Improvement of Speaker Vector-Based Speaker Verification

摘要：

This paper describes the improvement in the performance of a text-independent speaker verification based on a speaker vector. The verification system is based on the technique of anchor models. In our previous work, the performance improvement could be obtained by using phoneticbased models instead of Gaussian mixture models (GMMs) in speaker identification. This is because the phonetic models can represent a detailed difference in pronunciation. Therefore, we aim to improve the performance of speaker verification by using phonetic-based modeling. Comparative experiments between GMMs and Hidden Markov Models (HMMs) were conducted in the speaker verification task. In the experiments, the EER of 2.68％ was obtained at 1000-dimensional speaker space when HMMs were used as anchor models.

关键词： speaker recognition speaker veri.cation hidden Markov model (HMM) Gaussian mizture model (GMM) KL transform

作者: Naoki Tadokoro Tetsuo Kosaka Masaharu Kato Masaki Kohda

作者单位: Graduate School of Science and Engineering,Yamagata University Yonezawa-city,Yamagata,992-8510 Japan

会议类型: 国际会议

会议名称: The Fifth International Conference on Information Assurance and Security(第五届信息保障与安全国际会议)

会议地点: 西安

会议语种:英文

页码: 721-724

在线出版日期: 2009-08-18（万方平台首次上网日期，不代表论文的发表时间）