| Presentation | 2011-12-19 A proposal of acoustic feature related to voice quality for estimation of similarity in singing voice Chifumi Suzuki, Hideki Bannno, Fumitada Itakura, Masanori MORISE, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This report proposes an acoustic feature set to evaluate similarity in singing voice. This study focuses on voice quality of a singer and spectral fluctuation in vibrato and evaluates similarity by using features related to the voice quality and the spectral fluctuation. The data used in the evaluation includes non-imitative singing voice and imitative singing voice of target singer, whose voice and singing style have strong individuality. The data also includes the target singer's voice extracted from CD. The acoustic feature for comparing voice quality between input and target singers is distribution of formant frequencies. The acoustic features for comparing spectrum fluctuation of vibrato are cepstral distortion and time series of spectral centroid. By comparing distributions of formant frequencies, since distributions of many vowels in imitative singing were close to that of CD, it can be concluded that voice quality of imitative singing is close to that of the target singer. In investigating spectral fluctuation of vibrato, it also can be concluded that imitative singing is close to singing of the target singer in spectral fluctuation of vibrato, by comparing cepstral distortion and time series of spectral centroid. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | singing voice / similarity evaluation / acoustic feature / vibrato |
| Paper # | NLC2011-44,SP2011-89 |
| Date of Issue |
| Conference Information | |
| Committee | NLC |
|---|---|
| Conference Date | 2011/12/12(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 proposal of acoustic feature related to voice quality for estimation of similarity in singing voice |
| Sub Title (in English) | |
| Keyword(1) | singing voice |
| Keyword(2) | similarity evaluation |
| Keyword(3) | acoustic feature |
| Keyword(4) | vibrato |
| 1st Author's Name | Chifumi Suzuki |
| 1st Author's Affiliation | Graduate School of Meijo University() |
| 2nd Author's Name | Hideki Bannno |
| 2nd Author's Affiliation | Graduate School of Meijo University |
| 3rd Author's Name | Fumitada Itakura |
| 3rd Author's Affiliation | Graduate School of Meijo University |
| 4th Author's Name | Masanori MORISE |
| 4th Author's Affiliation | College of Information Science and Engineering, Ritsumeikan University |
| Date | 2011-12-19 |
| Paper # | NLC2011-44,SP2011-89 |
| Volume (vol) | vol.111 |
| Number (no) | 364 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |