Publications | Freddy Cheng

Preprints

2024

Task Arithmetic for Language Expansion in Speech Translation

Yao-Fei Cheng, Hayato Futami, Yosuke Kashiwagi, Emiru Tsunoo, Wen Shen Teo, and 2 more authors

In Arxiv preprint, 2024

@inproceedings{preprint_2024_02,
  author = {Cheng, Yao-Fei and Futami, Hayato and Kashiwagi, Yosuke and Tsunoo, Emiru and Teo, Wen Shen and Arora, Siddhant and Watanabe, Shinji},
  title = {Task Arithmetic for Language Expansion in Speech Translation},
  year = {2024},
  booktitle = {Arxiv preprint},
}

Exploring the Impact of Data Quantity on ASR in Extremely Low-resource Languages

Yao-Fei Cheng, Li-Wei Chen, Hung-Shin Lee, and Hsin-Min Wang

In Arxiv preprint, 2024

arXiv Bib

@inproceedings{preprint_2024_01,
  author = {Cheng, Yao-Fei and Chen, Li-Wei and Lee, Hung-Shin and Wang, Hsin-Min},
  title = {Exploring the Impact of Data Quantity on ASR in Extremely Low-resource Languages},
  year = {2024},
  booktitle = {Arxiv preprint},
}

2023

CasNet: Investigating Channel Robustness for Speech Separation

Fan-Lin Wang, Yao-Fei Cheng, Hung-Shin Lee, Yu Tsao, and Hsin-Min Wang

In Arxiv preprint, 2023

arXiv Bib Code

@inproceedings{preprint_2022_02,
  author = {Wang, Fan-Lin and Cheng, Yao-Fei and Lee, Hung-Shin and Tsao, Yu and Wang, Hsin-Min},
  title = {CasNet: Investigating Channel Robustness for Speech Separation},
  year = {2023},
  booktitle = {Arxiv preprint},
}

Peer-reviewed Journal & Conference Papers

2024

Effectiveness of Scalable Monolingual Data and Trigger Words Prompting on Cross-Lingual Emotion Detection Task

Yao-Fei Cheng, Jeongyeob Hong , Andrew Wang, Anita Silva, and Gina-Anne Levow

In Proc. WASSA@ACL, 2024

Bib

@inproceedings{YF_ACL,
  author = {Cheng, Yao-Fei and Hong, Jeongyeob and Wang, Andrew and Silva, Anita and Levow, Gina-Anne},
  title = {Effectiveness of Scalable Monolingual Data and Trigger Words Prompting on Cross-Lingual Emotion Detection Task},
  year = {2024},
  booktitle = {Proc. WASSA@ACL}
}

Exploring speech recognition, translation, and understanding with discrete speech units: A comparative study

Xuankai Chang, Brian Yan, Kwanghee Choi, Jee-Weon Jung, Yichen Lu, and 12 more authors

In Proc. ICASSP, 2024

Bib

@inproceedings{Xuankai_icassp,
  author = {Chang, Xuankai and Yan, Brian and Choi, Kwanghee and Jung, Jee-Weon and Lu, Yichen and Maiti, Soumi and Sharma, Roshan and Shi, Jiatong and Tian, Jinchuan and Watanabe, Shinji and Fujita, Yuya and Maekaku, Takashi and Guo, Pengcheng and Cheng, Yao-Fei and Denisov, Pavel and Saijo, Kohei and Wang, Hsiu-Hsuan},
  title = {Exploring speech recognition, translation, and understanding with discrete speech units: A comparative study},
  year = {2024},
  booktitle = {Proc. ICASSP}
}

2023

A Teacher-student Framework for Unsupervised Speech Enhancement Using Noise Remixing Training and Two-stage Inference

Li-Wei Chen, Yao-Fei Cheng, Hung-Shin Lee, Yu Tsao, and Hsin-Min Wang

In Proc. Interspeech, 2023

arXiv Bib Code

@inproceedings{LW_interspeech,
  author = {Chen, Li-Wei and Cheng, Yao-Fei and Lee, Hung-Shin and Tsao, Yu and Wang, Hsin-Min},
  title = {A Teacher-student Framework for Unsupervised Speech Enhancement Using Noise Remixing Training and Two-stage Inference},
  year = {2023},
  booktitle = {Proc. Interspeech},
}

2022

Speech-enhanced and Noise-aware Networks for Robust Speech Recognition

Hung-Shin Lee, Pin-Yuan Chen, Yao-Fei Cheng, Yu Tsao, and Hsin-Min Wang

In Proc. ISCSLP, 2022

arXiv Bib Code

@inproceedings{HS22_iscslp,
  author = {Lee, Hung-Shin and Chen, Pin-Yuan and Cheng, Yao-Fei and Tsao, Yu and Wang, Hsin-Min},
  title = {Speech-enhanced and Noise-aware Networks for Robust Speech Recognition},
  year = {2022},
  booktitle = {Proc. ISCSLP},
}

Chain-based Discriminative Autoencoders for Speech Recognition

Hung-Shin Lee, Pin-Tuan Huang, Yao-Fei Cheng, and Hsin-Min Wang

In Proc. Interspeech, 2022

arXiv Bib

@inproceedings{HS22_interspeech,
  author = {Lee, Hung-Shin and Huang, Pin-Tuan and Cheng, Yao-Fei and Wang, Hsin-Min},
  title = {Chain-based Discriminative Autoencoders for Speech Recognition},
  year = {2022},
  booktitle = {Proc. Interspeech},
}

2021

AlloST: Low-Resource Speech Translation Without Source Transcription

Yao-Fei Cheng, Hung-Shin Lee, and Hsin-Min Wang

In Proc. Interspeech, 2021

DOI arXiv Bib Code

@inproceedings{cheng21_interspeech,
  author = {Cheng, Yao-Fei and Lee, Hung-Shin and Wang, Hsin-Min},
  title = {AlloST: Low-Resource Speech Translation Without Source Transcription},
  year = {2021},
  booktitle = {Proc. Interspeech},
  pages = {2252--2256},
  doi = {10.21437/Interspeech.2021-526},
}