Abstract | ||
---|---|---|
Meeting transcription is one of the main tasks for large vocabulary automatic speech recognition (ASR) and is supported by several large international projects in the area. The conversational nature, the difficult acoustics, and the necessity of high quality speech transcripts for higher level processing make ASR of meeting recordings an interesting challenge. This paper describes the development and system architecture of the 2007 AMIDA meeting transcription system, the third of such systems developed in a collaboration of six research sites. Different variants of the system participated in all speech to text transcription tasks of the 2007 NIST RT evaluations and showed very competitive performance. The best result was obtained on close-talking microphone data where a final word error rate of 24.9% was obtained. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1007/978-3-540-68585-2_39 | CLEAR |
Keywords | Field | DocType |
meeting recording,high quality speech transcript,best result,system architecture,large international project,large vocabulary automatic speech,meeting transcription,nist rt evaluation,amida meeting transcription system,text transcription task | Transcription (biology),Computer science,Speech recognition | Conference |
Volume | ISSN | Citations |
4625 | 0302-9743 | 19 |
PageRank | References | Authors |
1.64 | 14 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Thomas Hain | 1 | 486 | 39.70 |
Lukas Burget | 2 | 169 | 14.43 |
John Dines | 3 | 42 | 3.47 |
Giulia Garau | 4 | 184 | 17.61 |
Martin Karafiát | 5 | 176 | 10.92 |
David van Leeuwen | 6 | 44 | 7.06 |
Mike Lincoln | 7 | 392 | 28.11 |
Vincent Wan | 8 | 373 | 35.85 |