Presentation | 2007/12/13 Text-independent speaker verification experiment using a large-scale bone-conducted speech database Masahiko KITA, Shingo KUROIWA, Satoru TSUGE, Hisanori MAKINAE, Takashi OSANAI, Toshiaki KAMADA, Masumi TANIMOTO, Seiji TSUCHIYA, Minoru FUKUMI, Fuji REN, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, we conducted a speaker verification experiment using large-scale speech database maintained by National Research Institute of Police Science, Japan. In this experiment, we used speech data of 664 people collected by a capacitor microphone and a bone-conducted microphone. From experimental results, we confirmed that our proposed method that uses rank information obtained by multiple speaker model in previous work improved verification performance than a conventional method using T-norm score. In addition, we compared the speaker model based on GMMs and that based on VQ centroids. From this comparison, we can see that the speaker model based on VQ centroids is higher performance than that based on GMMs under the condition of the capacitor microphone speech. However, VQ centroids degraded the performance of that based on GMMs under the condition of the bone-conducted speech. Moreover, the performances of the bone-conducted speech significant degraded performance if there were difference of the speaking session between the registration and the testing. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | bioinformatics / speaker verification / bone-conduction speech |
Paper # | NLC2007-64,SP2007-127 |
Date of Issue |
Conference Information | |
Committee | SP |
---|---|
Conference Date | 2007/12/13(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Speech (SP) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Text-independent speaker verification experiment using a large-scale bone-conducted speech database |
Sub Title (in English) | |
Keyword(1) | bioinformatics |
Keyword(2) | speaker verification |
Keyword(3) | bone-conduction speech |
1st Author's Name | Masahiko KITA |
1st Author's Affiliation | The University of Tokushima() |
2nd Author's Name | Shingo KUROIWA |
2nd Author's Affiliation | Chiba University |
3rd Author's Name | Satoru TSUGE |
3rd Author's Affiliation | The University of Tokushima |
4th Author's Name | Hisanori MAKINAE |
4th Author's Affiliation | National Research Institute of Police Science |
5th Author's Name | Takashi OSANAI |
5th Author's Affiliation | National Research Institute of Police Science |
6th Author's Name | Toshiaki KAMADA |
6th Author's Affiliation | National Research Institute of Police Science |
7th Author's Name | Masumi TANIMOTO |
7th Author's Affiliation | National Research Institute of Police Science |
8th Author's Name | Seiji TSUCHIYA |
8th Author's Affiliation | The University of Tokushima |
9th Author's Name | Minoru FUKUMI |
9th Author's Affiliation | The University of Tokushima |
10th Author's Name | Fuji REN |
10th Author's Affiliation | The University of Tokushima |
Date | 2007/12/13 |
Paper # | NLC2007-64,SP2007-127 |
Volume (vol) | vol.107 |
Number (no) | 406 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |