Papers

Improved Time-Frequency Trajectory Excitation Vocoder for DNN-Based Speech Synthesis

International Conference
2016~2020
작성자
한혜원
작성일
2016-09-01 16:25
조회
2638
Authors : Eunwoo Song, Frank K. Soong, Hong-Goo Kang

Year : 2016

Publisher / Conference : INTERSPEECH

We investigate an improved time-frequency trajectory excitation (ITFTE) vocoder for deep neural network (DNN)-based statistical parametric speech synthesis (SPSS) systems. The ITFTE is a linear predictive coding-based vocoder, where a pitch-dependent excitation signal is represented by a periodicity distribution in a time-frequency domain. The proposed method significantly improves the parameterization efficiency of ITFTE vocoder for the DNN-based SPSS system, even if its dimension changes due to the inherent nature of pitch variation. By utilizing an orthogonality property of discrete cosine transform, we not only accurately reconstruct the ITFTE parameters but also improve the perceptual quality of synthesized speech. Objective and subjective test results confirm that the proposed method provides superior synthesized speech compared to the previous system.
전체 369
87 International Conference Young-Sun Joo, Won-Suk Jun, Hong-Goo Kang "Efficient deep neural networks for speech synthesis using bottleneck features" in APSIPA, 2016
86 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
85 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
84 International Conference Eunwoo Song, Frank K. Soong, Hong-Goo Kang "Improved Time-Frequency Trajectory Excitation Vocoder for DNN-Based Speech Synthesis" in INTERSPEECH, 2016
83 Domestic Conference Hyeonjoo Kang, Young-sun Joo, Wonsuk Jun, Hong-goo Kang "다층신경망 기반 다중 화자 음성변환 시스템" in 한국음향학회 제 33회 음성통신 및 신호처리 학술대회, 2016
82 International Conference Eunwoo Song, Hong-Goo Kang "Multi-class learning algorithm for deep neural network-based statistical parametric speech synthesis" in EUSIPCO, 2016
81 Domestic Conference Min-jae Hwang, JeeSok Lee, Misuk Lee, and Hong-Goo Kang "사전 분석법을 통한 스프레드 스펙트럼 기반 오디오 워터마킹 알고리즘의 성능 향상" in 한국음향학회 제 33회 음성통신 및 신호처리 학술대회, 2016
80 International Conference Il-eun Kwak, Hong-Goo Kang "Robust formant features for speaker verification in the lombard effect" in APSIPA, pp.114-118, 2015
79 International Journal Ho Seon Shin, Tim Fingscheidt, Hong-Goo Kang "A Priori SNR Estimation Using Air- and Bone-Conduction Microphones" in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol.23, issue 11, pp.2015-2025, 2015
78 International Conference Hyeonjoo Kang, JeeSok Lee, Soonho Baek, Hong-Goo Kang "Systematic Integration of Acoustic Echo Canceller and Noise Reduction Modules for Voice Communication Systems" in INTERSPEECH, 2015