A unified trajectory tiling approach to high quality speech rendering

IEEE Transactions on Audio, Speech and Language Processing

Volumn 21, Issue 2, 2013, Pages 280-290

  Qian, Yao ^a   Soong, Frank K ^a   Yan, Zhi Jie ^a  

^a MICROSOFT RESEARCH ASIA   (China)

Author keywords

Cross lingual; speech synthesis; trajectory tiling; voice transformation

Indexed keywords

CROSS-LINGUAL; HIGH QUALITY; SPEECH DATABASE; SUBJECTIVE EVALUATIONS; SYNTHESIZED SPEECH; UNIFIED ALGORITHM; WAVE FORMS;

SPEECH SYNTHESIS;

TRAJECTORIES;

EID: 84871382567     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2012.2221460     Document Type: Article

References (45)

1. EMIME [Online]. Available: http://www. emime. org
2. Z.-H. Ling and R.-H. Wang, "HMM-based hierarchical unit selection combining Kullback-Leibler divergence with likelihood criterion, " in Proc. ICASSP., 2007, pp. 1245-1248.
3. Z.-J. Yan, Y. Qian, and F. K. Soong, "Rich-context unit selection (RUS) approach to high quality TTS, " in Proc. ICASSP, 2010, pp. 4798-4801.
4. Y. Qian, Z.-J. Yan, Y.-J. Wu, F. K. Soong, G.-L. Zhang, andL.-J. Wang, "An HMM trajectory tiling (HTT) approach to high quality TTS-Microsoft entry to Blizzard challenge 2010, " in Proc. Blizzard Challenge Workshop, 2010.
5. T. Hirai and S. Tenpaku, "Using 5ms segments in concatenative speech synthesis, " in Proc. 5th Speech Synth. Workshop, 2004.
6. T. Hirai, J. Yamagishi, and S. Tenpaku, "Utilization of an HMM-based feature generation module in 5 ms segment concatenative speech synthesis, " in Proc. ISCA SSW6, 2007.
7. H. Zen, K. Tokuda, and A. W. Black, "Statistical parametric speech synthesis, " Speech Commun., vol. 51, no. 11, pp. 1039-1064, 2009.
8. X. Gonzalvo, A. Gutkin, J. C. Socoró, I. Iriondo, and P. Taylor, "Local minimum generation error criterion for hybrid HMM speech synthesis, " in Proc. Interspeech, 2009, pp. 416-419.
9. Z.-J. Yan, Y. Qian, and F. K. Soong, "Rich context modeling for high quality HMM-Based TTS, " in Proc. Interspeech, 2009.
10. A. W. Black, H. Zen, and K. Tokuda, "Statistical parametric speech synthesis, " in Proc. ICASSP, 2007, pp. 1229-1232.
11. T. Toda and K. Tokuda, "Speech parameter generation algorithm considering global variance for HMM-based speech synthesis, " in Proc. Interspeech, 2005.
12. J. Yamagishi, T. Kobayashi, Y. Nakano, K. Ogata, and J. Isogai, "Analysis of speaker adaptation algorithms for HMM-based speech synthesis and a constrained SMAPLR adaptation algorithm, " IEEE Trans. Audio, Speech, Lang. Process., vol. 17, no. 1, pp. 66-83, Jan. 2009.
13. Y. Qian, H. Liang, and F. K. Soong, "A cross-language state sharing and mapping approach to bilingual (Mandarin-English) TTS, " IEEE Trans. Audio, Speech, Lang. Process., vol. 17, no. 6, pp. 1231-1239, Aug. 2009.
14. Y.-J. Wu, Y. Nankaku, and K. Tokuda, "State mapping based method for cross-lingual speaker adaptation in HMM-based speech synthesis, " in Proc. Interspeech, 2009, pp. 528-531.
15. K. Oura, J. Yamagishi, M. Wester, S. King, and K. Tokuda, "Analysis of unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis usingKLD-based transform mapping, " Speech Commun. vol. 54, no. 6, pp. 704-714, Jul. 2012.
16. Y.-N. Chen, Y. Jiao, Y. Qian, and F. K. Soong, "State mapping for cross-language speaker adaptation in TTS, " in Proc. ICASSP, 2009, pp. 4273-4276.
17. M. Gibson, T. Hirsimaki, R. Karhila, M. Kurimo, andW. Byrne, "Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction, " in Proc. ICASSP, 2010, pp. 4642-4645.
18. H. Liang and J. Dines, "Phonological knowledge guided HMM state mapping for cross-Lingual speaker adaptation, " in Proc. Interspeech, 2011, pp. 1825-1828.
19. Y. Qian, J. Xu, and F. K. Soong, "A frame mapping based HMM approach to cross-lingual voice transformation, " in Proc. ICASSP, 2011, pp. 5120-5123.
20. F. Itakura, "Line spectrum representation of linear predictive coefficients of speech signals, " J. Acoust. Soc. Amer., vol. 57, p. S35, 1975.
21. F. K. Soong and B. H. Juang, "Line spectrum pair (LSP) and speech data compression, " in Proc. ICASSP, 1984, pp. 37-40.
22. H. Wakita, "Linear prediction voice synthesizers: Line spectrum pairs (LSP) is the newest of the several techniques, " Speech Technol., vol. 1, pp. 17-22, 1981.
23. K. K. Paliwal, "On the use of line spectral frequency parameters for speech recognition, " Digital Signal Process., vol. 2, pp. 80-87, 1992.
24. H. Kawahara, I. Masuda-Katsuse, andA. deCheveigne, "Restructuring speech representations using pitch-adaptive time-frequency smoothing and instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in sounds, " Speech Commun., vol. 27, pp. 187-207, 1999.
25. A. D. Talkin, Speech Coding and Synthesis, Chapter A, Robust Algorithm for Pitch Tracking (RAPT). Amsterdam, The Netherlands: Elservier, 1995.
26. T. Yoshimura, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura, "Simultaneous modeling of spectrum, pitch and duration in HMMbased speech synthesis, " in Proc. Eurospeech, 1999.
27. Y.-J. Wu and R. H. Wang, "Minimum generation error training for HMM-based speech synthesis, " in Proc. ICASSP, 2006, pp. 89-92.
28. Y. Qian, F. K. Soong, M.-M. Wang, and Z.-Z. Wu, "A minimum v/u error approach to F0 generation in HMM-based TTS, " in Proc. Interspeech, 2009.
29. L. Saheer, P. N. Garner, J. Dines, and H. Liang, "VTLN adaptation for statistical speech synthesis, " in Proc. ICASSP, 2010, pp. 4838-4841.
30. X. Zhuang, Y. Qian, F. K. Soong, Y.-J. Wu, and B. Zhang, "Formantbased frequency warping for improving speaker adaptation in HMM TTS, " in Proc. Interspeech, 2010, pp. 817-820.
31. R. Laroia, N. Phamdo, and N. Farvardin, "Robust and efficient quantization of speech LSP parameters using structured vector quantizers, " in Proc. ICASSP, 1991, pp. 641-644.
32. M. S. Lee, H. K. Kim, and H. S. Lee, "A new distortion measure for spectral quantization based on the LSP intermodal interlacing property, " Speech Commun., vol. 35, pp. 191-201, 2001.
33. Y. Qian, F. K. Soong, Y. N. Chen, and M. Chu, "An HMM-based Mandarin Chinese text-to-speech system, " in Proc. ISCSLP, 2006, Springer LNAI Vol. 4274, pp. 223-232. .
34. G. Fant, Acoustic Theory of Speech Production. The Hague, Netherlands: Mouton, 1960.
35. L. R. Rabiner and R. W. Schafer, Digital Processing of Speech Signals. Englewood Cliffs, NJ: Prentice-Hall, 1978.
36. Z.-H. Ling, Y.-J. Wu, Y.-P. Wang, L. Qin, and R.-H. Wang, "USTC system for Blizzard Challenge 2006 an improved HMM-based speech synthesis method, " in Proc. Blizzard Challenge Workshop, 2006.
37. Y. Stylianou and A. K. Syrdal, "Perceptual and objective detection of discontinuities in concatenative speech synthesis, " in Proc. ICASSP, 2001, pp. 837-840. (Pubitemid 32839049)
38. A. D. Conkie and S. Isard, "Optimal coupling of diphones, " in Proc. Eurospeech, 1995.
39. Demos of Synthesized Sentences, HTT-Based TTS, [Online]. Available: http://research. microsoft. com/en-us/projects/htt/default. aspx
40. Nancy Voice Provided by Lessac Technologies for the Blizzard Challenge 2011, [Online]. Available: http://www. synsig. org/index. php/Blizzard- Challenge-2011
41. K. Shinoda and T. Watanable, "MDL-based context-dependent subword modeling for speech recognition, " J. Acoust. Soc. Jpn(E), vol. 21, no. 2, pp. 79-86, 2000. (Pubitemid 30594111)
42. [Online]. Available: http://www. synsig. org/index. php/Blizzard- Challenge-2010
43. P. Zhan and A. Waibel, Vocal Tract Length Normalization for Large Vocabulary Continuous Speech Recognition. Pittsburgh, PA: Carnegie Mellon Univ., 1997, CMU-CS-97-148.
44. P. Liu and F. K. Soong, "Kullback-Leibler divergence between two hidden Markov models, " Microsoft Research Asia, 2005, Tech. Rep. .
45. Cross-Lingual Voice Transformation [Online]. Available: http://research. microsoft. com/en-us/projects/mixedlangtts/default. aspx