Hao SHI
Conference (Reviewed)
  • Ensemble Inference for Diffusion Model-based Speech Enhancement.  [PDF] [.bib]
    Hao Shi, Naoyuki Kamo, Marc Delcroix, Tomohiro Nakatani, and Shoko Araki.
    In Proc. HSCMA, pp.xx--xx, 2024.
  • Diffusion-Based Speech Enhancement with Joint Generative and Predictive Decoders.  [PDF] [.bib]
    Hao Shi, Kazuki Shimada, Masato Hirano, Takashi Shibuya, Yuichiro Koyama, Zhi Zhong, Shusuke Takahashi, Tatsuya Kawahara, and Yuki Mitsufuji.
    In Proc. ICASSP, pp.12951--12955, 2024.
  • Enhancing Two-stage Finetuning for Speech Emotion Recognition Using Adapters.  [PDF] [.bib]
    Yuan Gao, Hao Shi, Chenhui Chu, Tatsuya Kawahara
    In Proc. ICASSP, pp.11316--11320, 2024.
  • Investigation of Adapter for Automatic Speech Recognition in Noisy Environment.  [PDF] [.bib]
    Hao Shi, Tatsuya Kawahara.
    In SIG Technical Reports, pp.1--6, 2023.
  • Extending Audio Masked Autoencoders Toward Audio Restoration.  [PDF] [.bib]
    Zhi Zhong, Hao Shi, Masato Hirano, Kazuki Shimada, Kazuya Tateishi, Takashi Shibuya, Shusuke Takahashi, Yuki Mitsufuji.
    In Proc. WASPAA, pp.1--5, 2023.
  • Time-domain Speech Enhancement Assisted by Multi-resolution Frequency Encoder and Decoder.  [PDF] [.bib]
    Hao Shi, Masato Mimura, Longbiao Wang, Jianwu Dang, and Tatsuya Kawahara.
    In Proc. ICASSP, pp.1--5, 2023.
  • Fusing Multiple Bandwidth Spectrograms for Improving Speech Enhancement.  [PDF] [.bib]
    Hao Shi, Yuchun Shu, Longbiao Wang, Jianwu Dang, and Tatsuya Kawahara.
    In Proc. APSIPA ASC, pp.1935--1940, 2022.
  • Subband-Based Spectrogram Fusion for Speech Enhancement by Combining Mapping and Masking Approaches.  [PDF] [.bib]
    Hao Shi, Longbiao Wang, Sheng Li, Jianwu Dang, and Tatsuya Kawahara.
    In Proc. APSIPA ASC, pp.286--292, 2022.
  • Monaural speech enhancement based on spectrogram decomposition for convolutional neural network-sensitive feature extraction.  [PDF] [.bib]
    Hao Shi, Longbiao Wang, Sheng Li, Jianwu Dang, and Tatsuya Kawahara.
    In Proc. INTERSPEECH, pp.221--225, 2022.
  • Language-specific Characteristic Assistance for Code-switching Speech Recognition.  [PDF] [.bib]
    Tongtong Song, Qiang Xu, Meng Ge, Longbiao Wang, Hao Shi, Yongjie Lv, Yuqin Lin, and Jianwu Dang.
    In Proc. INTERSPEECH, pp.3924--3928, 2022.
    (Corresponding author)
  • Self-Distillation Based on High-level Information Supervision for Compressing End-to-End ASR Model.  [PDF] [.bib]
    Qiang Xu, Tongtong Song, Longbiao Wang, Hao Shi, Yuqin Lin, Yongjie Lv, Meng Ge, Qiang Yu, and Jianwu Dang.
    In Proc. INTERSPEECH, pp.1716--1720, 2022.
    (Corresponding author)
  • Adaptive Attention Network with Domain Adversarial Training for Multi-Accent Speech Recognition.  [PDF] [.bib]
    Yanbing Yang, Hao Shi, Yuqin Lin, Meng Ge, Longbiao Wang, Qingzhi Hou and Jianwu Dang.
    In Proc. ISCSLP, pp.6--10, 2022.
  • Spectrograms Fusion-based End-to-end Robust Automatic Speech Recognition.  [PDF] [.bib]
    Hao Shi, Longbiao Wang, Sheng Li, Cunhang Fan, Jianwu Dang, and Tatsuya Kawahara.
    In Proc. APSIPA ASC, pp.438--442, 2021.
  • Speech Dereverberation Based on Scale-aware Mean Square Error Loss.  [PDF] [.bib]
    Luya Qiang, Hao Shi, Meng Ge, Haoran Yin, Nan Li, Longbiao Wang, Sheng Li, and Jianwu Dang.
    In Proc of ICONIP, pp.55--63, 2021.
    (Joint first author, equal contribution)
  • Simultaneous Progressive Filtering-based Monaural Speech Enhancement.  [PDF] [.bib]
    Haoran Yin, Hao Shi, Longbiao Wang, Luya Qiang, Sheng Li, Meng Ge, Gaoyan Zhang, and Jianwu Dang.
    In Proc. ICONIP, pp.213--221, 2021.
    (Joint first author, equal contribution)
  • Singing Voice Extraction with Attention-Based Spectrograms Fusion.  [PDF] [.bib]
    Hao Shi, Longbiao Wang, Sheng Li, Chenchen Ding, Meng Ge, Nan Li, Jianwu Dang, and Hiroshi Seki.
    In Proc. INTERSPEECH, pp.2412--2416, 2020.
  • Spectrograms Fusion with Minimum Difference Masks Estimation for Monaural Speech Dereverberation.  [PDF] [.bib]
    Hao Shi, Longbiao Wang, Meng Ge, Sheng Li, and Jianwu Dang.
    In Proc. ICASSP, pp.7539--7543, 2020.
  • Environment-Dependent Attention-Driven Recurrent Convolutional Neural Network for Robust Speech Enhancement.  [PDF] [.bib]
    Meng Ge, Longbiao Wang, Nan Li, Hao Shi, Jianwu Dang, and Xiangang Li.
    In Proc. INTERSPEECH, pp.3151--3157, 2019.

    • Last updated on 2024-02-06