Speech Compression for Noise-Corrupted Thai Dialects | Science Publications

American Journal of Applied Sciences

Suphattharachai Chomphan¹ 

关键词: Adaptive pulse;    Conjugate Structure Algebraic Code Excited Linear Predictive (CS-ACELP);    speech coding;    bitrate scalability;    Linear Prediction (LP);    noise-corrupted speech;    Thai dialects;    coding rate;    speech communication;   

DOI  :  10.3844/ajassp.2012.278.282

学科分类：自然科学（综合）

来源: Science Publications

【 摘 要 】

Problem statement: Dialects of Thai are quite different in the speaking styles.Environmental noises play an important role in corrupting the communication speech quality. Twofactors affect the coded speech in the present speech communication. It is necessary to investigate howthe two factors influence on the speech compression. Approach: In this study, the Multi-Pulse basedCode Excited Linear Predictive (MP-CELP) coder and the Conjugate Structure Algebraic CodeExcited Linear Predictive (CS-ACELP) coder are selected as the coding methods. This study showsthe effects of the six kinds of noise to speech coding quality. The comparison of speech quality ofthe four coded Thai dialects is conducted. The speech material includes a hundred male speechutterances and a hundred female speech utterances. Four speaking styles include Thai Northern, NorthEastern, Southern and Central dialects. Five sentences of Thai speech are chosen. Six types of noiseinclude train, factory, motorcycle, air conditioner, men speaker and women speaker. Moreover, fivelevels of each type of noise are varied from 0-20 dB. The subjective test of mean opinion score areexploited in the evaluation process. Results: The experimental results show that CS-ACELP givesbetter speech quality than that of MP-CELP at all three bitrates of 6000, 8600 and 12600 bps. Whenconsidering the levels of noise, the 20-dB noise gives the best speech quality, while 0-dB noisegives the worst speech quality. When considering the speech gender, male speech gives betterresults than that of female speech. When considering the types of dialect, the central dialect givesthe best speech quality, while the North dialect gives the worst speech quality. Finally, whenconsidering the types of noise, the air-conditioner noise gives the best speech quality, while the trainnoise gives the worst speech quality. Conclusion: From the study, it can be seen that codingmethod, type of noise, level of noise, speech gender and dialect influence on the coding speechquality.

【 授权许可】

Unknown