Name
Abstract | ||
|---|---|---|
This paper describes experiments carried out to automatically transcribe football commentaries in Dutch, English and German for multimedia indexing. Our r esults s how that t he high levels of stadium noise in the material create a task that is extremely difficult for conventional ASR. The baseline WERs vary from 83% to 94 % for the three languages investigated. Employing state-of-the-art noise robustness techniques leads to relative reductions of 9-10% WER. Application specific words s uch as players' names are recognized correctly in about 50% of cases. Although this result i s s ubstantially better than the overall result, it i s inadequate. Much better results can be obtained if the football commentaries are recorded separately from the stadium noise. This would make the automatic transcriptions more useful for multimedia indexing. |
Year | Venue | Keywords |
|---|---|---|
2003 | INTERSPEECH | speech |
Field | DocType | Citations |
Football,Transcription (linguistics),Application specific,Stadium,Computer science,Robustness (computer science),Speech recognition,Multimedia indexing,German | Conference | 2 |
PageRank | References | Authors |
0.40 | 9 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Janienke Sturm | 1 | 356 | 36.54 |
| Judith M. Kessens | 2 | 136 | 16.05 |
| Mirjam Wester | 3 | 276 | 27.25 |
| Febe de Wet | 4 | 139 | 27.57 |
| Eric Sanders | 5 | 138 | 27.90 |
| Helmer Strik | 6 | 430 | 74.89 |