Reducing mismatch in training of DNN-based glottal excitation models in a statistical parametric text-to-speech system

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

Volumn 2017-August, Issue , 2017, Pages 1368-1372

  Juvela, Lauri ^a   Bollepalli, Bajibabu ^a   Yamagishi, Junichi ^b,c   Alku, Paavo ^a  

^a AALTO UNIVERSITY   (Finland)

^b NATIONAL INSTITUTE OF INFORMATICS   (Japan)

^c UNIVERSITY OF EDINBURGH   (United Kingdom)

Author keywords

Excitation modeling; Statistical parametric speech synthesis

Indexed keywords

DEEP NEURAL NETWORKS; ERRORS; INVERSE PROBLEMS; SPEECH; SPEECH SYNTHESIS;

EXCITATION MODELING; EXCITATION MODELS; IMPROVE PERFORMANCE; INVERSE FILTERING; PERFECT RECONSTRUCTION; STATISTICAL PARAMETRIC SPEECH SYNTHESIS; SUBJECTIVE QUALITY; TEXT-TO-SPEECH SYSTEM;

SPEECH COMMUNICATION;

EID: 85039167642     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: 10.21437/Interspeech.2017-848     Document Type: Conference Paper

References (33)

1. H. Zen, K. Tokuda, and A. W. Black, "Statistical parametric speech synthesis, " Speech Communication, vol. 51, no. 11, pp. 1039-1064, 2009.
2. K. Tokuda, Y. Nankaku, T. Toda, H. Zen, J. Yamagishi, and K. Oura, "Speech synthesis based on hidden Markov models, " Proceedings of the IEEE, vol. 101, no. 5, pp. 1234-1252, May 2013.
3. H. Zen, A. Senior, and M. Schuster, "Statistical parametric speech synthesis using deep neural networks, " in Proc. of ICASSP, May 2013, pp. 7962-7966.
4. Z.-H. Ling, S.-Y. Kang, H. Zen, A. Senior, M. Schuster, X.-J. Qian, H. Meng, and L. Deng, "Deep learning for acoustic modeling in parametric speech generation: A systematic review of existing techniques and future trends, " Signal Processing Magazine, IEEE, vol. 32, no. 3, pp. 35-52, May 2015.
5. Y. Fan, Y. Qian, F.-L. Xie, and F. K. Soong, "TTS synthesis with bidirectional LSTM based recurrent neural networks." in Interspeech, 2014, pp. 1964-1968.
6. H. Zen and H. Sak, "Unidirectional long short-term memory recurrent neural network with recurrent output layer for low-latency speech synthesis, " in Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on. IEEE, 2015, pp. 4470-4474.
7. H. Kawahara, J. Estill, and O. Fujimura, "Aperiodicity extraction and control using mixed mode excitation and group delay manipulation for a high quality speech analysis, modification and synthesis system straight, " in MAVEBA, 2001.
8. X. Wang, S. Takaki, and J. Yamagishi, "An autoregressive recurrent mixture density network for parametric speech synthesis, " in Proc. of ICASSP. IEEE, 2017, pp. 4895-4899.
9. T. Kaneko, H. Kameoka, N. Hojo, Y. Ijima, K. Hiramatsu, and K. Kashino, "Generative adversarial network-based postfilter for statistical parametric speech synthesis, " in Proc. of ICASSP, March 2017, pp. 4910-4914.
10. K. Tokuda and H. Zen, "Directly modeling speech waveforms by neural networks for statistical parametric speech synthesis, " in Proc. of ICASSP, April 2015, pp. 4215-4219.
11. -, "Directly modeling voiced and unvoiced components in speech waveforms by neural networks, " in Proc. of ICASSP, March 2016, pp. 5640-5644.
12. S. Takaki and J. Yamagishi, "A deep auto-encoder based lowdimensional feature extraction from FFT spectral envelopes for statistical parametric speech synthesis, " in Proc. of ICASSP, March 2016, pp. 5535-5539.
13. S. Takaki, H. Kameoka, and J. Yamagishi, "Direct modeling of frequency spectra and waveform generation based on phase recovery for DNN-based speech synthesis, " in Interspeech (submitted), 2017.
14. A. van den Oord, S. Dieleman, H. Zen, K. Simonyan, O. Vinyals, A. Graves, N. Kalchbrenner, A. Senior, and K. Kavukcuoglu, "WaveNet: A generative model for raw audio, " Pre-print, 2016, https://arxiv.org/pdf/1609.03499.pdf.
