Grapheme-to-phoneme conversion using Long Short-Term Memory recurrent neural networks

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 2015-August, Issue , 2015, Pages 4225-4229

  Rao, Kanishka ^a   Peng, Fuchun ^a   Sak, Hasim ^a   Beaufays, Francoise ^a  

^a GOOGLE INC   (United States)

Author keywords

CTC; G2P; LSTM; pronunciation; RNN; speech recognition

Indexed keywords

AUDIO SIGNAL PROCESSING; BRAIN; CHARACTER RECOGNITION; HYBRID SYSTEMS; SPEECH; SPEECH COMMUNICATION; SPEECH RECOGNITION;

GRAPHEME TO PHONEMES; GRAPHEME-TO-PHONEME CONVERSION; LSTM; PRONUNCIATION; RECURRENT NEURAL NETWORK (RNN); TEMPORAL CLASSIFICATION; TEXT-TO-SPEECH SYSTEM; TRADITIONAL JOINTS;

LONG SHORT-TERM MEMORY;

EID: 84946032010     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2015.7178767     Document Type: Conference Paper

References (18)

1. A. Rutherford, F. P eng, and F. Beaufays, "P ronunciation learning for named-entities through crowd-sourcing, " in Proceedings of InterSpeech, 2014
2. M. Bisani and H. Ney, "joint-sequence models for grapheme-to-phoneme conversion, " Speech Communications, vol. 50, no. 5, pp. 434-451, 2008
3. S. Hochreiter and]. Schmidhuber, "Long short-term memory," Neural Computation, vol. 9(8), pp. 17351780, 1997
4. L. Galescu and]. F. Allen, "Pronunciation of proper names with a joint n-gram model for bi-directional grapheme-to-phoneme conversion, " in Proceedings of InterSpeech,2002
5. J. R. Novak et aI., "Improving wfst-based g2p conversion with alignment constraints and rnnlm n-best rescoring, " in Proceedings of InterSpeech, 2012
6. J. R. Novak, N. Minematu, and K. Hirose, "Failure transitions for joint n-gram models and g2p conversion, " in Proceedings of InterSpeech, 2013
7. S. F. Chen, "Conditional and joint models for graphemeto-phoneme conversion, " in Proceedings ofInterSpeech, 2003
8. D. Wang and S. King, "Letter-to-sound pronunciation prediction using conditional random fields, " IEEE Signal Processing Letters, vol. 18 (2), pp. 122-125, 20 1 1
9. P. Lehnen, A. Allauzen, T. Lavergne, F. Yvon, S. Hahn, and H. Ney, "Structure learning in hidden conditional random fields for grapheme-to-phoneme conversion, " in Proceedings of InterSpeech, 2013
10. S. Jiampojamarn, C. Cherry, and G. Kondrak, "Joint processing and discriminative training for letter-tophoneme conversion, " in Proceedings of ACL, 2008, pp. 905-9 13
11. E. B. Bilcu, Text-to-Phoneme Mapping Using Neural Networks, Ph.D. thesis, Tampere University of Technology, 2008
12. K. Wu et aI., "Encoding linear models as weighted finite-state transducers, " in Proceedings of InterSpeech, 2014
13. S. Hahn, P. Vozila, and M. Bisani, "Comparison of grapheme-to-phoneme methods on large pronunciation dictionaries and lvcsr tasks, " in Proceedings of InterSpeech, 2012
14. A. Graves, A. Mohamed, and G. Hinton, "Speech recognition with deep recurrent neural networks, " in Proceedings of ICASSP, 2013, pp. 6645-6649
15. H. Sak, A. Senior, and F. Beau fays, "Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition, " in Proceedings of InterSpeech, 2014
16. A. Graves and]. Schmidhuber, "Offline handwriting recognition with multidimensional recurrent neural networks, " in Proceedings of NIPS, 2008, pp. 545-552
17. M. Sundermeyer, R. Schluter, and H. Ney, "Lstm neural networks for language modeling, " in Proceedings of InterSpeech, 2012, pp. 194-197
18. A. Graves, S. Fernandez, F. Gomez, and]. Schmidhuber, "Connectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks, " in Proceedings of ICML, 2006