 InterMPL: Momentum Pseudo-Labeling with Intermediate CTC LossIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022 |
 BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning
for Automatic Speech RecognitionIEEE Journal on Selected Topics in Signal Processing (JSTSP), 2021 |
 Kaizen: Continuously improving teacher using Exponential Moving Average
for semi-supervised speech recognitionAutomatic Speech Recognition & Understanding (ASRU), 2021 |
 HuBERT: Self-Supervised Speech Representation Learning by Masked
Prediction of Hidden UnitsIEEE/ACM Transactions on Audio Speech and Language Processing (TASLP), 2021 |
 Unsupervised Speech RecognitionNeural Information Processing Systems (NeurIPS), 2021 |
 EAT: Enhanced ASR-TTS for Self-supervised Speech RecognitionIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021 |
 Unsupervised Domain Adaptation for Speech Recognition via Uncertainty
Driven Self-TrainingIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020 |
 Joint Masked CPC and CTC Training for ASRIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020 |
 Semi-Supervised Speech Recognition via Graph-based Temporal
ClassificationIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020 |
