Efficient deep neural networks for speech synthesis using bottleneck features

International Conference
2016-12-01 16:29
Authors : Young-Sun Joo, Won-Suk Jun, Hong-Goo Kang

Year : 2016

Publisher / Conference : APSIPA

This paper proposes a cascading deep neural network (DNN) structure for speech synthesis system that consists of text-to-bottleneck (TTB) and bottleneck-to-speech (BTS) models. Unlike conventional single structure that requires a large database to find complicated mapping rules between linguistic and acoustic features, the proposed structure is very effective even if the available training database is inadequate. The bottle-neck feature utilized in the proposed approach represents the characteristics of linguistic features and its average acoustic features of several speakers. Therefore, it is more efficient to learn a mapping rule between bottleneck and acoustic features than to learn directly a mapping rule between linguistic and acoustic features. Experimental results show that the learning capability of the proposed structure is much higher than that of the conventional structures. Objective and subjective listening test results also verify the superiority of the proposed structure.
전체 327
7 International Conference Young-Sun Joo, Won-Suk Jun, Hong-Goo Kang "Efficient deep neural networks for speech synthesis using bottleneck features" in APSIPA, 2016
6 International Conference Ji-ho Seo, Young-cheol Park, Dae Hee Youn "Design of feedback active noise control system based on a constrained optimization for headphone/earphone applications" in IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia), 2016
5 International Conference Haemin Yang, Kyungguen Byun, Youngsu Kwak, Hong-Goo Kang "Parametric-based non-intrusive speech quality assessment by deep neural network" in 21th International Conference on Digital Signal Processing (DSP), 2016
4 International Conference Jin-Seob Kim, Young-Sun Joo, Inseon Jang, ChungHyun Ahn, Jeongil Seo, Hong-Goo Kang "A pitch-synchronous speech analysis and synthesis method for DNN-SPSS system" in 21th International Conference on Digital Signal Processing (DSP), 2016
3 International Conference Eunwoo Song, Frank K. Soong, Hong-Goo Kang "Improved Time-Frequency Trajectory Excitation Vocoder for DNN-Based Speech Synthesis" in INTERSPEECH, 2016
2 International Conference Eunwoo Song, Hong-Goo Kang "Multi-class learning algorithm for deep neural network-based statistical parametric speech synthesis" in EUSIPCO, 2016
1 International Conference Hyeongi Moon, Gyutae Park, Yeong-cheol Park, Dae Hee Youn "A Phase-Matched Exponential Harmonic Weighting for Improved Sensation of Virtual Bass" in 140th Convention of Audio Engineering Society, pp.9544, 2016