Many-to-many voice conversion based on multiple non-negative matrix factorization

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

Volumn 2015-January, Issue , 2015, Pages 2749-2753

  Aihara, Ryo ^a   Takiguchi, Testuya ^a   Ariki, Yasuo ^a  

^a KOBE UNIVERSITY   (Japan)

Author keywords

Exemplar based; Many tomany; NMF; Speech synthesis; Voice conversion

Indexed keywords

FACTORIZATION; GAUSSIAN DISTRIBUTION; SPEECH COMMUNICATION; SPEECH PROCESSING; SPEECH SYNTHESIS;

EXEMPLAR-BASED; GAUSSIAN MIXTURE MODEL; MANY-TOMANY; NOISE ROBUSTNESS; NONNEGATIVE MATRIX FACTORIZATION; PARALLEL TRAINING; VOICE CONVERSION; VOICE QUALITY CONTROLS;

MATRIX ALGEBRA;

EID: 84959090646     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (27)

1. Y. Stylianou, O. Cappe, and E. Moilines, "Continuous probabilistictransform for voice conversion, " IEEE Trans. Speech and AudioProcessing, vol. 6, no. 2, pp. 131-142, 1998.
2. K. Nakamura, T. Toda, H. Saruwatari, and K. Shikano, "Speakingaidsystems using GMM-based voice conversion for electrolaryngealspeech, " Speech Communication, vol. 54, no. 1, pp. 134-146, 2012.
3. A. Kain and M. W. Macon, "Spectral voice conversion for text-tospeechsynthesis, " in Proc. ICASSP, vol. 1, pp. 285-288, 1998.
4. K. Nakamura, K. Hashimoto, K. Oura, Y. Nankaku, and K. Tokuda, "A mel-cepstral analysis technique restoring high frequencycomponents from low-sampling-rate speech, " in Proc. Interspeech, pp. 2494-2498, 2014.
5. Y. Ohtani, M. Tamura, M. Morita, and M. Akamine, "GMM-basedband width extension using sub-band basis spectrum model, " inProc. Interspeech, pp. 2489-2493, 2014.
6. M. Abe, S. Nakamura, K. Shikano, and H. Kuwabara, "Esophageal speech enhancement based on statistical voice conversionwith Gaussian mixture models, " in Proc. ICASSP, pp. 655-658, 1988.
7. H. Valbret, E. Moulines, and J. P. Tubach, "Voice transformationusing PSOLA technique, " Speech Communication, vol. 11, no. 2-3, pp. 175-187, 1992.
8. T. Toda, A. Black, and K. Tokuda, "Voice conversion based onmaximum likelihood estimation of spectral parameter trajectory, "IEEE Trans. Audio, Speech, Lang. Process., vol. 15, no. 8, pp. 2222-2235, 2007.
9. E. Heland er, T. Virtanen, J. Nurminen, and M. Gabbouj, "Voiceconversion using partial least squares regression, " IEEE Trans. Audio, Speech, Lang. Process., vol. 18, Issue: 5, pp. 912-921, 2010.
10. R. Takashima, T. Takiguchi, and Y. Ariki, "Exemplar-based voiceconversion in noisy environment, " in Proc. SLT, pp. 313-317, 2012.
11. Z. Wu, T. Virtanen, E. S. Chng, and H. Li, "Exemplar-basedsparse representation with residual compensation for voice conversion, "IEEE Trans. Audio, Speech, Lang. Process., vol. 22, no. 10, pp. 1506-1521, 2014.
12. R. Aihara, R. Takashima, T. Takiguchi, and Y. Ariki, "Noiserobustvoice conversion based on sparse spectral mapping usingnon-negative matrix factorization, " IEICE Transactions on Informationand Systems, vol. E97-D, no. 6, pp. 1411-1418, 2014.
13. D. D. Lee and H. S. Seung, "Algorithms for non-negative matrixfactorization, " Neural Information Processing System, pp. 556-562, 2001.
14. M. N. Schmidt and R. K. Olsson, "Single-channel speech separationusing sparse non-negative matrix factorization, " in Proc. Interspeech, 2006.
15. T. Virtanen, "Monaural sound source separation by non-negativematrix factorization with temporal continuity and sparseness criteria, "IEEE Trans. Audio, Speech, Lang. Process., vol. 15, no. 3, pp. 1066-1074, 2007.
16. J. F. Gemmeke, T. Viratnen, and A. Hurmalainen, "Exemplarbasedsparse representations for noise robust automatic speechrecognition, " IEEE Trans. Audio, Speech, Lang. Process., vol. 19, no. 7, pp. 2067-2080, 2011.
17. R. Aihara, T. Nakashika, T. Takiguchi, and Y. Ariki, "Voiceconversion based on non-negative matrix factorization usingphoneme-categorized dictionary, " in Proc. ICASSP, pp. 7944-7948, 2014.
18. R. Aihara, R. Takashima, T. Takiguchi, and Y. Ariki, "A preliminarydemonstration of exemplar-based voice conversion for articulationdisorders using an individuality-preserving dictionary, "EURASIP Journal on Audio, Speech, and Music Processing, vol. 2014: 5, doi: 10. 1186/1687-4722-2014-5, 2014.
19. K. Masaka, R. Aihara, T. Takiguchi, and Y. Ariki, "Multimodalexemplar-based voice conversion using lip features in noisy environments, "in Proc. INTERSPEECH, vol. 1159-1163, 2014.
20. C. H. Lee and C. H. Wu, "MAP-based adaptation for speech conversionusing adaptation data selection and non-parallel training, "in Proc. INTERSPEECH, pp. 2254-2257, 2006.
21. A. Mouchtaris, J. V. der Spiegel, and P. Mueller, "Nonparalleltraining for voice conversion based on a parameter adaptation approach, "Audio, Speech, and Language Processing, IEEE Transactionson 14 (3), pp. 952-963, 2006.
22. T. Toda, Y. Ohtani, and K. Shikano, "Eigenvoice conversion basedon Gaussian mixture model, " in Proc. Interspeech, pp. 2446-2449, 2006.
23. Y. Ohtani, T. Toda, H. Saruwatari, and K. Shikano, "Many-tomanyeigenvoice conversion with reference voice, " in Proc. Interspeech, pp. 1623-1626, 2009.
24. D. Saito, K. Yamamoto, N. Minematsu, and K. Hirose, "One-tomanyvoice conversion based on tensor representation of speakerspace, " in Proc. INTERSPEECH, pp. 653-656, 2011.
25. A. Kurematsu, K. Takeda, Y. Sagisaka, S. Katagiri, H. Kuwabara, and K. Shikano, "ATR Japanese speech database as a tool ofspeech recognition and synthesis, " Speech Communication, vol. 9, pp. 357-363, 1990.
26. H. Kawahara, "STRAIGHT, exploitation of the other aspectof vocoder: Perceptually isomorphic decomposition of speechsounds, " Acoustical Science and Technology, pp. 349-353, 2006.
27. INTERNATIONAL TELECOMMUNICATION UNION, "Methodsfor objective and subjective assessment of quality, " ITU-TRecommendation P. 800, 2003.