| Paper: | SP-L4.3 | ||
| Session: | Higher-Level Knowledge in Speaker Recognition | ||
| Time: | Wednesday, May 19, 16:10 - 16:30 | ||
| Presentation: | Lecture | ||
| Topic: | Speech Processing: Speaker Recognition | ||
| Title: | TEXT-INDEPENDENT SPEAKER RECOGNITION BY COMBINING SPEAKER-SPECIFIC GMM WITH SPEAKER ADAPTED SYLLABLE-BASED HMM | ||
| Authors: | Seiichi Nakagawa; Toyohashi University of Technology | ||
| Wei Zhang; Toyohashi University of Technology | |||
| Mitsuo Takahashi; Toyohashi University of Technology | |||
| Abstract: | We presented a new text-independent speaker recognition method by combining speaker-specific Gaussian Mixture Model(GMM) with syllable-basedHMM adapted by MLLRor MAP (EuroSpeech 2003[16]). The robustness of this speaker recognition method for speaking styleÂfs change was evaluated in this paper. The speaker identification experiment using NTT database which consists of sentences data uttered at three speed modes (normal, fast and slow) by 35 Japanesespeakers(22 males and 13 females) on five sessions over ten months was conducted. Each speaker uttered only 5 training utterances (about 20 seconds in total). We obtained the accuracy of 98.8% for text-independent speaker identification for three speaking style modes (normal, fast, slow) by using a short test utterance (about 4 seconds). This result was superior to conventional methods for the same database. We show that the attractive result was brought from the compensational effect between speaker specific GMM and speaker adapted syllable based HMM. | ||
| Back | |||
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops