摘要
In this paper we study various front-end features, modeling and adaptation algorithms on the Aurora 3 databases, including auditory, moment, and AM-FM modulation features, context-dependent digit models, segmental K-means training, discriminative training, and model adaptations. The evaluation results on Aurora 3 are presented with a brief summary of our Aurora 2 results.
源语言 | 英语 |
---|---|
页 | 229-232 |
页数 | 4 |
出版状态 | 已出版 - 2002 |
已对外发布 | 是 |
活动 | 7th International Conference on Spoken Language Processing, ICSLP 2002 - Denver, 美国 期限: 16 9月 2002 → 20 9月 2002 |
会议
会议 | 7th International Conference on Spoken Language Processing, ICSLP 2002 |
---|---|
国家/地区 | 美国 |
市 | Denver |
时期 | 16/09/02 → 20/09/02 |