| Presentation | 2013-05-16 An evaluation of the performance estimation of noisy and reverberant speech recognition with noisy and reverberant criteria NRSR-PD_n Takahiro FUKUMORI, Masato NAKAYAMA, Takanobu NISHIURA, Yoichi YAMASHITA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The noisy and reverberant speech degrades the recognition performance in the field of distant-talking speech recognition. It is possibly addressed by taking preventive methods against the degradation of recognition performance with the criteria for recognition performance estimation. We thus proposed new noisy and reverberation criteria, NRSR-PD_n (Noisy and Reverberant Speech Recognition criteria with PESQ and D_n) for recognition performance estimation. We first designed NRSR-PD_n with the relation among ISO3382 Annex A acoustic parameters, PESQ and speech recognition performance. We then estimated speech recognition performance based on our designed reverberation criteria, NRSR-PD_n. In evaluation experiments, we could confirm that the noisy and reverberant recognition performance could be accurately and robustly estimated with NRSR-PD_n. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Noisy and reverberant speech recognition / Performance estimation / PESQ / Acoustic parameters |
| Paper # | EA2013-6,SIP2013-6,SP2013-6 |
| Date of Issue |
| Conference Information | |
| Committee | SP |
|---|---|
| Conference Date | 2013/5/9(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) | An evaluation of the performance estimation of noisy and reverberant speech recognition with noisy and reverberant criteria NRSR-PD_n |
| Sub Title (in English) | |
| Keyword(1) | Noisy and reverberant speech recognition |
| Keyword(2) | Performance estimation |
| Keyword(3) | PESQ |
| Keyword(4) | Acoustic parameters |
| 1st Author's Name | Takahiro FUKUMORI |
| 1st Author's Affiliation | Graduate School of Information Science and Engineering, Ritsumeikan University() |
| 2nd Author's Name | Masato NAKAYAMA |
| 2nd Author's Affiliation | College of Information Science and Engineering, Ritsumeikan University |
| 3rd Author's Name | Takanobu NISHIURA |
| 3rd Author's Affiliation | College of Information Science and Engineering, Ritsumeikan University |
| 4th Author's Name | Yoichi YAMASHITA |
| 4th Author's Affiliation | College of Information Science and Engineering, Ritsumeikan University |
| Date | 2013-05-16 |
| Paper # | EA2013-6,SIP2013-6,SP2013-6 |
| Volume (vol) | vol.113 |
| Number (no) | 29 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |