Siri on-device deep learning-guided unit selection text-To-speech system

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

Volumn 2017-August, Issue , 2017, Pages 4011-4015

  Capes, Tim ^a   Coles, Paul ^a   Conkie, Alistair ^a   Golipour, Ladan ^a   Hadjitarkhani, Abie ^a   Hu, Qiong ^a   Huddleston, Nancy ^a   Hunt, Melvyn ^a   Li, Jiangchuan ^a   Neeracher, Matthias ^a   Prahallad, Kishore ^a   Raitio, Tuomo ^a   Rasipuram, Ramya ^a   Townsend, Greg ^a   Williamson, Becci ^a   Winarsky, David ^a   Wu, Zhizheng ^a   Zhang, Hepeng ^a  

^a APPLE INC   (United States)

Author keywords

Hybrid; Recurrent mixture density network, on device; Speech synthesis; Unit selection

Indexed keywords

DEEP LEARNING; MIXTURES; SPEECH; SPEECH SYNTHESIS;

DEVICE CAPABILITIES; HYBRID; LEARNING TECHNIQUES; MIXTURE DENSITY; TEXT-TO-SPEECH SYSTEM; UNIT SELECTION; UNIT-SELECTION SPEECH SYNTHESIS; VOICE BUILDING PROCESS;

SPEECH COMMUNICATION;

EID: 85039170210     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: 10.21437/Interspeech.2017-1798     Document Type: Conference Paper

References (17)

1. H. Zen, K. Tokuda, and A. W. Black, "Statistical parametric speech synthesis, " Speech Communication, vol. 51, no. 11, pp. 1039-1064, 2009.
2. A. J. Hunt and A. W. Black, "Unit selection in a concatenative speech synthesis system using a large speech database, " in IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 1, 1996, pp. 373-376.
3. S. P. Kishore and A. W. Black, "Unit size in unit selection speech synthesis." in Interspeech, 2003.
4. Z.-H. Ling, L. Qin, H. Lu, Y. Gao, L.-R. Dai, R.-H. Wang, Y. Jiang, Z.-W. Zhao, J.-H. Yang, J. Chen et al., "The USTC and iflytek speech synthesis systems for Blizzard Challenge 2007, " in Blizzard Challenge Workshop, 2007.
5. R. Fernandez, A. Rendel, B. Ramabhadran, and R. Hoory, "Using deep bidirectional recurrent neural networks for prosodictarget prediction in a unit-selection text-To-speech system." in Interspeech, 2015, pp. 1606-1610.
6. T. Merritt, R. A. Clark, Z. Wu, J. Yamagishi, and S. King, "Deep neural network-guided unit selection synthesis, " in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016, pp. 5145-5149.
7. L.-H. Chen, Y. Jiang, M. Zhou, Z.-H. Ling, and L.-R. Dai, "The USTC system for Blizzard Challenge 2016, " in Blizzard Challenge Workshop, 2016.
8. R. A. Clark, K. Richmond, and S. King, "Multisyn: Open-domain unit selection for the festival speech synthesis system, " Speech Communication, vol. 49, no. 4, pp. 317-330, 2007.
9. X. Gonzalvo, S. Tazari, C.-A. Chan, M. Becker, A. Gutkin, and H. Silen, "Recent advances in google real-Time HMM-driven unit selection synthesizer, " in Interspeech, 2016, pp. 2238-2242.
10. C. Bishop, "Mixture density networks, " Tech. Rep. NCRG/94/004, Neural Computing Research Group, Aston University, 1994.
11. H. Zen and A. Senior, "Deep mixture density networks for acoustic modeling in statistical parametric speech synthesis, " in IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2014, pp. 3872-3876.
12. J. Chung, C. Gulcehre, K. Cho, and Y. Bengio, "Empirical evaluation of gated recurrent neural networks on sequence modeling, " arXiv preprint arXiv:1412.3555, 2014.
13. Z. Wu and S. King, "Investigating gated recurrent networks for speech synthesis, " in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2016, pp. 5140-5144.
14. Z. Wu, C. Valentini-Botinhao, O. Watts, and S. King, "Deep neural networks employing multi-Task learning and stacked bottleneck features for speech synthesis, " in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2015, pp. 4460-4464.
15. N. Campbell, "Conversational speech synthesis and the need for some laughter, " IEEE Transactions on Audio, Speech, and Language Processing, vol. 14, no. 4, pp. 1171-1178, 2006.
16. H. Lu, W. Zhang, X. Shao, Q. Zhou, W. Lei, H. Zhou, and A. Breen, "Pruning redundant synthesis units based on static and delta unit appearance frequency, " in Interspeech, 2015.
17. A. Stan, J. Yamagishi, S. King, and M. Aylett, "The Romanian speech synthesis (RSS) corpus: Building a high quality HMMbased speech synthesis system using a high sampling rate, " Speech Communication, vol. 53, no. 3, pp. 442-450, 2011.