Scopus

Reducing over-smoothness in HMM-based speech synthesis using exemplar-based voice conversion

Năm XB 2017 Tạp chí / Hội thảo Eurasip Journal on Audio, Speech, and Music Processing Volume 2017 (1) DOI / Link https://doi.org/10.1186/s13636-017-0113-5 ↗

Tác giả

Trung-Nghia Phung

Tóm tắt

Speech synthesis has been applied in many kinds of practical applications. Currently, state-of-the-art speech synthesis uses statistical methods based on hidden Markov model (HMM). Speech synthesized by statistical methods can be considered over-smooth caused by the averaging in statistical processing. In the literature, there have been many studies attempting to solve over-smoothness in speech synthesized by an HMM. However, they are still limited. In this paper, a hybrid synthesis between HMM and exemplar-based voice conversion has been proposed. The experimental results show that the proposed method outperforms state-of-the-art HMM synthesis using global variance.

Tài liệu tham khảo

[1] J Yamagishi et al., A training method of average voice model for HMM-based speech synthesis. IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences 86.8, 2003, pp. 1956–1963

[2] K Tokuda, Z Heiga, AW Black, An HMM-based speech synthesis system applied to English. IEEE Speech Synthesis Workshop, 2002

[3] K Tokuda et al., Speech parameter generation algorithms for HMM-based speech synthesis. IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP'00, Vol. 3. IEEE, 2000

[4] T Tomoki, T Keiichi, A speech parameter generation algorithm considering global variance for HMM-based speech synthesis. IEICE Transactions on Information and Systems 90.5, 2007, pp. 816–824

[5] M Zhang et al., Improving HMM Based speech synthesis by reducing over-smoothing problems. 6th International Symposium on Chinese Spoken Language Processing, ISCSLP'08, IEEE, 2008

[6] G Beller, O Nicolas, R Xavier, Articulation degree as a prosodic dimension of expressive speech. Fourth International Conference on Speech Prosody, 2008

[7] S Lee, B Erik, N Shrikanth, An exploratory study of emotional speech production using functional data analysis techniques. 7th International Seminar on Speech Production, 2006

[8] Y Agiomyrgiannakis, R Zoi, Voice morphing that improves TTS quality using an optimal dynamic frequency warping-and-weighting transform. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2016

[9] Y Qian, FK Soong, Y Zhi-Jie, A unified trajectory tiling approach to high quality speech rendering. IEEE Transactions on Audio, Speech, and Language Processing 21.2, 2013, pp. 280–290

[10] T Toda, AW Black, T Keiichi, Voice conversion based on maximum-likelihood estimation of spectral parameter trajectory. IEEE Transactions on Audio, Speech, and Language Processing 15.8, 2007, pp. 2222–2235

[11] W Zhizheng, C Eng Siong, L Haizhou, Exemplar-based voice conversion using joint nonnegative matrix factorization. Multimedia Tools and Applications 74(22), 9943–9958 (2015). Springer

[12] L-H Chen et al., DNN-based stochastic postfilter for HMM-based speech synthesis. INTERSPEECH, 2014

[13] E Godoy, R Olivier, C Thierry, Voice conversion using dynamic frequency warping with amplitude scaling, for parallel or nonparallel corpora. IEEE Transactions on Audio, Speech, and Language Processing 20.4, 2012, pp. 1313–1323

[14] Y Jiao et al., Improving voice quality of HMM-based speech synthesis using voice conversion method, 2014

[15] AT Dinh, M Akagi, Quality improvement of HMM-based synthesized speech based on decomposition of naturalness and intelligibility using non-negative matrix factorization. O-COCOSDA (ᅟ, Bali, Indonesia, 2016), pp. 62–67

[16] C Nguyen Phu, T Ochi, A Masato, Modified restricted temporal decomposition and its application to low rate speech coding. IEICE Transactions on Information and Systems 86.3, 2003, pp. 397–405

[17] H Kawahara, Speech representation and transformation using adaptive interpolation of weighted spectrum: vocoder revisited. IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP-97, Vol. 2. IEEE, 1997

[18] C Veaux, Y Junichi, MD Kirsten, CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit, 2016

← Quay lại danh sách bài báo