| Presentation | 2014-10-24 Speech enhancement techniques in multi-speaker spontaneous speech recognition for conversation scene analysis(Invited Talk) Shoko ARAKI, Takaaki HORI, Tomohiro NAKATANI, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper illustrates speech enhancement techniques for multi-speaker distant-talk speech recognition, where a conversation scene analysis is adopted as a test scenario. Our speech enhancement techniques include dereverberation, speech separation, and noise suppression. Because some of our techniques employ both the spatial information of speech sources and the speech spectrum information, their output signals become suitable for the input of a speech recognizer. We report the latest speech enhancement techniques and their speech recognition performance in a real conversation. Moreover, the effect of deep learning in multi-speaker speech recognition is also discussed. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Conversation scene analysis / dereverberation / speech separation / noise suppression / speech recognition with DNN-HMM |
| Paper # | EA2014-25 |
| Date of Issue |
| Conference Information | |
| Committee | EA |
|---|---|
| Conference Date | 2014/10/17(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 | Engineering Acoustics (EA) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Speech enhancement techniques in multi-speaker spontaneous speech recognition for conversation scene analysis(Invited Talk) |
| Sub Title (in English) | |
| Keyword(1) | Conversation scene analysis |
| Keyword(2) | dereverberation |
| Keyword(3) | speech separation |
| Keyword(4) | noise suppression |
| Keyword(5) | speech recognition with DNN-HMM |
| 1st Author's Name | Shoko ARAKI |
| 1st Author's Affiliation | NTT Communication Science Laboratories, NTT Corporation() |
| 2nd Author's Name | Takaaki HORI |
| 2nd Author's Affiliation | NTT Communication Science Laboratories, NTT Corporation |
| 3rd Author's Name | Tomohiro NAKATANI |
| 3rd Author's Affiliation | NTT Communication Science Laboratories, NTT Corporation |
| Date | 2014-10-24 |
| Paper # | EA2014-25 |
| Volume (vol) | vol.114 |
| Number (no) | 274 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |