DeepAI AI Chat
Log In Sign Up

Semi-Supervised Learning with Data Augmentation for End-to-End ASR

by   Felix Weninger, et al.
Nuance Communications

In this paper, we apply Semi-Supervised Learning (SSL) along with Data Augmentation (DA) for improving the accuracy of End-to-End ASR. We focus on the consistency regularization principle, which has been successfully applied to image classification tasks, and present sequence-to-sequence (seq2seq) versions of the FixMatch and Noisy Student algorithms. Specifically, we generate the pseudo labels for the unlabeled data on-the-fly with a seq2seq model after perturbing the input features with DA. We also propose soft label variants of both algorithms to cope with pseudo label errors, showing further performance improvements. We conduct SSL experiments on a conversational speech data set with 1.9kh manually transcribed training data, using only 25 labels (475h labeled data). In the result, the Noisy Student algorithm with soft labels and consistency regularization achieves 10.4 reduction when adding 475h of unlabeled data, corresponding to a recovery rate of 92 SSL performance is within 5 training set (recovery rate: 78


page 1

page 2

page 3

page 4


Semi-Supervised Heterogeneous Graph Learning with Multi-level Data Augmentation

In recent years, semi-supervised graph learning with data augmentation (...

Semi-supervised ASR by End-to-end Self-training

While deep learning based end-to-end automatic speech recognition (ASR) ...

Continuous Soft Pseudo-Labeling in ASR

Continuous pseudo-labeling (PL) algorithms such as slimIPL have recently...

Gradient-based Data Augmentation for Semi-Supervised Learning

In semi-supervised learning (SSL), a technique called consistency regula...

Manifold Graph with Learned Prototypes for Semi-Supervised Image Classification

Recent advances in semi-supervised learning methods rely on estimating c...

Unsupervised Data Augmentation with Naive Augmentation and without Unlabeled Data

Unsupervised Data Augmentation (UDA) is a semi-supervised technique that...