Synthesis of F0 contours using generation process model parameters predicted from unlabeled corpora: Application to emotional speech synthesis

Speech Communication

Volumn 46, Issue 3-4, 2005, Pages 385-404

  Hirose, Keikichi ^a   Sato, Kentaro ^a,b   Asano, Yasufumi ^a   Minematsu, Nobuaki ^a  

^a UNIVERSITY OF TOKYO   (Japan)

^b NEC CORPORATION   (Japan)

Author keywords

Automatic extraction of model commands; Corpus based generation; Emotional speech synthesis; F0 model; HMM based speech synthesis

Indexed keywords

BINARY CODES; DECISION THEORY; ERROR DETECTION; MATHEMATICAL MODELS; NATURAL FREQUENCIES; PARAMETER ESTIMATION;

AUTOMATIC EXTRACTION OF MODEL COMMANDS; CORPUS-BASED GENERATION; COUNTER GENERATION PROCESS; EMOTIONAL SPEECH SYNTHESIS; F0 MODEL; HMM-BASED SPEECH SYNTHESIS;

SPEECH SYNTHESIS;

EID: 21844479845     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.specom.2005.03.014     Document Type: Conference Paper

References (37)

1. 0 contours from ToBI labels using linear regression. In: Proc. Internat. Conf. on Spoken Language Processing, Philadelphia, pp. 1385-1388.
2. Burkhardt, F., Sendlmeier, W., 2000. Verification of acoustic correlates of emotional speech using formant-synthesis. In: Proc. ISCA Workshop on Speech and Emotion, Northern Ireland 2000, pp. 151-156.
3. Fukuda, T., Komori, Y., Aso, T., Ohora, Y., 1994. A study on pitch pattern generation using HMM-based statistical information. In: Proc. Internat. Conf. on Spoken Language Processing, Yokohama, pp. 723-726.
4. H. Fujisaki, and K. Hirose Analysis of voice fundamental frequency contours for declarative sentences of Japanese J. Acoust. Soc. Japan 5 4 1984 233 242
5. 0 control rules using statistical analysis J. Santen R. Sproat J. Olive J. Hirschberg Progress in Speech Synthesis 1996 Springer 333 346
6. K. Hirose, and H. Fujisaki A system for the synthesis of high-quality speech from texts on general weather conditions IEICE Trans. Fundamentals Electron. Comm. Comput. Sci. E76-A 11 1993 1971 1980
7. Hirose, K., Sakata, M., Kawanami, H., 1996. Synthesizing dialogue speech of Japanese based on the quantitative analysis of prosodic features. In: Proc. Internat. Conf. on Spoken Language Processing, Philadelphia, Vol. 1, pp. 378-381.
8. Hirose, K., Minematsu, N., Kawanami, H., 2000. Analytical and perceptual study on the role of acoustic features in realizing emotional speech. In: Internat. Conf. on Spoken Language Processing, Beijing, Vol. 2, pp. 369-372.
9. Hirose, K., Eto, M., Minematsu, N., Sakurai, A., 2001. Corpus-based synthesis of fundamental frequency contours based on a generation process model. In: Proc. European Conf. on Speech Communication and Technology, Aalborg, pp. 2255-2258.
10. Hirose, K., Eto, M., Minematsu, N., 2002. Improved corpus-based synthesis of fundamental frequency contours using generation process model. In: Proc. Internat. Conf. on Spoken Language Processing, Denver, pp. 2085-2088.
11. Hirose, K., Minematsu, N., Eto, M., 2002. Data-driven synthesis of fundamental frequency contours for TTS systems based on a generation process model. In: Proc. Internat. Conf. on Speech Prosody, Aix-en-Provence, pp. 391-394.
12. 0 contours for emotional speech using the generation process model. In: Proc. 15th Internat. Congress of Phonetic Sciences, Barcelona, Vol. 3, pp. 2945-2948.
13. Hirose, K., Ono, T., Minematsu, N., 2003. Corpus-based synthesis of fundamental frequency contours of Japanese using automatically-generated prosodic corpus and generation process model. In: Proc. European Conf. on Speech Communication and Technology, Geneva, pp. 333-336.
14. 0 contours using generation process model. In: Proc. Internat. Conf. on Speech Prosody, Nara, pp. 417-420.
15. 0 contours using generation process model for emotional speech synthesis. In: Proc. Internat. Conf. on Spoken Language Processing, Jeju, pp. 1349-1352.
