| Presentation | 2011-12-19 Speaker Clustering Using Speaker Subspace Obtained Dynamically Based on Variance of Intra-Utterance Yuki ISHIKAWA, Masafumi NISHIDA, Seiichi YAMAMOTO, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Speech has two types of information, such as phoneme and speaker. If these information are separated, robust speaker clustering can be achieved. It is necessary to suppress the phonetic information for each utterance because variance of utterance duration is large in multi-party conversation. We propose a speaker clustering method using Gaussian mixture model in flexibly selected speaker subspace based on variance of intra-utterance. We carried out speaker clustering experiments compared with conventional methods based on Bayesian information criterion and Gaussian mixture model in an observation space. The experimental results showed that the proposed method can achieve higher clustering accuracy than conventional methods. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | speaker clustering / variance of intra-utterance / speaker subspace / Gaussian mixture model / principal component analysis |
| Paper # | NLC2011-42,SP2011-87 |
| 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) | Speaker Clustering Using Speaker Subspace Obtained Dynamically Based on Variance of Intra-Utterance |
| Sub Title (in English) | |
| Keyword(1) | speaker clustering |
| Keyword(2) | variance of intra-utterance |
| Keyword(3) | speaker subspace |
| Keyword(4) | Gaussian mixture model |
| Keyword(5) | principal component analysis |
| 1st Author's Name | Yuki ISHIKAWA |
| 1st Author's Affiliation | Graduate School of Engineering, Doshisha University() |
| 2nd Author's Name | Masafumi NISHIDA |
| 2nd Author's Affiliation | Graduate School of Engineering, Doshisha University |
| 3rd Author's Name | Seiichi YAMAMOTO |
| 3rd Author's Affiliation | Graduate School of Engineering, Doshisha University |
| Date | 2011-12-19 |
| Paper # | NLC2011-42,SP2011-87 |
| Volume (vol) | vol.111 |
| Number (no) | 364 |
| Page | pp.pp.- |
| #Pages | 5 |
| Date of Issue | |