| Presentation | 2014-12-16 A Study on Speaker Recognition Method in Consideration of Speaking Style Differences in Lecture Speech Kota NAKATSUJI, Masafumi NISHIDA, Seiichi YAMAMOTO, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Speaker recognition technology has been applied to achieve a variety of tasks such as minute taking and speaker search for a discussion and a meeting. In conventional studies, a speaker model trained in consideration of individuality has been mainly used to read speech. However, an influence on recognition accuracy with differences of speaking style has not been fully studied in the speaker recognition. Thus, we analyzed the influence on recognition accuracy with differences of speaking style from a viewpoint of within-speaker variance and between-speaker variance for lecture speech. We also applied a divided UBM, a LDA to distributions of UBM, and a LDA to a feature space of UBM as speaker recognition methods in consideration of differences of speaking style and evaluated an effectiveness of these methods compared with conventional UBM-MAP method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | speaker recognition / speaking style / lecture speech / linear discriminant analysis / within-speaker variance / between-speaker variance |
| Paper # | SP2014-123 |
| Date of Issue |
| Conference Information | |
| Committee | SP |
|---|---|
| Conference Date | 2014/12/8(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) | A Study on Speaker Recognition Method in Consideration of Speaking Style Differences in Lecture Speech |
| Sub Title (in English) | |
| Keyword(1) | speaker recognition |
| Keyword(2) | speaking style |
| Keyword(3) | lecture speech |
| Keyword(4) | linear discriminant analysis |
| Keyword(5) | within-speaker variance |
| Keyword(6) | between-speaker variance |
| 1st Author's Name | Kota NAKATSUJI |
| 1st Author's Affiliation | Graduate School of Engineering, Doshisha University() |
| 2nd Author's Name | Masafumi NISHIDA |
| 2nd Author's Affiliation | Institute of Innovation for Future Society, Nagoya University |
| 3rd Author's Name | Seiichi YAMAMOTO |
| 3rd Author's Affiliation | Graduate School of Engineering, Doshisha University |
| Date | 2014-12-16 |
| Paper # | SP2014-123 |
| Volume (vol) | vol.114 |
| Number (no) | 365 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |