56 citations · 109 across the 14 of their papers we have counts for
14 papers
Decoupled Pronunciation and Prosody Modeling in Meta-Learning-Based Multilingual Speech Synthesis
Yukun Peng, Zhenhua Ling
This paper presents a method of decoupled pronunciation and prosody modeling to improve the performance of meta-learning-based multilingual speech synthesis. The baseline meta-lear…
Generation of Speaker Representations Using Heterogeneous Training Batch Assembly
Yu-Huai Peng, Hung-Shin Lee, Pin-Tuan Huang +1
In traditional speaker diarization systems, a well-trained speaker model is a key component to extract representations from consecutive and partially overlapping segments in a long…
Time Alignment using Lip Images for Frame-based Electrolaryngeal Voice Conversion
Yi-Syuan Liou, Wen-Chin Huang, Ming-Chi Yen +5
Voice conversion (VC) is an effective approach to electrolaryngeal (EL) speech enhancement, a task that aims to improve the quality of the artificial voice from an electrolarynx de…
SVSNet: An End-to-end Speaker Voice Similarity Assessment Model
Cheng-Hung Hu, Yu-Huai Peng, Junichi Yamagishi +2
Neural evaluation metrics derived for numerous speech generation tasks have recently attracted great attention. In this paper, we propose SVSNet, the first end-to-end neural networ…
Relational Data Selection for Data Augmentation of Speaker-dependent Multi-band MelGAN Vocoder
Yi-Chiao Wu, Cheng-Hung Hu, Hung-Shin Lee +5
Nowadays, neural vocoders can generate very high-fidelity speech when a bunch of training data is available. Although a speaker-dependent (SD) vocoder usually outperforms a speaker…
A Preliminary Study of a Two-Stage Paradigm for Preserving Speaker Identity in Dysarthric Voice Conversion
Wen-Chin Huang, Kazuhiro Kobayashi, Yu-Huai Peng +4
We propose a new paradigm for maintaining speaker identity in dysarthric voice conversion (DVC). The poor quality of dysarthric speech can be greatly improved by statistical VC, bu…
Dual-Path Filter Network: Speaker-Aware Modeling for Speech Separation
Fan-Lin Wang, Yu-Huai Peng, Hung-Shin Lee +1
Speech separation has been extensively studied to deal with the cocktail party problem in recent years. All related approaches can be divided into two categories: time-frequency do…
The AS-NU System for the M2VoC Challenge
Cheng-Hung Hu, Yi-Chiao Wu, Wen-Chin Huang +6
This paper describes the AS-NU systems for two tracks in MultiSpeaker Multi-Style Voice Cloning Challenge (M2VoC). The first track focuses on using a small number of 100 target utt…
The Academia Sinica Systems of Voice Conversion for VCC2020
Yu-Huai Peng, Cheng-Hung Hu, Alexander Kang +4
This paper describes the Academia Sinica systems for the two tasks of Voice Conversion Challenge 2020, namely voice conversion within the same language (Task 1) and cross-lingual v…
Unsupervised Representation Disentanglement using Cross Domain Features and Adversarial Learning in Variational Autoencoder based Voice Conversion
Wen-Chin Huang, Hao Luo, Hsin-Te Hwang +4
An effective approach for voice conversion (VC) is to disentangle linguistic content from other components in the speech signal. The effectiveness of variational autoencoder (VAE)…
MoEVC: A Mixture-of-experts Voice Conversion System with Sparse Gating Mechanism for Accelerating Online Computation
Yu-Tao Chang, Yuan-Hong Yang, Yu-Huai Peng +4
With the recent advancements of deep learning technologies, the performance of voice conversion (VC) in terms of quality and similarity has been significantly improved. However, he…
ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech
Xin Wang, Junichi Yamagishi, Massimiliano Todisco +37
Automatic speaker verification (ASV) is one of the most natural and convenient means of biometric person recognition. Unfortunately, just like all other biometric systems, ASV is v…
Generalization of Spectrum Differential based Direct Waveform Modification for Voice Conversion
Wen-Chin Huang, Yi-Chiao Wu, Kazuhiro Kobayashi +6
We present a modification to the spectrum differential based direct waveform modification for voice conversion (DIFFVC) so that it can be directly applied as a waveform generation…
Voice Conversion Based on Cross-Domain Features Using Variational Auto Encoders
Wen-Chin Huang, Hsin-Te Hwang, Yu-Huai Peng +2
An effective approach to non-parallel voice conversion (VC) is to utilize deep neural networks (DNNs), specifically variational auto encoders (VAEs), to model the latent structure…