Emotional voice conversion for Mandarin using tone nucleus model - Small corpus and high efficiency

Proceedings of the 6th International Conference on Speech Prosody, SP 2012

Volumn 1, Issue , 2012, Pages 163-166

  Wang, Miaomiao ^a   Wen, Miaomiao ^b   Hirose, Keikichi ^c   Minematsu, Nobuaki ^c  

^a Toshiba China R and D Center   (China)

^b Language Technologies Institute Carnegie Mellon University ^*  (United States)

^c UNIVERSITY OF TOKYO   (Japan)

Author keywords

Emotional voice conversion; Mandarin; Tone nucleus

Indexed keywords

DYNAMIC PROGRAMMING; METADATA;

CLASSIFICATION AND REGRESSION TREE; DATA SPARSENESS PROBLEM; EMOTIONAL INFORMATION; EMOTIONAL VOICES; MANDARIN; SPECTRAL CONVERSION; SPECTRAL TRANSFORMATIONS; TONE NUCLEUS;

SPEECH PROCESSING;

EID: 84902959938     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. Schröder, M., "Emotional Speech Synthesis: A Review", In Proc. Eurospeech, pp. 561-564, 2001
2. J. Yamagishi, K. Onishi, T. Masuko and T. Kobayashi. 2003. Modeling of various speaking styles and emotions for HMMbased speech synthesis, Proc. Eurospeech, pp.2461-2464.
3. J. Tao, Y. Kang, and A. Li. 2006. Prosody conversion from neutral speech to emotional speech, IEEE Trans. Audio, Speech and Language Processing, vol.14: 1145-1153.
4. H. Tang, X. Zhou, M. Odisio, M. Hasegawa-Johnson and T. Huang. 2008. Two-Stage prosody prediction for emotional textto-speech synthesis, Proc. Interspeech 2008, pp.2138-2141.
5. S.-H. Chen and Y.-R. Wang, Tone recognition of continuous Mandarin speech based on Neural Networks, IEEE Trans. On SAP, Vol. 3, No. 2, 1995, pp.146-150.
6. Xu, Y., Contextual tonal variations in Mandarin. J. Phonetics 25, 61-83, 1997.
7. B. Lindblom, Explaining phonetic variation: a sketch of the H&H theory, W.Hardcastle and A. Marchal (ed.), Speech Production and Speech Modelling. Kluwer Academic Publishers, 1990, pp.403-439.
8. Zhang, J. and Hirose, K., Tone nucleus modeling for Chinese lexical tone recognition, Speech Communication, Vol. 42, Nos. 3-4, pp. 447-466, 2004
9. Chao, Y.-R., 1968. A Grammar of Spoken Chinese. University of California Press, Berkeley.
10. M. Wen, M. Wang, K. Hirose, N. Minematsu, Prosody conversion for emotional Mandarin speech synthesis using the tone nucleus model, Proc. INTERSPEECH, pp.2797-2800, 2011
11. Z. Inanoglu and S. Young. 2009. Data-driven emotion conversion in spoken English, Speech Communication, 51, pp.268-283.
12. H. Kawanami, Y. Iwami, T. Toda, H. Saruwatari, and K. Shikamo. 1999. GMM-based Voice Conversion Applied to Emotional Speech Synthesis, IEEE Trans. Speech and Audio Proc., 7(6):697-708.
13. T. Toda, H. Saruwatari, and K. Shikano. 2001. Voice Conversion Algorithm based on Gaussian Mixture Model with Dynamic Frequency Warping of STRAIGHT spectrum. In Proc. ICASSP, pp. 841-844, Salt Lake City, USA.
14. Y. Stylianou. 1998. Continuous probabilistic transform for voice conversion, IEEE TSAP, no. 6, pp. 131-142.
15. H. Kawahara, I. M. Katsuse, and A. D. 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, no. 3-4, pp. 187-207, 1999.