paper-with-me

홈 › Papers

Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition

2021-06-16 · Yosuke Higuchi, Niko Moritz, Jonathan Le Roux, Takaaki Hori

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. While PL can be further improved by iteratively updating pseudo-labels as the model evolves, most of the previous approaches involve inefficient retraining of the model or intricate control of the label update. 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. The online model is trained to predict pseudo-labels generated on the fly by the offline model. The offline model maintains a momentum-based moving average of the online model. MPL is performed in a single training process and the interaction between the two models effectively helps them reinforce each other to improve the ASR performance. We apply MPL to an end-to-end ASR model based on the connectionist temporal classification. The experimental results demonstrate that MPL effectively improves over the base model and is scalable to different semi-supervised scenarios with varying amounts of data or domain mismatch.

📄 PDF Abstract BibTeX arXiv:2106.08922

Code (1)

robflynnyh/Self-Train-Before-You-Transcribe pytorch

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Advancing Momentum Pseudo-Labeling with Conformer and Initialization Strategy

2021-10-11 · Yosuke Higuchi, Niko Moritz, Jonathan Le Roux, Takaaki Hori

Pseudo-labeling (PL), a semi-supervised learning (SSL) method where a seed model performs self-training using pseudo-labels generated from untranscribed speech, has been shown to enhance the performance of end-to-end aut…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language Modellingspeech-recognition+1

InterMPL: Momentum Pseudo-Labeling with Intermediate CTC Loss

2022-11-02 · Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi, Shinji Watanabe

This paper presents InterMPL, a semi-supervised learning method of end-to-end automatic speech recognition (ASR) that performs pseudo-labeling (PL) with intermediate supervision. Momentum PL (MPL) trains a connectionist …

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Decoderspeech-recognition+1

Pseudo-Labeling for Massively Multilingual Speech Recognition

2021-10-30 · Loren Lugosch, Tatiana Likhomanenko, Gabriel Synnaeve, Ronan Collobert

Semi-supervised learning through pseudo-labeling has become a staple of state-of-the-art monolingual speech recognition systems. In this work, we extend pseudo-labeling to massively multilingual speech recognition with 6…

speech-recognitionSpeech Recognition

Online pseudo labeling for polyp segmentation with momentum networks

2022-09-29 · Toan Pham Van, Linh Bao Doan, Thanh Tung Nguyen, Duc Trung Tran 외

Semantic segmentation is an essential task in developing medical image diagnosis systems. However, building an annotated medical dataset is expensive. Thus, semi-supervised methods are significant in this circumstance. I…

Semantic Segmentation

Iterative Pseudo-Labeling for Speech Recognition

2020-05-19 · Qiantong Xu, Tatiana Likhomanenko, Jacob Kahn, Awni Hannun 외

Pseudo-labeling has recently shown promise in end-to-end automatic speech recognition (ASR). We study Iterative Pseudo-Labeling (IPL), a semi-supervised algorithm which efficiently performs multiple iterations of pseudo-…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data AugmentationLanguage Modeling+3