Abstract | ||
---|---|---|
This paper describes the year 2000 BBN Byblos Mandarin large vocabulary conversational speech recognition (LVCSR) system, the winning (and only) Mandarin system from the Spring 2 000 Hub-5 evaluation sponsored by NIST. We first outline the training and d ecoding procedures used in the system, and describe the performance of the system used in the e valuation. We then d escribe the e ffect of several features that were not in the e valuation system but have been added since, including Jacobian compensated Vocal Tract Length Normalization (VTLN), system combination, a higher number of system parameters, and additional training data. Together these give a n additional 5.4% relative improvement on character error r ate (CER) from the evaluation system. |
Year | Venue | Field |
---|---|---|
2000 | INTERSPEECH | Training set,System combination,Evaluation system,Normalization (statistics),Computer science,Speech recognition,NIST,Vocabulary,Vocal tract,Mandarin Chinese |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
4 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Han Shu | 1 | 3 | 0.79 |
Chuck Wooters | 2 | 404 | 58.49 |
Owen Kimball | 3 | 83 | 17.82 |
Thomas Colthurst | 4 | 78 | 7.71 |
Fred Richardson | 5 | 179 | 18.80 |
Spyros Matsoukas | 6 | 449 | 37.56 |
Herbert Gish | 7 | 447 | 100.85 |