INFLUENCE OF LANGUAGES ON CELP CODECS PERFORMANCE

This paper investigates the performance of speech codec's that uses linear predictive coding (LPC), over different languages. Investigations show that most low-rate (8kbits/s and below) speech coders show bias towards non-accented English. When the coders are used for heavily accented English or other languages, significant performance degradation is noted. In order to judge the performance of the most popular speech codec’s (Speex and AMR), we encoded and decoded the speech samples from three different languages: English, Arabic and Lithuanian. The quality of transformed speech signals was estimated using two quality estimation techniques 3SQM and PESQ algorithms according to ITU recommendations P.563 and P.862. The results showed quality bias toward the English language – the scores were hgiher and the performance was more stable.

[1]  Manfred R. Schroeder,et al.  Code-excited linear prediction(CELP): High-quality speech at very low bit rates , 1985, ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2]  John H. L. Hansen,et al.  Discrete-Time Processing of Speech Signals , 1993 .

[3]  Ian S. Burnett,et al.  On the effects of accent and language on low rate speech coders , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[4]  A. Uvliden,et al.  Adaptive multi-rate. A speech service adapted to cellular radio network quality , 1998, Conference Record of Thirty-Second Asilomar Conference on Signals, Systems and Computers (Cat. No.98CH36284).

[5]  Vijay Parsa,et al.  Interaction of speech coders and atypical speech I: effects on speech intelligibility. , 2002, Journal of speech, language, and hearing research : JSLHR.

[6]  Joe F. Chicharo,et al.  Language-specific phonetic structure and the quantisation of the spectral envelope of speech , 2000, Speech Commun..