论文信息 - De’hubert: Disentangling Noise in a Self-Supervised Model for Robust Speech Recognition - 字舞流文

De’hubert: Disentangling Noise in a Self-Supervised Model for Robust Speech Recognition

E. Chng | Chongjia Ni | Dianwen Ng | Bin Ma | Jinjie Ni | Jia Qi Yip | Yukun Ma | Ruixiu Zhang | Zhao Yang | Chong Zhang

[1] Qun Liu,et al. SPIRAL: Self-supervised Perturbation-Invariant Representation Learning for Speech Pre-Training , 2022, ICLR.

[2] Juan Pino,et al. XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale , 2021, INTERSPEECH.

[3] Yann LeCun,et al. Barlow Twins: Self-Supervised Learning via Redundancy Reduction , 2021, ICML.

[4] Abdel-rahman Mohamed,et al. wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations , 2020, NeurIPS.

[5] Oriol Vinyals,et al. Representation Learning with Contrastive Predictive Coding , 2018, ArXiv.

[6] Yannick Estève,et al. TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation , 2018, SPECOM.

[7] Xavier Serra,et al. Freesound technical demo , 2013, ACM Multimedia.

[8] Aapo Hyvärinen,et al. Noise-contrastive estimation: A new estimation principle for unnormalized statistical models , 2010, AISTATS.