim R., Schafer, J., Stockham T.G. Filtering Of Multiplied And Convolved Signals. Proc. IEE. 1968; 1264-91p.

Hu Y., Loizou P.C.. Speech enhancement basedon wavelet thresholding the multitaper spectrum. IEEE Trans. Speech Audio Proc. 2004; 59–67p.

Avendano, Hermansky H. Study on the dereverberation of speech based on temporal envelope filtering. In Proc. Fourth Int. Conf. Spoken Language. 1996 Oct.; 2: 889–92p.




DOI: https://doi.org/10.37628/jdcas.v2i1.276

Refbacks

  • There are currently no refbacks.