15. S. Mehri, K. Kumar, I. Gulrajani, R. Kumar, S. Jain, J. Sotelo, A. C. Courville, and Y. Bengio, "SampleRNN: An unconditional end-to-end neural audio generation model, " in ICLR 2017 (submission), 2017. [Online]. Available: http://arxiv.org/abs/1612.07837
16. J. Sotelo, S. Mehri, K. Kumar, J. F. Santos, K. Kastner, A. Courville, and Y. Bengio, "Char2Waw: End-to-end speech synthesis, " in ICLR 2017 workshop (submission), 2017, https://openreview.net/pdf?id=B1VWyySKx.
17. S. O. Arik, M. Chrzanowski, A. Coates, G. Diamos, A. Gibiansky, Y. Kang, X. Li, J. Miller, A. Ng, J. Raiman, S. Sengupta, and M. Shoeybi, "Deep voice: Real-time neural text-to-speech, " in ICML 2017 (submission), 2017, https://arxiv.org/pdf/1702.07825.pdf.
18. L. Juvela, B. Bollepalli, M. Airaksinen, and P. Alku, "Highpitched excitation generation for glottal vocoding in statistical parametric speech synthesis using a deep neural network, " in "Proc. of ICASSP", Mar. 2016, pp. 5120-5124.
19. M. Airaksinen, B. Bollepalli, L. Juvela, Z. Wu, S. King, and P. Alku, "GlottDNN-a full-band glottal vocoder for statistical parametric speech synthesis, " in Proc. of Interspeech, 2016.
20. L. Juvela, X. Wang, S. Takaki, M. Airaksinen, J. Yamagishi, and P. Alku, "Using text and acoustic features in predicting glottal excitation waveforms for parametric speech synthesis with recurrent neural networks, " in "Proc. of Interspeech", Sep. 2016, pp. 2283-2287.
21. A.W. Black and K. A. Lenzo, "Flite: a small fast run-time synthesis engine, " in 4th ISCA Tutorial and Research Workshop (ITRW) on Speech Synthesis, 2001.
22. K. Richmond, R. A. Clark, and S. Fitt, "Robust LTS rules with the Combilex speech technology lexicon, " in Proc. of Interspeech, Brighton, September 2009, pp. 1295-1298.
23. H. Zen, T. Nose, J. Yamagishi, S. Sako, T. Masuko, A. W. Black, and K. Tokuda, "The HMM-based speech synthesis system version 2.0, " in Proc. of ISCA SSW6, Bonn, Germany, August 2007, pp. 294-299.
24. M. Airaksinen, T. Raitio, B. Story, and P. Alku, "Quasi closed phase glottal inverse filtering analysis with weighted linear prediction, " Audio, Speech, and Language Processing, IEEE/ACM Transactions on, vol. 22, no. 3, pp. 596-607, March 2014.
25. D. Talkin, "A robust algorithm for pitch tracking (RAPT), " Speech coding and synthesis, vol. 495, p. 518, 1995.
26. -, "REAPER: Robust Epoch And Pitch EstimatoR, " https://github.com/google/REAPER, 2015.
27. T. Raitio, A. Suni, J. Yamagishi, H. Pulakka, J. Nurminen, M. Vainio, and P. Alku, "HMM-based speech synthesis utilizing glottal inverse filtering, " IEEE Transactions on Audio, Speech, and Language Processing, vol. 19, no. 1, pp. 153-165, January 2011.
28. T. Raitio, A. Suni, H. Pulakka, M. Vainio, and P. Alku, "Comparison of formant enhancement methods for HMM-based speech synthesis." in SSW, 2010, pp. 334-339.
29. E. Moulines and J. Laroche, "Non-parametric techniques for pitch-scale and time-scale modification of speech, " Speech communication, vol. 16, no. 2, pp. 175-205, 1995.
30. "ETSI TS 126 090: Mandatory Speech Codec speech processing functions; Adaptive Multi-Rate (AMR) speech codec; Transcoding functions" , " European Telecommunications Standards Institute, Technical specification, 2016.
31. F. Weninger, "Introducing CURRENNT: The Munich opensource CUDA recurrent neural network toolkit, " Journal of Machine Learning Research, vol. 16, pp. 547-551, 2015.
32. CrowdFlower Inc. (2017) Crowd-sourcing platform. [Online]. Available: https://www.crowdflower.com/
33. (2017) EF English proficiency index. [Online]. Available: http://www.ef.com/epi/