@techreport{oai:ipsj.ixsq.nii.ac.jp:00194519,
 author = {Zhenhua, Ling and Zhenhua, Ling},
 issue = {4},
 month = {Feb},
 note = {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.},
 title = {Deep Learning-Based Voice Conversion},
 year = {2019}
}