语音识别

语音识别

语音识别，Automatic Speech Recognition，简称ASR

基本工具

LSTM

Long short term memory neural network

1. Long short term memory neural computation, Neural computation 9 (8), 1735-1780, 1997. LSTM

CTC

Connectionist temporal classification

1. Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks, ICML 2006.

GRU

Gated Recursive Unit

1. On the Properties of Neural Machine Translation: Encoder-Decoder Approaches, SSST-8, 2014.

研究

传统方法综述

1. S. Karpagavalli and E. Chandra. "A Review on Automatic Speech Recognition Architecture and Approaches." International Journal of Signal Processing, Image Processing and Pattern Recognition 9, No. 4 (2016): 393-404.

Google

Alex Graves，DeepMind研究员，语音识别多项技术开创者

1. Speech recognition with deep recurrent neural networks, 2013.
2. Hybrid speech recognition with deep bidirectional LSTM, ASRU 2013.
3. Towards End-To-End Speech Recognition with Recurrent Neural Networks, ICML 2014.
4. Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks, ICML 2006.

Google Speech

1. Google Speech Processing from Mobile to Farfield, CHiME 2016. Google_Speech_Processing

1. Listen, attend and spell: A neural network for large vocabulary conversational speech recognition, ICASSP 2015.
2. Convolutional, long short-term memory, fully connected deep neural networks, ICASSP 2015.
3. Context dependent phone models for LSTM RNN acoustic modelling, ICASSP 2015.
4. Learning the Speech Front-end With Raw Waveform CLDNNs, InterSpeech 2015.

Baidu

1. Deep Speech 2 End-to-End Speech Recognition in English and Mandarin, JMLR 2016.
2. Gram-CTC: Automatic Unit Selection and Target Decomposition for Sequence Labelling