连续隐马尔可夫模型和神经网络在说话人识别中的比较

Comparative Study of Continuous Hidden Markov Models and Artificial Neural Network on Speaker Recognition

连续隐马尔可夫模型(CHMM)和人工神经网络(ANN)广泛的应用于说话人识别系统中,本文分别建立基于这两种模型的说话人识别系统,提取感知谐波倒谱系数作为与文本有关的说话人识别的特征参数,并分别在理想和噪声环境下仿真比较。实验结果表明ANN和CHMM模型在理想环境下平均识别率基本一致,而在噪声环境下ANN模型鲁棒性明显优于CHMM模型,识别率较高。

The paper reports a comparative study between a continuous hidden Markov model （CHMM） and an artificial neural network （ANN） on a text dependent, closed set speaker recognition system in clean and noisy environment. Perception Harmonic Cepstral Coefficients（PHCC） are selected as the studied features. Two well -known recognition engines, CHMM and ANN, are conducted and compared. CHMM provides the same average identification rate as ANN on isolated digits in clean environment, moreover,the training of ANN is more effective in noisy environment.