Speech recognition with deep recurrent neural networks

Citations Over TimeTop 1% of 2013 papers

Abstract

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 far 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.

Related Papers

• → A Variable Initialization Approach to the EM Algorithm for Better Estimation of the Parameters of Hidden Markov Model Based Acoustic Modeling of Speech Signals(2006)9 cited
• → Global optimization of a neural network-hidden Markov model hybrid(2002)18 cited
• → Towards Constructing HMM Structure for Speech Recognition With Deep Neural Fenonic Baseform Growing(2021)3 cited
• → Hidden neural networks: a framework for HMM/NN hybrids(2002)25 cited
• → On the phonetic structure of a large hidden Markov model(1991)8 cited