%0 Generic %1 sak2014shortterm %A Sak, Haşim %A Senior, Andrew %A Beaufays, Françoise %D 2014 %K LSTM network neural recurrent %T Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition %U http://arxiv.org/abs/1402.1128 %X Long Short-Term Memory (LSTM) is a recurrent neural network (RNN) architecture that has been designed to address the vanishing and exploding gradient problems of conventional RNNs. Unlike feedforward neural networks, RNNs have cyclic connections making them powerful for modeling sequences. They have been successfully used for sequence labeling and sequence prediction tasks, such as handwriting recognition, language modeling, phonetic labeling of acoustic frames. However, in contrast to the deep neural networks, the use of RNNs in speech recognition has been limited to phone recognition in small scale tasks. In this paper, we present novel LSTM based RNN architectures which make more effective use of model parameters to train acoustic models for large vocabulary speech recognition. We train and compare LSTM, RNN and DNN models at various numbers of parameters and configurations. We show that LSTM models converge quickly and give state of the art speech recognition performance for relatively small sized models.

@misc{sak2014shortterm, abstract = {Long Short-Term Memory (LSTM) is a recurrent neural network (RNN) architecture that has been designed to address the vanishing and exploding gradient problems of conventional RNNs. Unlike feedforward neural networks, RNNs have cyclic connections making them powerful for modeling sequences. They have been successfully used for sequence labeling and sequence prediction tasks, such as handwriting recognition, language modeling, phonetic labeling of acoustic frames. However, in contrast to the deep neural networks, the use of RNNs in speech recognition has been limited to phone recognition in small scale tasks. In this paper, we present novel LSTM based RNN architectures which make more effective use of model parameters to train acoustic models for large vocabulary speech recognition. We train and compare LSTM, RNN and DNN models at various numbers of parameters and configurations. We show that LSTM models converge quickly and give state of the art speech recognition performance for relatively small sized models.}, added-at = {2018-05-20T12:04:31.000+0200}, author = {Sak, Haşim and Senior, Andrew and Beaufays, Françoise}, biburl = {https://www.bibsonomy.org/bibtex/227f8a3a6550a7dbbd44393c951a99e15/qlience}, description = {Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition}, interhash = {35ab7ab81e5f2b02231490797dc62ed1}, intrahash = {27f8a3a6550a7dbbd44393c951a99e15}, keywords = {LSTM network neural recurrent}, month = {05}, note = {cite arxiv:1402.1128}, timestamp = {2018-05-20T12:04:31.000+0200}, title = {Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition}, url = {http://arxiv.org/abs/1402.1128}, year = 2014 }