publications

2023

1. ICASSP 2024

   AV2Wav: Diffusion-Based Re-synthesis from Continuous Self-supervised Features for Audio-Visual Speech Enhancement

   Ju-Chieh Chou, Chung-Ming Chien, and Karen Livescu

   preprint arXiv:2309.08030

   arXiv Bib

   @misc{chou2023av2wav,
     title = {AV2Wav: Diffusion-Based Re-synthesis from Continuous Self-supervised Features for Audio-Visual Speech Enhancement},
     author = {Chou, Ju-Chieh and Chien, Chung-Ming and Livescu, Karen},
     year = {2023},
     month = dec,
     eprint = {2309.08030},
     archiveprefix = {arXiv},
     primaryclass = {eess.AS},
   }

2. arXiv

   What Do Self-Supervised Speech Models Know about Words?

   Ankita Pasad, Chung-Ming Chien, Shane Settle, and 1 more author

   preprint arXiv:2307.00162

   arXiv Bib

   @misc{pasad2023selfsupervised,
     title = {What Do Self-Supervised Speech Models Know about Words?},
     author = {Pasad, Ankita and Chien, Chung-Ming and Settle, Shane and Livescu, Karen},
     year = {2023},
     eprint = {2307.00162},
     archiveprefix = {arXiv},
     primaryclass = {cs.CL},
   }

3. ASRU 2023

   Few-Shot Spoken Language Understanding via Joint Speech-Text Models

   Chung-Ming Chien, Mingjiamei Zhang, Ju-Chieh Chou, and 1 more author

   Best Student Paper Award

   In 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

   arXiv Bib Poster Slides Video

   @inproceedings{chien2023few,
     title = {Few-Shot Spoken Language Understanding via Joint Speech-Text Models},
     author = {Chien, Chung-Ming and Zhang, Mingjiamei and Chou, Ju-Chieh and Livescu, Karen},
     booktitle = {2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)},
     year = {2023},
     month = dec,
     eprint = {2310.05919},
     archiveprefix = {arXiv},
     primaryclass = {cs.CL},
   }

4. EMNLP 2023

   Toward Joint Language Modeling for Speech Units and Text

   Ju-Chieh Chou, Chung-Ming Chien, Wei-Ning Hsu, and 5 more authors

   In Findings of the Association for Computational Linguistics: EMNLP 2023

   arXiv Bib

   @inproceedings{chou2023toward,
     title = {Toward Joint Language Modeling for Speech Units and Text},
     author = {Chou, Ju-Chieh and Chien, Chung-Ming and Hsu, Wei-Ning and Livescu, Karen and Babu, Arun and Conneau, Alexis and Baevski, Alexei and Auli, Michael},
     booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2023},
     year = {2023},
     pages = {6582--6593},
     doi = {10.18653/v1/2023.findings-emnlp.438"},
     month = dec,
     url = {https://aclanthology.org/2023.findings-emnlp.438},
     eprint = {2310.08715},
     archiveprefix = {arXiv},
     primaryclass = {cs.CL},
   }

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)

   arXiv Bib

   @inproceedings{gabrys2022voice,
     author = {Gabry\'s, Adam and Huybrechts, Goeric and Ribeiro, Manuel Sam and Chien, Chung-Ming 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

   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)

   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)

   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)

   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},
   }