| Presentation | 2004/12/14 A Study of Talker Localization Based on Subband CSP Analysis Yuki DENDA, Takanobu NISHIURA, Hideki KAWAHARA, Toshio IRINO, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | It is very important to capture distant-talking speech with high quality for voice-controlled systems or teleconferencing systems. A microphone array steering is an idela candidate as an effective method for capturing distant talking speech with high quality. However, it requires to localize a target talker before capturing distant-talking speech. For this purpose, a talker localization method based on GSP (Cross-power Spectrum Phase) analysis has been proposed, for example. However, talker localization performance of the CSP analysis is degraded in higher noisy environments. To deal with this problem, in this papaer, we propose a subband CSP analysis with weighting of average speech spectrum and we propose a specialized localization method for speech. In addition, we evaluate the ASR (Automatic Speech Recognition) performance when the microphone array steering is steered to the estimated talker direction by the proposed method. As a result of evaluation experiments in a real room, we confirmed that the proposed method provides better talker localization performance than the conventional method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Talker localization / CSP analysis / Subband analysis / Microphone array / Speech recognition |
| Paper # | NLC2004-69,SP2004-109 |
| Date of Issue |
| Conference Information | |
| Committee | NLC |
|---|---|
| Conference Date | 2004/12/14(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 | Natural Language Understanding and Models of Communication (NLC) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Study of Talker Localization Based on Subband CSP Analysis |
| Sub Title (in English) | |
| Keyword(1) | Talker localization |
| Keyword(2) | CSP analysis |
| Keyword(3) | Subband analysis |
| Keyword(4) | Microphone array |
| Keyword(5) | Speech recognition |
| 1st Author's Name | Yuki DENDA |
| 1st Author's Affiliation | Graduate School of Systems Engineering, Wakayama University() |
| 2nd Author's Name | Takanobu NISHIURA |
| 2nd Author's Affiliation | College of Information Science and Engineering, Ritsumeikan University |
| 3rd Author's Name | Hideki KAWAHARA |
| 3rd Author's Affiliation | Graduate School of Systems Engineering, Wakayama University |
| 4th Author's Name | Toshio IRINO |
| 4th Author's Affiliation | Graduate School of Systems Engineering, Wakayama University |
| Date | 2004/12/14 |
| Paper # | NLC2004-69,SP2004-109 |
| Volume (vol) | vol.104 |
| Number (no) | 539 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |