TR2021-103
Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition
-
- "Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition", Interspeech, DOI: 10.21437/Interspeech.2021-571, September 2021, pp. 726-730.BibTeX TR2021-103 PDF
- @inproceedings{Higuchi2021sep,
- author = {Higuchi, Yosuke and Moritz, Niko and Le Roux, Jonathan and Hori, Takaaki},
- title = {Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition},
- booktitle = {Interspeech},
- year = 2021,
- pages = {726--730},
- month = sep,
- doi = {10.21437/Interspeech.2021-571},
- url = {https://www.merl.com/publications/TR2021-103}
- }
,
- "Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition", Interspeech, DOI: 10.21437/Interspeech.2021-571, September 2021, pp. 726-730.
-
MERL Contact:
-
Research Areas:
Abstract:
Pseudo-labeling (PL) has been shown to be effective in semi-supervised automatic speech recognition (ASR), where a base model is self-trained with pseudo-labels generated from unlabeled data. We present momentum pseudo-labeling (MPL), a simple yet effective strategy for semi-supervised ASR. MPL consists of a pair of online and offline models that interact and learn from each other, inspired by the mean teacher method.