Sequence generation error (SGE) minimization based deep neural networks training for text-to-speech synthesis

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn 2015-January, Issue , 2015, Pages 864-868

  Fan, Yuchen ^a   Qian, Yao ^a   Soong, Frank K ^a   He, Lei ^a  

^a MICROSOFT RESEARCH ASIA   (China)

Author keywords

Deep neural networks(DNNs); Sequence generation error (SGE) minimization training; Speech synthesis

Indexed keywords

DECISION TREES; ERRORS; SPEECH; SPEECH RECOGNITION; SPEECH SYNTHESIS;

BASE-LINE PERFORMANCE; CONTEXTUAL INFORMATION; DEEP NEURAL NETWORKS; MINIMIZATION CRITERIONS; MULTI-LAYERED STRUCTURE; SEQUENCE GENERATION; STATISTICAL CORRELATION; SUBJECTIVE LISTENING TEST;

SPEECH COMMUNICATION;

EID: 84959172579     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (18)

1. H. Zen, K. Tokuda, and W. Black, Alan, "Statistical parametricspeech synthesis", Speech Communication, Volume 51, Issue 11, pp. 1039-1064, 2009.
2. G. Hinton, L. Deng, D. Yu, G. Dahl, A. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. Sainath, and B. Kingsbury, "Deep neural networks for acoustic modeling in speechrecognition: The shared views of four research groups, " SignalProcessing Magazine, IEEE, vol. 29, no. 6, pp. 82-97, 2012.
3. G. E. Dahl, D. Yu, L. Deng, and A. Acero, "Context-dependentpre-trained deep neural networks for large-vocabulary speechrecognition, " IEEE Trans. on Audio, Speech, and LanguageProcessing, vol. 20, no. 1, pp. 30-42, 2012.
4. F. Seide, G. Li, and D. Yu, "Conversational speechtranscription using context-dependent deep neural networks, " inProc. InterSpeech, pp. 437-440, 2011
5. H. Zen, A. Senior and M. Senior, "Statistical Parametric SpeechSynthesis Using Deep Neural Networks", in Proc. ICASSP, pp. 8012-8016, 2013.
6. Y. Qian, Y.-C. Fan, W.-P. Hu and F. K. Soong, "On the trainingaspects of deep neural network (DNN) for parametric TTSsynthesis", in Proc. ICASSP, pp. 3829-3833, 2014.
7. H. Lu, S. King, and O. Watts, "Combining a vector spacerepresentation of linguistic context with a deep neural networkfor text-to-speech synthesis", in 8th ISCA Workshop on SpeechSynthesis, pp. 281-285, 2013.
8. S. Kang, X. Qian, and H. Meng, "Multi-distribution deep beliefnetwork for speech synthesis", in Proc. ICASSP, pp. 7962-7966, 2013.
9. Z.-H. Ling, L. Deng, and D. Yu, "Modeling spectral envelopesusing restricted Boltzmann machines for statistical parametricspeech synthesis", in Proc. ICASSP, pp. 7825-7829, 2013.
10. K. Tokuda, T. Kobayashi, T. Masuko, T. Kobayashi, and T. Kitamura, "Speech parameter generation algorithms for HMMbasedspeech synthesis", in Proc. ICASSP, pp. 1315-1318, 2000.
11. Y.-J. Wu and R.-H. Wang, "Minimum generation error trainingfor HMM-based speech synthesis", in Proc. ICASSP, pp. I, I, 2006.
12. A.-R. Mohamed, D. Yu and L. Deng, "Investigation of Full-Sequence Training of Deep Belief Networks for SpeechRecognition", in Proc. Interspeech, pp. 2846-2849, 2010.
13. H. Su, G. Li, D. Yu, and F. Seide, "Error back propagation forsequence training of context-dependent deep networks forconversational speech transcription", in Proc. ICASSP, pp. 6664-6668, 2013
14. D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learningrepresentations by back-propagating errors, " Nature, vol. 323, no. 9, pp. 533-536, 1986.
15. C. Julian Chen, Ramesh A. Gopinath, Michael D. Monkowski, Michael A. Picheny, and Katherine Shen, "New methods incontinuous Mand arin speech recognition., " in Proc. EUROSPEECH, pp. 1543-1546, 1997.
16. Z.-H. Ling, Y.-J. Wu, Y.-P. Wang, L. Qin, and R.-H. Wang, "USTC System for Blizzard Challenge 2006 an ImprovedHMM-based Speech Synthesis Method, " in Proc. BlizzardChallenge 2006 Workshop, 2006.
17. Amazon Mechanical Turk, Avaliable: https: //www. mturk. com/mturk/welcome
18. F.-L. Xie, Y. Qian, Y.-C. Fan, F. K. Soong, "Sequence Error(SE) Minimization Training of Neural Network for VoiceConversion", in Proc. Interspeech, 2014.