activity
20182021
most citedVoice Transformer Network: Sequence-to-Sequence Voice Conversion Using Transformer with Text-to-Speech Pretraining

38 citations · 69 across the 10 of their papers we have counts for

collaborators

22 papers

cs.SD20217 cited

Noisy-to-Noisy Voice Conversion Framework with Denoising Model

Chao Xie, Yi-Chiao Wu, Patrick Lumban Tobing +2

In a conventional voice conversion (VC) framework, a VC model is often trained with a clean dataset consisting of speech data carefully recorded and selected by minimizing backgrou…

eess.AS2021

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…

eess.AS20212 cited

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…

cs.SD2021

Unified Source-Filter GAN: Unified Source-filter Network Based On Factorization of Quasi-Periodic Parallel WaveGAN

Reo Yoneyama, Yi-Chiao Wu, Tomoki Toda

We propose a unified approach to data-driven source-filter modeling using a single neural network for developing a neural vocoder capable of generating high-quality synthetic speec…

eess.AS20212 cited

crank: An Open-Source Software for Nonparallel Voice Conversion Based on Vector-Quantized Variational Autoencoder

Kazuhiro Kobayashi, Wen-Chin Huang, Yi-Chiao Wu +3

In this paper, we present an open-source software for developing a nonparallel voice conversion (VC) system named crank. Although we have released an open-source VC software based…

eess.AS2020

Any-to-One Sequence-to-Sequence Voice Conversion using Self-Supervised Discrete Speech Representations

Wen-Chin Huang, Yi-Chiao Wu, Tomoki Hayashi +1

We present a novel approach to any-to-one (A2O) voice conversion (VC) in a sequence-to-sequence (seq2seq) framework. A2O VC aims to convert any speaker, including those unseen duri…