| Presentation | 1997/2/21 Sound Source Identification Using Adaptive Template Mixtures : Formulation and Application to Music Stream Segregation Kunio Kashino, Hiroshi Murase, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Sound source identification is an essential problem in auditory scene analysis when multiple acoustical objects are simultaneously present in the scene. However, little work has been done on sound source identificaiton for a multiple-source environment. Here we propose a novel method for sound source identification. The key idea is adaptation of templates, which has permitted to cope with variation of sounds. As an example application of the proposed method, we have built a music recognition system that recognizes instrument names and pitches of the notes included in ensemble music performances. Experimental results show that the proposed adaptive mechanisms significantly improve the accuracy of sound source identification in comparison to a conventional matched-filter-based method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | auditory scene analysis, sound source identification, sound source separation, music scene analysis, automatic music transcription, matched filter |
| Paper # | SP96-117 |
| Date of Issue |
| Conference Information | |
| Committee | SP |
|---|---|
| Conference Date | 1997/2/21(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) | Sound Source Identification Using Adaptive Template Mixtures : Formulation and Application to Music Stream Segregation |
| Sub Title (in English) | |
| Keyword(1) | auditory scene analysis, sound source identification, sound source separation, music scene analysis, automatic music transcription, matched filter |
| 1st Author's Name | Kunio Kashino |
| 1st Author's Affiliation | NTT Basic Research Laboratories() |
| 2nd Author's Name | Hiroshi Murase |
| 2nd Author's Affiliation | NTT Basic Research Laboratories |
| Date | 1997/2/21 |
| Paper # | SP96-117 |
| Volume (vol) | vol.96 |
| Number (no) | 540 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |