most citedVoice Conversion from Non-parallel Corpora Using Variational Auto-encoder

23 citations · 26 across the 6 of their papers we have counts for

collaborators

6 papers

cs.SD2019

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…

cs.SD2019

Improving the Intelligibility of Electric and Acoustic Stimulation Speech Using Fully Convolutional Networks Based Speech Enhancement

Natalie Yu-Hsien Wang, Hsiao-Lan Sharon Wang, Tao-Wei Wang +4

The combined electric and acoustic stimulation (EAS) has demonstrated better speech recognition than conventional cochlear implant (CI) and yielded satisfactory performance under q…

cs.CL20162 cited

Learning to Distill: The Essence Vector Modeling Framework

Kuan-Yu Chen, Shih-Hung Liu, Berlin Chen +1

In the context of natural language processing, representation learning has emerged as a newly active research subject because of its excellent performance in many applications. Lea…

stat.ML201623 cited

Voice Conversion from Non-parallel Corpora Using Variational Auto-encoder

Chin-Cheng Hsu, Hsin-Te Hwang, Yi-Chiao Wu +2

We propose a flexible framework for spectral conversion (SC) that facilitates training with unaligned corpora. Many SC frameworks require parallel corpora, phonetic alignments, or…

stat.ML2016

Dictionary Update for NMF-based Voice Conversion Using an Encoder-Decoder Network

Chin-Cheng Hsu, Hsin-Te Hwang, Yi-Chiao Wu +2

In this paper, we propose a dictionary update method for Nonnegative Matrix Factorization (NMF) with high dimensional data in a spectral conversion (SC) task. Voice conversion has…

cs.CL20161 cited

Novel Word Embedding and Translation-based Language Modeling for Extractive Speech Summarization

Kuan-Yu Chen, Shih-Hung Liu, Berlin Chen +2

Word embedding methods revolve around learning continuous distributed vector representations of words with neural networks, which can capture semantic and/or syntactic cues, and in…