| Presentation | 2002/10/23 Simultaneous Subtitling System for Live Broadcast Programs with a Speech Recognizer Akio Ando, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper introduces two simultaneous subtitling systems using speech recognition technology. One is a system for broadcast news programs which recognizes announcers' speech in the news program and consists of a broadcast news speech transcription system and a recognition-error correction system. In the system, speech recognition errors are corrected manually with short delay time in order to implement error-free simultaneous subtitled broadcasting. The other is a system for live variety program and live sports broadcasting. This system, which uses re-speak method, recognizes re-spoken speech in the studio, instead of speech in the program, to handle high levels of background noise and spontaneity in the speaking style. NHK (Japan Broadcasting Corporation) started simultaneous subtitled broadcasting for the news program, "News 7", on March 27, 2000 using the former system and simultaneous subtitled broadcasting for "Kohaku Utagassen" on December 31, 2001 using the latter system. The latter system was also used for subtitled broadcasting of the Winter Olympic Games from Salt Lake City in February 2002. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Caption broadcasting / Speech recognition / Recognition-error correction / Re-speak / Real-time system |
| Paper # | WIT2002-40 |
| Date of Issue |
| Conference Information | |
| Committee | WIT |
|---|---|
| Conference Date | 2002/10/23(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 | Well-being Information Technology(WIT) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Simultaneous Subtitling System for Live Broadcast Programs with a Speech Recognizer |
| Sub Title (in English) | |
| Keyword(1) | Caption broadcasting |
| Keyword(2) | Speech recognition |
| Keyword(3) | Recognition-error correction |
| Keyword(4) | Re-speak |
| Keyword(5) | Real-time system |
| 1st Author's Name | Akio Ando |
| 1st Author's Affiliation | Three Dimensional Audio-visual Systems, NHK Science and Technical Research Laboratories() |
| Date | 2002/10/23 |
| Paper # | WIT2002-40 |
| Volume (vol) | vol.102 |
| Number (no) | 419 |
| Page | pp.pp.- |
| #Pages | 2 |
| Date of Issue | |