Alternative Pseudo-labeling For Semi-supervised Automatic Speech Recognition

Abstract

When labeled data is insufficient, semi-supervised learning with the pseudo-labeling technique can significantly improve the performance of automatic speech recognition. However, pseudo-labels are often noisy, containing numerous incorrect tokens. Taking noisy labels as ground-truth in the loss function results in suboptimal performance. Previous works attempted to mitigate this issue by either filtering out the nosiest pseudo-labels or improving the overall quality of pseudo-labels. While these methods are effective to some extent, it is unrealistic to entirely eliminate incorrect tokens in pseudo-labels. In this work, we propose a novel framework named alternative pseudo-labeling to tackle the issue of noisy pseudo-labels from the perspective of the training objective. The framework comprises several components. Firstly, a generalized CTC loss function is introduced to handle noisy pseudo-labels by accepting alternative tokens in the positions of incorrect tokens. Applying this loss

Stats

• citations24
• S2 citations—
• github stars0
• HF likes0
• heat score10.48
• arxiv keyzhu2023alternative

Related papers

• Joint Speech Transcription And Translation: Pseudo-labeling With Out-of-distribution Data (2022)0.00
• Improving Pseudo-label Training For End-to-end Speech Recognition Using Gradient Mask (2021)5.84
• Softctc -- Semi-supervised Learning For Text Recognition Using Soft Pseudo-labels (2022)5.24
• Intermpl: Momentum Pseudo-labeling With Intermediate CTC Loss (2022)0.00
• Slimipl: Language-model-free Iterative Pseudo-labeling (2020)10.74
• Boosting Active Learning For Speech Recognition With Noisy Pseudo-labeled Samples (2020)0.00
• Pseudo Labeling And Negative Feedback Learning For Large-scale Multi-label Domain Classification (2020)5.24
• Censer: Curriculum Semi-supervised Learning For Speech Recognition Based On Self-supervised Pre-training (2022)4.52