“Speech book”版本间的差异
来自cslt Wiki
| 第2行： | 第2行： | ||
*[[媒体文件:20181224 speech book.pdf | Version 20181224]] | *[[媒体文件:20181224 speech book.pdf | Version 20181224]] | ||
| + | |||
| + | |||
| + | |||
| + | =语音识别基础知识= | ||
| + | ==语音是什么== | ||
| + | ==语音识别方法== | ||
| + | ==语音识别工具== | ||
| + | |||
| + | =语音识别基本流程= | ||
| + | ==语音识别流程速览== | ||
| + | ==声学特征== | ||
| + | ==GMM-HMM== | ||
| + | ==DNN== | ||
| + | ==解码器== | ||
| + | |||
| + | =语音识别实际问题= | ||
| + | ==说话人自适应== | ||
| + | ==噪声对抗与环境鲁棒性== | ||
| + | ==新词处理与领域泛化== | ||
| + | ==小语种识别== | ||
| + | ==关键词唤醒与嵌入式系统== | ||
| + | |||
| + | =前沿课题= | ||
| + | ==说话人识别== | ||
| + | ==语种识别== | ||
| + | ==情绪识别== | ||
| + | ==语音合成== | ||
2018年12月24日 (一) 06:41的版本
《语音识别基本法》
