Papers

ExcitGlow: Improving a WaveGlow-based Neural Vocoder with Linear Prediction Analysis

International Conference
2016~2020
작성자
한혜원
작성일
2020-12-01 16:59
조회
1775
Authors : Suhyeon Oh, Hyungseob Lim, Kyungguen Byun, Min-Jae Hwang, Eunwoo Song, Hong-Goo Kang

Year : 2020

Publisher / Conference : APSIPA (*awarded Best Paper)

Research area : Speech Signal Processing, Text-to-Speech

Presentation/Publication date : 2020.12.10

Related project : Embedded Neural TTS

Presentation : Oral

In this paper we propose ExcitGlow, a vocoder that incorporates the source-filter model of voice production theory into a flow-based deep generative model. By targeting the distribution of the excitation signal instead of the speech waveform itself, we significantly reduce the size of the flow-based generative model. To further reduce the number of parameters, we apply a parameter sharing technique in which a single affine coupling layer is used for several flow layers. To avoid quality degradation, we also introduce a closed-loop training framework to optimize the flow model for both the speech and excitation signal generation processes. Specifically, we choose negative log-likelihood (NLL) loss for the excitation signal and multi-resolution spectral distance for the speech signal. As a result, we are able to reduce the model size from 87.73M to 15.60M parameters while maintaining the perceptual quality of synthesized speech.

* Awarded Best paper in APSIPA 2020

전체 356
356 International Conference Yanjue Song, Doyeon Kim, Hong-Goo Kang, Nilesh Madhu "Spectrum-aware neural vocoder based on self-supervised learning for speech enhancement" in EUSIPCO, 2024
355 International Conference Hyewon Han, Naveen Kumar "A cross-talk robust multichannel VAD model for multiparty agent interactions trained using synthetic re-recordings" in Hands-free Speech Communication and Microphone Arrays (HSCMA, Satellite workshop in ICASSP), 2024
354 International Conference Yanjue Song, Doyeon Kim, Nilesh Madhu, Hong-Goo Kang "On the Disentanglement and Robustness of Self-Supervised Speech Representations" in International Conference on Electronics, Information, and Communication (ICEIC) (*awarded Best Paper), 2024
353 International Conference Yeona Hong, Miseul Kim, Woo-Jin Chung, Hong-Goo Kang "Contextual Learning for Missing Speech Automatic Speech Recognition" in International Conference on Electronics, Information, and Communication (ICEIC), 2024
352 International Conference Juhwan Yoon, Seyun Um, Woo-Jin Chung, Hong-Goo Kang "SC-ERM: Speaker-Centric Learning for Speech Emotion Recognition" in International Conference on Electronics, Information, and Communication (ICEIC), 2024
351 International Conference Hejung Yang, Hong-Goo Kang "On Fine-Tuning Pre-Trained Speech Models With EMA-Target Self-Supervised Loss" in ICASSP, 2024
350 International Journal Zainab Alhakeem, Se-In Jang, Hong-Goo Kang "Disentangled Representations in Local-Global Contexts for Arabic Dialect Identification" in Transactions on Audio, Speech, and Language Processing, 2024
349 International Conference Hong-Goo Kang, W. Bastiaan Kleijn, Jan Skoglund, Michael Chinen "Convolutional Transformer for Neural Speech Coding" in Audio Engineering Society Convention, 2023
348 International Conference Hong-Goo Kang, Jan Skoglund, W. Bastiaan Kleijn, Andrew Storus, Hengchin Yeh "A High-Rate Extension to Soundstream" in IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2023
347 International Conference Zhenyu Piao, Hyungseob Lim, Miseul Kim, Hong-goo Kang "PDF-NET: Pitch-adaptive Dynamic Filter Network for Intra-gender Speaker Verification" in APSIPA ASC, 2023