9P-C-2 聴覚末梢系モデルから得られる多次元パルス信号を用いた話者識別(C会場 大学院生・学部学生 奨励賞セッション)

抄録

This paper discusses an approach for speaker identification using multi-dimensional pulse signals generated from a model of a peripheral auditory system. The peripheral auditory system employed consists of a basilar membrane, hair cells, and auditory nerves. The input to this system is a speech signal divided into frames, and the outputs from which are the multi-dimensional pulse signals for each framed signal. The feature vector based on the post-stimulus time histogram (PSTH) of the pulse signals is used for the speaker identification. Also, in order to improve the accuracy of the speaker identification, the feature vector conversion using its mean and standard deviation is performed. The experiments were conducted for each Japanese vowel spoken by 12 speakers (9 males and 3 females), and the identification accuracy is evaluated by 5 hold leave 2 out cross-validation for each vowel. The effectiveness of the proposed method has been verified by comparing with the conventional LPC analysis.