2026-03-06T06:13:39Z https://ipsj.ixsq.nii.ac.jp/oai

oai:ipsj.ixsq.nii.ac.jp:00194519 2025-01-19T23:27:17Z 1164:5159:9712:9713

Deep Learning-Based Voice Conversion Deep Learning-Based Voice Conversion Zhenhua, Ling Zhenhua, Ling I will introduce our recent work on applying deep learning techniques to voice conversion in this talk. Several methods have been proposed to improve different components in the pipeline of a statistical parametric voice conversion system, including deep neural networks with layer-wise generative training for acoustic modeling, deep autoencoders with binary distributed hidden units for feature representation, and WaveNet vocoder with limited training data for waveform reconstruction. Then, I will introduce our system designed for Voice Conversion Challenge 2018, which achieved the best performance under both parallel and non-parallel conditions in this evaluation. After this, I will present our recent progress on sequence-to-sequence acoustic modeling for voice conversion, which converts the acoustic features and durations of source utterances simultaneously using a unified acoustic model. Finally, some discussions on the future development of voice conversion techniques will be given. I will introduce our recent work on applying deep learning techniques to voice conversion in this talk. Several methods have been proposed to improve different components in the pipeline of a statistical parametric voice conversion system, including deep neural networks with layer-wise generative training for acoustic modeling, deep autoencoders with binary distributed hidden units for feature representation, and WaveNet vocoder with limited training data for waveform reconstruction. Then, I will introduce our system designed for Voice Conversion Challenge 2018, which achieved the best performance under both parallel and non-parallel conditions in this evaluation. After this, I will present our recent progress on sequence-to-sequence acoustic modeling for voice conversion, which converts the acoustic features and durations of source utterances simultaneously using a unified acoustic model. Finally, some discussions on the future development of voice conversion techniques will be given. 情報処理学会 2019-02-20 eng technical report https://ipsj.ixsq.nii.ac.jp/records/194519 2188-8663 AN10442647 研究報告音声言語情報処理（SLP） 2019-SLP-126 4 1 1 https://ipsj.ixsq.nii.ac.jp/record/194519/files/IPSJ-SLP19126004.pdf application/pdf 553.6 kB 2021-02-20