Speaker verification by integrating dynamic and static features using subspace method
Masafumi Nishida, Yasuo Ariki · 2000
In speaker recognition, it is a problem that variation of speech features is caused by sentences and time difference. Speech data includes a phonetic information and a speaker information. If they are separated each other, robust speaker verification will be realized by using only the speaker information. However, it is difficult to separate the speaker information from the phonetic information included in speech data at present. From this viewpoint, we propose a speaker verification method using a subspace method based on principal component analysis in order to extract only the speaker information included in speech data. We also propose dynamic and static features of each speaker presented in the speaker eigenspace as well as their integration for robust normalization of speech feature variations. We carried out comparative experiments between the proposed method and conventional GMM to show an effectiveness of our proposed method. As a result, integrated dynamic and static features in speaker eigenspace were shown to be effective for speaker verification. 1.