| Presentation | 2015-12-08 Realtime Detection of Speaker Change Considering Mobile Device Environment Masashi Tateno, Eiji Kamioka, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Aiming at achieving a high performance speaker change detection using mobile-devices, the extraction of each person’s individuality in the vocal tract characteristic using the cepstrum information has been proposed. However, the use of a combined characteristic, which is created from several characteristics, is more advantageous than the one of single characteristic in order to improve the accuracy of speaker change detection. In addition, the appropriate threshold value to the combined characteristic is needed to decide if the speaker change has occurred or not. In this paper, in the speaker change detection, the most effective combination of characteristics among Mel-Cepstrum, fundamental frequency, MFCC, and their Δ and ΔΔ parameters will be discussed. Moreover, the most appropriate threshold value of the combined characteristic to the speaker change detection will be shown. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Speaker Change Detection / Speaker Verification / Mel-Cepstrum / Fundamental Frequency / Vocal Tract Characteristics / Mel Scale |
| Paper # | WIT2015-64 |
| Date of Issue | 2015-12-01 (WIT) |
| Conference Information | |
| Committee | WIT / HI-SIGACI |
|---|---|
| Conference Date | 2015/12/8(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | AIST Tokyo Waterfront |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Well-being Information Technology, etc. |
| Chair | Kiyohiko Nunokawa(Tokyo International Univ.) / Makoto Kobayashi(筑波技術大学) |
| Vice Chair | Chikamune Wada(Kyushu Inst. of Tech.) / Sumihiro Kawano(筑波技術大学) |
| Secretary | Chikamune Wada(Nagoya Inst. of Tech.) / Sumihiro Kawano(AIST) |
| Assistant | Tomohiro Amemiya(NTT) / Takeaki Shionome(Tsukuba Univ. of Tech.) / Manabi Miyagi(Tsukuba Univ. of Tech.) |
| Paper Information | |
| Registration To | Technical Committee on Well-being Information Technology / * |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Realtime Detection of Speaker Change Considering Mobile Device Environment |
| Sub Title (in English) | |
| Keyword(1) | Speaker Change Detection |
| Keyword(2) | Speaker Verification |
| Keyword(3) | Mel-Cepstrum |
| Keyword(4) | Fundamental Frequency |
| Keyword(5) | Vocal Tract Characteristics |
| Keyword(6) | Mel Scale |
| 1st Author's Name | Masashi Tateno |
| 1st Author's Affiliation | Shibaura Institute of Technology(SIT) |
| 2nd Author's Name | Eiji Kamioka |
| 2nd Author's Affiliation | Shibaura Institute of Technology(SIT) |
| Date | 2015-12-08 |
| Paper # | WIT2015-64 |
| Volume (vol) | vol.115 |
| Number (no) | WIT-354 |
| Page | pp.pp.7-12(WIT), |
| #Pages | 6 |
| Date of Issue | 2015-12-01 (WIT) |