遵循的规范 发表于 2025-4-1 03:19:36

The Use of Recurrent Neural Networks in Continuous Speech Recognition, decoding). The advantages of using recurrent networks are that they require a small number of parameters and provide a fast decoding capability (relative to conventional, large-vocabulary, HMM systems)..

jaundiced 发表于 2025-4-1 07:13:30

An Overview of Speaker Recognition Technology,include parameter/distance normalization techniques, model adaptation techniques, VQ-/ergodic-HMM-based text-independent recognition methods, and a text-prompted recognition method. The chapter concludes with a short discussion assessing the current status and possibilities for the future.

常到 发表于 2025-4-1 13:14:56

http://reply.papertrans.cn/17/1665/166452/166452_63.png
页: 1 2 3 4 5 6 [7]
查看完整版本: Titlebook: Automatic Speech and Speaker Recognition; Advanced Topics Chin-Hui Lee,Frank K. Soong,Kuldip K. Paliwal Book 1996 Kluwer Academic Publisher