publications

2022

1. ICASSP 2022

   Voice Filter: Few-Shot Text-to-Speech Speaker Adaptation Using Voice Conversion as a Post-Processing Module

   Adam Gabryś, Goeric Huybrechts, Manuel Sam Ribeiro, and 6 more authors

   In ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) May 2022

   arXiv Bib

   @inproceedings{gabrys2022voice,
     author = {Gabry\'s, Adam and Huybrechts, Goeric and Ribeiro, Manuel Sam and \textbf{Chung-Ming Chien} and Roth, Julian and Comini, Giulia and Barra-Chicote, Roberto and Perz, Bartek and Lorenzo-Trueba, Jaime},
     booktitle = {ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
     title = {Voice Filter: Few-Shot Text-to-Speech Speaker Adaptation Using Voice Conversion as a Post-Processing Module},
     year = {2022},
     volume = {},
     number = {},
     pages = {7902-7906},
     doi = {10.1109/ICASSP43922.2022.9747239},
     month = may,
     eprint = {2202.08164},
     archiveprefix = {arXiv},
     primaryclass = {eess.AS},
   }

2021

1. InterSpeech 2021

   S2VC: A Framework for Any-to-Any Voice Conversion with Self-Supervised Pretrained Representations

   Jheng-hao Lin, Yist Y. Lin, Chung-Ming Chien, and 1 more author

   In Proc. Interspeech 2021 Aug 2021

   arXiv Bib Code

   @inproceedings{lin2021s2vc,
     author = {Lin, Jheng-hao and Lin, Yist Y. and Chien, Chung-Ming and Lee, Hung-yi},
     title = {S2VC: A Framework for Any-to-Any Voice Conversion with Self-Supervised Pretrained Representations},
     year = {2021},
     booktitle = {Proc. Interspeech 2021},
     pages = {836--840},
     doi = {10.21437/Interspeech.2021-1356},
     month = aug,
     eprint = {2104.02901},
     archiveprefix = {arXiv},
     primaryclass = {eess.AS},
   }

2. ICASSP 2021

   Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech

   Chung-Ming Chien, Jheng-Hao Lin, Chien-yu Huang, and 2 more authors

   In ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Jun 2021

   arXiv Bib Code Poster Slides

   @inproceedings{chien2021investigating,
     author = {Chien, Chung-Ming and Lin, Jheng-Hao and Huang, Chien-yu and Hsu, Po-chun and Lee, Hung-yi},
     booktitle = {ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
     title = {Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech},
     year = {2021},
     volume = {},
     number = {},
     pages = {8588-8592},
     doi = {10.1109/ICASSP39728.2021.9413880},
     month = jun,
     eprint = {2103.04088},
     archiveprefix = {arXiv},
     primaryclass = {eess.AS},
   }

3. ICASSP 2021

   FragmentVC: Any-To-Any Voice Conversion by End-To-End Extracting and Fusing Fine-Grained Voice Fragments with Attention

   Chung-Ming Chien*, Yist Y. Lin*, Jheng-Hao Lin, and 2 more authors

   *equal contribution

   In ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Jun 2021

   arXiv Bib Code Poster Slides

   @inproceedings{chien2020fragmentvc,
     author = {Chien*, Chung-Ming and Lin*, Yist Y. and Lin, Jheng-Hao and Lee, Hung-yi and Lee, Lin-shan},
     booktitle = {ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
     title = {FragmentVC: Any-To-Any Voice Conversion by End-To-End Extracting and Fusing Fine-Grained Voice Fragments with Attention},
     year = {2021},
     volume = {},
     number = {},
     pages = {5939-5943},
     doi = {10.1109/ICASSP39728.2021.9413699},
     month = jun,
     eprint = {2010.14150},
     archiveprefix = {arXiv},
     primaryclass = {eess.AS},
   }

4. SLT 2021

   Hierarchical Prosody Modeling for Non-Autoregressive Speech Synthesis

   Chung-Ming Chien, and Hung-yi Lee

   In 2021 IEEE Spoken Language Technology Workshop (SLT) Jan 2021

   arXiv Bib Slides

   @inproceedings{chien2020hierarchical,
     author = {Chien, Chung-Ming and Lee, Hung-yi},
     booktitle = {2021 IEEE Spoken Language Technology Workshop (SLT)},
     title = {Hierarchical Prosody Modeling for Non-Autoregressive Speech Synthesis},
     year = {2021},
     volume = {},
     number = {},
     pages = {446-453},
     doi = {10.1109/SLT48900.2021.9383629},
     month = jan,
     eprint = {2011.06465},
     archiveprefix = {arXiv},
     primaryclass = {eess.AS},
   }