Grapheme-to-phoneme conversion using Long Short-Term Memory recurrent neural networks
Authors:
- 1 April 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 4225-4229
Abstract
Grapheme-to-phoneme (G2P) models are key components in speech recognition and text-to-speech systems as they describe how words are pronounced. We propose a G2P model based on a Long Short-Term Memory (LSTM) recurrent neural network (RNN). In contrast to traditional joint-sequence based G2P approaches, LSTMs have the flexibility of taking into consideration the full context of graphemes and transform the problem from a series of grapheme-to-phoneme conversions to a word-to-pronunciation conversion. Training joint-sequence based G2P require explicit grapheme-to-phoneme alignments which are not straightforward since graphemes and phonemes don't correspond one-to-one. The LSTM based approach forgoes the need for such explicit alignments. We experiment with unidirectional LSTM (ULSTM) with different kinds of output delays and deep bidirectional LSTM (DBLSTM) with a connectionist temporal classification (CTC) layer. The DBLSTM-CTC model achieves a word error rate (WER) of 25.8% on the public CMU dataset for US English. Combining the DBLSTM-CTC model with a joint n-gram model results in a WER of 21.3%, which is a 9% relative improvement compared to the previous best WER of 23.4% from a hybrid system.Keywords
This publication has 8 references indexed in Scilit:
- Speech recognition with deep recurrent neural networks2013
- Improving WFST-based G2p conversion with alignment constraints and RNNLM n-best rescoring2012
- Comparison of grapheme-to-phoneme methods on large pronunciation dictionaries and LVCSR tasks2012
- LSTM neural networks for language modeling2012
- Letter-to-Sound Pronunciation Prediction Using Conditional Random FieldsIEEE Signal Processing Letters, 2010
- Joint-sequence models for grapheme-to-phoneme conversionSpeech Communication, 2008
- Connectionist temporal classification2006
- Long Short-Term MemoryNeural Computation, 1997