publications

2023

  1. Bayes Risk Transducer: Transducer with Controllable Alignment Prediction
    Jinchuan Tian, Jianwei Yu, Hangting Chen, and 4 more authors
    In Proc. INTERSPEECH 2023, 2023
  2. Integrating Lattice-Free MMI Into End-to-End Speech Recognition
    Jinchuan Tian, Jianwei Yu, Chao Weng, and 2 more authors
    IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2023
  3. BAYES RISK CTC: CONTROLLABLE CTC ALIGNMENT IN SEQUENCE-TO-SEQUENCE TASKS
    Jinchuan Tian, Brian Yan, Jianwei Yu, and 3 more authors
    In The Eleventh International Conference on Learning Representations , 2023
  4. Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data
    Yifan Peng, Jinchuan Tian, Brian Yan, and 8 more authors
    arXiv preprint arXiv:2309.13876, 2023
  5. UniAudio: An Audio Foundation Model Toward Universal Audio Generation
    Dongchao* Yang, Jinchuan* Tian, Xu Tan, and 8 more authors
    arXiv preprint arXiv:2310.00704, 2023
  6. AutoPrep: An Automatic Preprocessing Framework for In-the-Wild Speech Data
    Jianwei Yu, Hangting Chen, Yanyao Bian, and 6 more authors
    arXiv preprint arXiv:2309.13905, 2023
  7. Hifi-codec: Group-residual vector quantization for high fidelity audio codec
    Dongchao Yang, Songxiang Liu, Rongjie Huang, and 3 more authors
    arXiv preprint arXiv:2305.02765, 2023
  8. Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study
    Xuankai Chang, Brian Yan, Kwanghee Choi, and 8 more authors
    arXiv preprint arXiv:2309.15800, 2023

2022

  1. LAE: Language-Aware Encoder for Monolingual and Multilingual ASR
    Jinchuan Tian, Jianwei Yu, Chunlei Zhang, and 2 more authors
    In Proc. Interspeech 2022, 2022
  2. Consistent Training and Decoding for End-to-End Speech Recognition Using Lattice-Free MMI
    Jinchuan Tian, Jianwei Yu, Chao Weng, and 4 more authors
    In ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022
  3. Improving Mandarin End-to-End Speech Recognition With Word N-Gram Language Model
    Jinchuan Tian, Jianwei Yu, Chao Weng, and 2 more authors
    IEEE Signal Processing Letters, 2022
  4. Speaker-Aware Mixture of Mixtures Training for Weakly Supervised Speaker Extraction
    Zifeng Zhao, Rongzhi Gu, Dongchao Yang, and 2 more authors
    In Proc. Interspeech 2022, 2022

2020

  1. A Random Gossip BMUF Process for Neural Language Modeling
    Yiheng Huang, Jinchuan Tian, Lei Han, and 4 more authors
    In ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020