Speech recognition with deep recurrent neural networks

Alex Graves, Abdel-rahman Mohamed, Geoffrey Hinton
2013 2013 IEEE International Conference on Acoustics, Speech and Signal Processing  
Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist Temporal Classification make it possible to train RNNs for sequence labelling problems where the input-output alignment is unknown. The combination of these methods with the Long Short-term Memory RNN architecture has proved particularly fruitful, delivering state-of-the-art results in cursive handwriting recognition. However RNN performance in speech recognition has so
more » ... r been disappointing, with better results returned by deep feedforward networks. This paper investigates deep recurrent neural networks, which combine the multiple levels of representation that have proved so effective in deep networks with the flexible use of long range context that empowers RNNs. When trained end-to-end with suitable regularisation, we find that deep Long Short-term Memory RNNs achieve a test set error of 17.7% on the TIMIT phoneme recognition benchmark, which to our knowledge is the best recorded score. Index Termsrecurrent neural networks, deep neural networks, speech recognition
doi:10.1109/icassp.2013.6638947 dblp:conf/icassp/GravesMH13 fatcat:5f2ghhhs55f2rdi6cvjgt3a5km