An improved speech analysis-synthesis algorithm based on the autoregressive with exogenous input speech production model
An improved speech analysis-synthesis algorithm based on the autoregressive with exogenous input speech production model
复制标题
基于外源输入语音产生模型自回归的改进语音分析合成算法
DOI：
10.21437/icslp.2000-387
复制
发表时间：
2000
期刊：
影响因子：
--
通讯作者：
H. Kasuya
中科院分区：
文献类型：
--
作者：
Takahiro Ohtsuka;H. Kasuya
Ding等人基于具有外源输入的自回归（ARX）语音产生模型探索了一种新颖的音高同步语音分析-合成方法[1]。该方法从语音中自动估计声道（共振峰）和声源参数。然而，这种方法在分析高音语音和在元音和弱浊辅音段之间的过渡中引入咔嗒声方面存在缺陷。针对上述问题，提出了一种改进的ARX方法.感知对比实验表明，该方法合成的语音质量高于已知的倒谱方法。
Ding et al. have explored a novel pitch-synchronous speech analysis-synthesis method[1] based on an auto-regressive with exogenous input (ARX) speech production model. This method makes an automatic estimation of the vocal tract (formant) and voice source parameters from a speech utterance. This method, however, has suffered deficiencies in the analysis of a high-pitch voice and the introduction of click sounds in the transition between vocalic and weak voiced consonantal segments. This paper proposes an improved ARX method in order to solve the problems mentioned above. Perceptual comparison experiments have shown that quality of re-synthesized speech by the proposed method is higher than that by a well-known cepstral method.