Advancing Momentum Pseudo-Labeling with Conformer and Initialization
Strategy

Advancing Momentum Pseudo-Labeling with Conformer and Initialization Strategy

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021

11 October 2021

Jonathan Le Roux

ArXiv (abs)PDF HTML

Papers citing "Advancing Momentum Pseudo-Labeling with Conformer and Initialization Strategy"

6 / 6 papers shown

Title
Continuous Soft Pseudo-Labeling in ASR Tatiana Likhomanenko R. Collobert Navdeep Jaitly Samy Bengio VLM 213 5 0 11 Nov 2022
InterMPL: Momentum Pseudo-Labeling with Intermediate CTC LossIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022 Yosuke Higuchi Tetsuji Ogawa Tetsunori Kobayashi Shinji Watanabe 170 1 0 02 Nov 2022
Semi-Supervised Learning Based on Reference Model for Low-resource TTSInternational Conference on Mobile Ad-hoc and Sensor Networks (MSN), 2022 Xulong Zhang Jianzong Wang Ning Cheng Jing Xiao AI4TS 92 5 0 25 Oct 2022
Continuous Pseudo-Labeling from the StartInternational Conference on Learning Representations (ICLR), 2022 Dan Berrebbi R. Collobert Samy Bengio Navdeep Jaitly Tatiana Likhomanenko 112 17 0 17 Oct 2022
Test-Time Adaptation via Conjugate Pseudo-labelsNeural Information Processing Systems (NeurIPS), 2022 Sachin Goyal Mingjie Sun Aditi Raghunathan Zico Kolter OOD 165 123 0 20 Jul 2022
Xception: Deep Learning with Depthwise Separable ConvolutionsComputer Vision and Pattern Recognition (CVPR), 2016 François Chollet MDE BDL PINN 2.3K 16,214 0 07 Oct 2016