| Presentation | 2014-01-23 Fundamental study of speaker identification by the peripheral auditory model and deep neural network Masanori MORISE, Kenji OZAWA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In the recognition of linguistic information, the acoustic features for explaining the comprehensive structure of the power spectrum are important because they do not depend on the individuality. Other acoustic features would be important to deal with the speaker identification and emotion. Mel-frequency cepstrum coefficients (MFCC) has been used as one of the effective acoustic features for recognizing not only linguistic information, but also the speaker identification. However, MFCC is specialized to recognize the linguistic information. In this research, we focused on using the deep neural network (DNN) for speaker identification, and examined the acoustic features for achieving the high performance. The proposed method uses the output of peripheral auditory model as the input of DNN. An evaluation with 1480 speech samples uttered by two males and two females was carried out, and the effectiveness of the proposed method was discussed based on the result. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Speech analysis / speaker identification / peripheral auditory model / deep neural network |
| Paper # | SP2013-97 |
| Date of Issue |
| Conference Information | |
| Committee | SP |
|---|---|
| Conference Date | 2014/1/16(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) | Fundamental study of speaker identification by the peripheral auditory model and deep neural network |
| Sub Title (in English) | |
| Keyword(1) | Speech analysis |
| Keyword(2) | speaker identification |
| Keyword(3) | peripheral auditory model |
| Keyword(4) | deep neural network |
| 1st Author's Name | Masanori MORISE |
| 1st Author's Affiliation | Interdisciplinary Graduate School of Medicine and Engineering, University of Yamanashi() |
| 2nd Author's Name | Kenji OZAWA |
| 2nd Author's Affiliation | Interdisciplinary Graduate School of Medicine and Engineering, University of Yamanashi |
| Date | 2014-01-23 |
| Paper # | SP2013-97 |
| Volume (vol) | vol.113 |
| Number (no) | 404 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |