更改

Student-Research-Training-THU

添加284字节2017年11月21日 (二) 02:50
/* ASR语音识别 */
==ASR语音识别==
 
Recent progresses in deep learning based acoustic models, 2017.
Multichannel Signal Processing with Deep Neural Networks for Automatic Speech Recognition, TASLP 2017.
DeepSpeech3 Exploring Neural Transducers for End-to-End Speech Recognition. https://arxiv.org/abs/1707.07413.
Cold Fusion: Training Seq2Seq Models Together with Language Models, 2017. https://arxiv.org/abs/1708.06426.
==选择==
行政员管理员
6,105
个编辑