摘要
文章阐述了多带激励（ＭＢＥ）语音产生模型与以往单一激励语音产生模型的区别及其优越性。研究了以ＭＢＥ模型为基础进行语音分析合成的基本原理和实现的算法。提出了４．８ｋｂｐｓＭＢＥ语音编码方案，并在计算机上进行了模拟实现。实验结果表明，所模拟的４．８ｋｂｐｓＭＢＥ语音编码器系统是成功的。其合成语音在可懂度与自然度方面，与以往的线性预测（ＬＰＣ）、码激励线性预测（ＣＥＬＰ）语音编码系统相比都有了明显的改善。
The differences between multi-band excited(MBE)speech model and pitch excited linearpredictive coding(LPC)speech model,and the advantages of MBE model over the conven-tional excited model are presented in this paper.The principles and algorithms of speech analy-sis/synthesis based upon MBE model are studied.The approaches ofspeech coding at 4.8 kbpsare presented and simulated with computer. Experimental results show that the method ofMBE speech coding at4.8 kbps is reliable and its synthesized speech is highly understandableand natural compared with that of conventional speech coder.
出处
《西安电子科技大学学报》
EI
CAS
CSCD
北大核心
1995年第3期227-234,共8页
Journal of Xidian University
