• Welcome to Bio-ASP Lab ~

Dataset

Speech Corpus

  • Yu-Wen Chen

VoiceBank-SLR

  • Szu-Wei Fu, Cheng Yu, Kuo-Hsuan Hung, Mirco Ravanelli, Yu Tsao
Please cite the paper if you find this dataset useful in your research.

Citation


@article{fu2021metricganu,
 title={METRICGAN-U: UNSUPERVISED SPEECH ENHANCEMENT/ DEREVERBERATION BASED
    ONLY ON NOISY/ REVERBERATED SPEECH},
 author={Szu-Wei Fu, Cheng Yu, Kuo-Hsuan Hung, Mirco Ravanelli, and Yu Tsao},
 journal={arXiv preprint arXiv:2110.05866},
 year={2021}
}

TMSV (Taiwan Mandarin speech with video)

  • Shang-Yi Chuang & Chen-Chou Lo
Please cite the paper iLAVSE if you find this dataset useful in your research.

Citation


@article{chuang2020improved,
 title={Improved Lite Audio-Visual Speech Enhancement},
 author={Chuang, Shang-Yi and Wang, Hsin-Min and Tsao, Yu},
 journal={arXiv preprint arXiv:2008.13222},
 year={2020}
}