Perceptual quality and modeling accuracy of excitation parameters in DLSTM-based speech synthesis systems

International Conference
2017-12-01 16:38
Authors : Eunwoo Song, Frank K. Soong, Hong-Goo Kang

Year : 2017

Publisher / Conference : ASRU

This paper investigates how the perceptual quality of the synthesized speech is affected by reconstruction errors in excitation signals generated by a deep learning-based statistical model. In this framework, the excitation signal obtained by an LPC inverse filter is first decomposed into harmonic and noise components using an improved time-frequency trajectory excitation (ITFTE) scheme, then they are trained and generated by a deep long short-term memory (DLSTM)-based speech synthesis system. By controlling the parametric dimension of the ITFTE vocoder, we analyze the impact of the harmonic and noise components to the perceptual quality of the synthesized speech. Both objective and subjective experimental results confirm that the maximum perceptually allowable spectral distortion for the harmonic spectrum of the generated excitation is ~0.08 dB. On the other hand, the absolute spectral distortion in the noise components is meaningless, and only the spectral envelope is relevant to the perceptual quality.
전체 355
102 International Conference Min-Jae Hwang, Hong-Goo Kang "Parameter enhancement for MELP speech codec in noisy communication environment" in INTERSPEECH, 2019
101 International Conference Keulbit Kim, Jinkyu Lee, Jan Skoglund, Hong-Goo Kang "Model Order Selection for Wind Noise Reduction in Non-negative Matrix Factorization" in ITC-CSCC, 2019
100 International Conference Ohsung Kwon, Inseon Jang, ChungHyun Ahn, Hong-Goo Kang "Emotional Speech Synthesis Based on Style Embedded Tacotron2 Framework" in ITC-CSCC, 2019
99 International Conference Kyungguen Byun, Eunwoo Song, Jinseob Kim, Jae-Min Kim, Hong-Goo Kang "Excitation-by-SampleRNN Model for Text-to-Speech" in ITC-CSCC, 2019
98 International Conference Yang Yuan, Soo-Whan Chung, Hong-Goo Kang "Gradient-based active learning query strategy for end-to-end speech recognition" in ICASSP, 2019
97 International Conference Soo-Whan Chung, Joon Son Chung, Hong-Goo Kang "Perfect match: Improved cross-modal embeddings for audio-visual synchronisation" in ICASSP, 2019
96 International Conference Hyewon Han, Kyungguen Byun, Hong-Goo Kang "A Deep Learning-based Stress Detection Algorithm with Speech Signal" in Workshop on Audio-Visual Scene Understanding for Immersive Multimedia (AVSU’18), 2018
95 International Conference Min-Jae Hwang, Eunwoo Song, Jin-Seob Kim, Hong-Goo Kang "A Unified Framework for the Generation of Glottal Signals in Deep Learning-based Parametric Speech Synthesis Systems" in INTERSPEECH, 2018
94 International Conference Haemin Yang, Soyeon Choe, Keulbit Kim, Hong-Goo Kang "Deep learning-based speech presence probability estimation for noise PSD estimation in single-channel speech enhancement" in ICSigSys, 2018
93 International Conference Min-Jae Hwang, Eunwoo Song, Kyungguen Byun, Hong-Goo Kang "Modeling-by-Generation-Structured Noise Compensation Algorithm for Glottal Vocoding Speech Synthesis System" in ICASSP, 2018