16. Jokisch, O., Mixdorff, H., Krusche, H., Kordon, U., 2000. Learning the parameters of quantitative prosody models. In: Proc. Internat. Conf. on Spoken Language Processing, Beijing, pp. 645-648.
17. Y. Kitahara, and Y. Tohkura Prosodic control to express emotions for man-machine speech interaction IEICE Trans. Fundamentals E75-A 2 1992 155 163
18. S. Kurohashi, and M. Nagao A syntactic analysis method of long Japanese sentences based on the detection of conjunctive structures J. Comput. Linguist. 20 4 1994 507 534
19. Lee, A., Kawahara, T., Shikano, K., 2001. Julius-an open source real-time large vocabulary recognition engine. In: Proc. European Conf. on Speech Communication and Technology, Aalborg, pp. 1691-1694.
20. A. Ljolie, and F. Fallside Synthesis of natural sopunding pitch contours in isolated utterances using hidden Markov models IEEE Trans. Acoust. Speech Signal Process. ASSP-34 5 1986 1074 1080
21. Y. Matsumoto Morpheme analysis system "Chasen" IPSJ Mag. 41 11 2000 1208 1214 (in Japanese)
22. N. Minematsu, R. Kita, and K. Hirose Automatic estimation of accentual attribute values of words for accent sandhi rules of Japanese text-to-speech conversion IEICE Trans. Inform. Systems E86-D 3 2003 550 557
23. Mixdorff, H., Jokisch, O., 2001. Building an integrated prosodic model of German. In: Proc. European Conf. on Speech Communication and Technology, Aalborg, pp. 947-950.
24. I. Murray, and J. Arnott Implementation and testing of a system for producing emotion-by-rule in synthetic speech Speech Communication 16 1995 369 390
25. Narusawa, N., Minematsu, N., Hirose, K., Fujiaski, H., 2002. A method for automatic extraction of model parameters from fundamental frequency contours of speech. In: Proc. Internat. Conf. on Acoustics, Speech, and Signal Processing, Orlando, pp. 509-512.
26. J. Pierrehumbert Synthesizing intonation J. Acoust. Soc. Amer. 70 1981 985 995
27. 0 for synthesis. In: Proc. ESCA/IEEE Workshop on Speech Synthesis, New Paltz, pp. 131-134.
28. 0 shape for Japanese text-to-speech. In: Proc. IEEE Internat. Conf. on Acoustics, Speech, and Signal Processing, Albuquerque, pp. 325-328.
29. 0 contours using a superpositional model Speech Communication 40 4 2003 535 549
30. Schröder, M., 2001. Emotional speech synthesis: a review. In: Proc. European Conf. on Speech Communication and Technology, Aalborg, pp. 561-564.
31. Silverman, K., Beckman, M., Pitrelli, J., Ostendorf, M., Wightman, C., Price, P., Pierrehumbert, J., Hirshberg, J., 1992. ToBI: a standard for labelling English prosody. In: Proc. Internat. Conf. on Spoken Language Processing, Banff, pp. 867-870.
32. Taylor, P., 1998. The Tilt intonation model. In: Proc. Internat. Conf. on Spoken Language Processing, Sydney, pp. 1383-1386.
33. Tokuda, K., Masuko, T., Miyazaki, N., Kobayashi, T., 1999. Hidden Markov models based on multispace probability distribution for pitch pattern modeling. In: Proc. Internat. Conf. on Acoustics, Speech, and Signal Processing, Phoenix, pp. 229-232.
34. Tsuzuki, R., Zen, H., Tokuda, K., Kitamura, T., Bulut, M., Narayanan, S., 2004. Constructing emotional speech synthesizers with limited speech database. In: Proc. Internat. Conf. on Spoken Language Processing, Jeju, pp. 1185-1188.
35. Yamagishi, J., Onishi, K., Masuko, T., Kobayashi, T., 2003. Modeling of various speaking styles and emotions for HMM-based speech synthesis. In: Proc. European Conf. on Speech Communication and Technology, Geneva, pp. 2461-2464.
36. Yoshimura, T., Tokuda, K., Masuko, T., Kobayashi, T., Kitamura, T., 1999. Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis. In: Proc. European Conf. on Speech Communication and Technology, Budapest, Vol. 5, pp. 1691-1694.
37. Zovato, E., Sandri, S., Quazza, S., and Badino, L., 2004. Prosodic analysis of a multi-style corpus in the perspective of emotional speech synthesis. In: Proc. Internat. Conf. on Spoken Language Processing, Jeju, pp. 1897-1900.