CROVER: IMPROVING ROVER USING AUTOMATIC ERROR DETECTION
Industrial Technology for Speech Processing Applications
Přednášející: Kacem Abida, Autoři: Kacem Abida, Fakhri Karray, University of Waterloo, Canada; Wafa Abida, Vestec, Canada
Recognizer Output Voting Error Reduction (ROVER), is a well-known procedure for decoders’ combination aiming at reducing the Word Error Rate (WER) in transcription applications. However, it appears that this technique has reached a plateau in terms of performance. This paper presents a novel approach, cROVER, to boosting the current ROVER performance, by relying on a contextual analysis to trim erroneous words. Experiments have proven that it is possible to outperform ROVER, despite the high false positive rate of the error detection technique.
Informace o přednášce
Nahráno: | 2011-05-26 10:50 - 11:10, Club H |
---|---|
Přidáno: | 9. 6. 2011 23:34 |
Počet zhlédnutí: | 16 |
Rozlišení videa: | 1024x576 px, 512x288 px |
Délka videa: | 0:16:35 |
Audio stopa: | MP3 [5.66 MB], 0:16:35 |
Komentáře