An autoregressive recurrent mixture density network for parametric speech synthesis

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

Volumn , Issue , 2017, Pages 4895-4899

  Wang, Xin ^a,b   Takaki, Shinji ^a   Yamagishi, Junichi ^a,b,c  

^a NATIONAL INSTITUTE OF INFORMATICS   (Japan)

^b GRADUATE UNIVERSITY FOR ADVANCED STUDIES   (Japan)

^c UNIVERSITY OF EDINBURGH   (United Kingdom)

Author keywords

Autoregressive model; Mixture density network; Recurrent neural network; Speech synthesis

Indexed keywords

EID: 85023745327     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2017.7953087     Document Type: Conference Paper

References (27)

1. Keiichi Tokuda, Yoshihiko Nankaku, Tomoki Toda, Heiga Zen, Junichi Yamagishi, and Keiichiro Oura, "Speech synthesis based on hidden Markov models," Proceedings of the IEEE, vol. 101, no. 5, pp. 1234-1252, 2013.
2. Heiga Zen, Alan Senior, and Martin Schuster, "Statistical parametric speech synthesis using deep neural networks," in Proc. ICASSP, 2013, pp. 7962-7966.
3. Yuchen Fan, Yap Qian, Feilong Xie, and Frank K. Soong, "TTS synthesis with bidirectional LSTM based recurrent neural networks," in Proc. INTERSPEECH, 2014, pp. 1964-1968.
4. Zhen-Hua Ling, Li Deng, and Dong Yu, "Modeling spectral envelopes using restricted Boltzmann machines and deep belief networks for statistical parametric speech synthesis," IEEE Transactions on Audio, Speech, and Language Processing, vol. 21, no. 10, pp. 2129-2139, 2013.
5. Shinji Takaki and Junichi Yamagishi, "A deep auto-encoder based low-dimensional feature extraction from FFT spectral envelopes for statistical parametric speech synthesis," in Proc. ICASSP, 2016, pp. 5535-5539.
6. Christopher M. Bishop, "Mixture Density Networks," Tech. Rep., Aston University, 2004, http://eprints.aston.ac.uk/373/.
7. Sophocles J. Orfanidis, Optimum Signal Processing: An Introduction, Macmillan publishing company, 1988.
8. Matt Shannon, Heiga Zen, and William Byrne, "Autoregressive models for statistical parametric speech synthesis," IEEE Transactions on Audio, Speech, and Language Processing, vol. 21, no. 3, pp. 587-597, 2013.
9. Carl Quillen, "Autoregressive HMM speech synthesis," in Proc. ICASSP, 2012, pp. 4021-4024.
10. Tomoki Toda and Keiichi Tokuda, "A speech parameter generation algorithm considering global variance for HMM-based speech synthesis," IEICE Transactions on Information and Systems, vol. 90, no. 5, pp. 816-824, 2007.
11. Alex Graves, Supervised Sequence Labelling with Recurrent Neural Networks, Ph.D. thesis, Technische Universität München, 2008.
12. Heiga Zen and Andrew Senior, "Deep mixture density networks for acoustic modeling in statistical parametric speech synthesis," in Proc. ICASSP, 2014, pp. 3844-3848.
13. Mike Schuster, "Better generative models for sequential data problems: Bidirectional recurrent mixture density networks," in Proc. NIPS, 1999, pp. 589-595.
14. Heiga Zen, Keiichi Tokuda, and Tadashi Kitamura, "Reformulating the HMM as a trajectory model by imposing explicit relationships between static and dynamic feature vector sequences," Computer Speech & Language, vol. 21, no. 1, pp. 153-173, 2007.
15. Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Trajectory training considering global variance for speech synthesis based on neural networks," in Proc. ICASSP, 2016, pp. 5600-5604.
16. Matt Shannon and William Byrne, "A formulation of the autoregressive HMM for speech synthesis," Tech. Rep., University of Cambridge, CUED/F-INFENG/TR.629, 2009.
17. Heiga Zen and Haşim Sak, "Unidirectional long short-term memory recurrent neural network with recurrent output layer for low-latency speech synthesis," in Proc. ICASSP, 2015, pp. 4470-4474.
18. Simon King and Vasilis Karaiskos, "The Blizzard Challenge 2011," in Proc. Blizzard Challenge 2011, 2011, pp. 1-10.
19. Hideki Kawahara, Ikuyo Masuda-Katsuse, and Alain de Cheveigne, "Restructuring speech representations using a pitch-adaptive time-frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in sounds," Speech Communication, vol. 27, pp. 187-207, 1999.
20. HTS Working Group, "The English TTS system Flite+HTS engine," 2014.
21. Felix Weninger, Johannes Bergmann, and Björn Schuller, "Introducing CURRENT: The Munich open-source CUDA recurrent neural network toolkit," The Journal of Machine Learning Research, vol. 16, no. 1, pp. 547-551, 2015.
22. John D. Markel, "Digital inverse filtering: A new tool for formant trajectory estimation," IEEE Transactions on Audio and Electroacoustics, vol. 20, no. 2, pp. 129-137, Jun 1972.
23. Mary E. Beckman and Gayle Ayers, "Guidelines for ToBI labelling," The OSU Research Foundation, vol. 3, 1997.
24. "Method for the subjective assessment of intermediate quality level of coding systems," in ITU-R BS.1534-1, International Telecommunication Union Radiocommunication Assembly, 2003, http://www.itu.int/rec/R-REC-BS.1534.
25. Gustav E. Henter, Srikanth Ronanki, Oliver Watts, Mirjam Wester, Zhizheng Wu, and Simon King, "Robust TTS duration modelling using DNNs," in Proc. ICASSP, 2016, pp. 5130-5134.
26. Heiga Zen, Yannis Agiomyrgiannakis, Niels Egberts, Fergus Henderson, and Przemyslaw Szczepaniak, "Fast, compact, and high quality LSTM-RNN based statistical parametric speech synthesizers for mobile devices," in Proc. INTERSPEECH, 2016, pp. 2273-2277.
27. Shinnosuke Takamichi, Tomoki Toda, Graham Neubig, Sakriani Sakti, and Satoshi Nakamura, "A postfilter to modify the modulation spectrum in HMM-based speech synthesis," in Proc. ICASSP, 2014, pp. 290-294.