Word embedding for recurrent neural network based TTS synthesis

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

Volumn 2015-August, Issue , 2015, Pages 4879-4883

  Wang, Peilu ^a,b   Qian, Yao ^b   Soong, Frank K ^b   He, Lei ^b   Zhao, Hai ^a  

^a SHANGHAI JIAO TONG UNIVERSITY   (China)

^b MICROSOFT RESEARCH ASIA   (China)

Author keywords

BLSTM; RNN; Speech synthesis; TTS; word embedding

Indexed keywords

RECURRENT NEURAL NETWORKS; SEMANTICS; SPEECH COMMUNICATION; SPEECH SYNTHESIS;

BLSTM; LOW DIMENSIONAL; RECURRENT NEURAL NETWORK (RNN); SEMANTIC INFORMATION; STATE OF THE ART; SUPRASEGMENTAL FEATURES; SYNTHESIZED SPEECH; WORD EMBEDDING;

AUDIO SIGNAL PROCESSING;

EID: 84946052755     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2015.7178898     Document Type: Conference Paper

References (24)

1. Heiga Zen, Andrew Senior, and Mike Schuster, Statis-tical parametric speech synthesis using deep neural net-works, in ICASSP, Vancouver, BC, Canada, May 2013, pp. 7962-7966
2. Yao Qian, Yuchen Fan, Wenping Hu, and Frank K. Soong, On the training aspects of deep neural network (DNN) for parametric TTS synthesis, in ICASSP, Flo-rence, Italy, May 2014, pp. 3829-3833
3. Alex Graves, Supervised sequence labelling with recur-rent neural networks, vol. 385, Springer, 2012
4. Sepp Hochreiter and Jürgen Schmidhuber, Long short-term memory, Neural computation, vol. 9, no. 8, pp. 1735-1780, 1997
5. Mike Schuster and Kuldip K. Paliwal, Bidirectional recurrent neural networks, Signal Processing, IEEE Transactions on, vol. 45, no. 11, pp. 2673-2681, 1997
6. Raul Fernandez, Asaf Rendel, Bhuvana Ramabhadran, and Ron Hoory, Prosody contour prediction with long short-term memory, bi-directional, deep recurrent neural networks, in INTERSPEECH, Singapore, September 2014
7. Yuchen Fan, Yao Qian, Fenglong Xie, and Frank K. Soong, TTS synthesis with bidirectional LSTM based recurrent neural networks, in INTERSPEECH, Singa-pore, September 2014
8. Yoshua Bengio, Réjean Ducharme, Pascal Vincent, and Christian Jauvin, Neural probabilistic language model-s, in Innovations in Machine Learning, pp. 1137-1155. Springer, 2003
9. Tomas Mikolov, Martin Karafiát, Lukas Burget, Jan Honza, and Sanjeev Khudanpur, Re-current neural network based language model, in INTERSPEECH, Makuhari, Chiba, Japan, September 2010, pp. 1045-1048
10. Andriy Mnih and Geoffrey Hinton, Three new graph-ical models for statistical language modelling, in Pro-ceedings of the 24th international conference on Ma-chine learning, Corvallis, Oregon, USA, June 2007, pp. 641-648
11. Joseph Turian, Lev Ratinov, and Yoshua Bengio, Word representations: A simple and general method for semi-supervised learning, in ACL, Uppsala, Sweden, July 2010, pp. 384-394
12. Ronan Collobert, Jason Weston, Léon Bottou, Michael Karlen, Koray Kavukcuoglu, and Pavel Kuksa, Natural language processing (almost) from scratch, The Jour-nal of Machine Learning Research, vol. 12, pp. 2493-2537, 2011
13. Eric H. Huang, Richard Socher, Christopher D. Man-ning, and Andrew Y. Ng, Improving word representa-tions via global context and multiple word prototypes, in ACL, Jeju Island, Korea, July 2012, pp. 873-882
14. Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean, Efficient estimation of word representations in vector space, CoRR, January 2013
15. O. Watts, S. Gangireddy, J. Yamagishi, S. King, S. Re-nals, A. Stan, and M. Giurgiu, Neural net word repre-sentations for phrase-break prediction without a part of speech tagger, in ICASSP, Florence, Italy, May 2014, pp. 2599-2603
16. Heng Lu, Simon King, and Oliver Watts, Combining a vector space representation of linguistic context with a deep neural network for text-to-speech synthesis, in 8th ISCA Speech Synthesis Workshop, Barcelona Spain, August 2013, pp. 281-285
17. OliverWatts, Unsupervised learning for text-to-speech synthesis, Ph.d. dissertation, 2013
18. Keiichi Tokuda, Takayoshi Yoshimura, Takashi Ma-suko, Takao Kobayashi, and Tadashi Kitamura, Speech parameter generation algorithms for HMM-based speech synthesis, in ICASSP, Istanbul, Turkey, June 2000, vol. 3, pp. 1315-1318
19. Weninger Felix and Geiger Jrgen, Current, http: //sourceforge.net/projects/currennt
20. Tomas Mikolov, Rnnlm, http://rnnlm.org
21. Joseph Turian, Lev Ratinov, and Yoshua Bengio, Word representations for NLP, http://metaoptimize. com/projects/wordreprs
22. Ronan Colloberte, Senna, http://ml. nec-labs.com/senna
23. Tomas Mikolov, word2vec, https:// code.google.com/p/word2vec
24. Turk, https://www.mturk.com