Boosting Active Learning for Speech Recognition with Noisy Pseudo-labeled Samples
arXiv:2006.11021
Abstract
The cost of annotating transcriptions for large speech corpora becomes a bottleneck to maximally enjoy the potential capacity of deep neural network-based automatic speech recognition models. In this paper, we present a new training pipeline boosting the conventional active learning approach targeting label-efficient learning to resolve the mentioned problem. Existing active learning methods only focus on selecting a set of informative samples under a labeling budget. One step further, we suggest that the training efficiency can be further improved by utilizing the unlabeled samples, exceeding the labeling budget, by introducing sophisticatedly configured unsupervised loss complementing supervised loss effectively. We propose new unsupervised loss based on consistency regularization, and we configure appropriate augmentation techniques for utterances to adopt consistency regularization in the automatic speech recognition task. From the qualitative and quantitative experiments on the real-world dataset and under real-usage scenarios, we show that the proposed training pipeline can boost the efficacy of active learning approaches, thus successfully reducing a sustainable amount of human labeling cost.
arXiv comment8 pages, 4 figures, 2 tables
References in corpus (17)
- Sequence to Sequence Learning with Neural Networks
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
- Improved Regularization of Convolutional Neural Networks with Cutout
- FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
- Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
- Attention-Based Models for Speech Recognition
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
- Temporal Ensembling for Semi-Supervised Learning
- Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
- ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring
- End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures
- NSML: Meet the MLaaS platform with a real-world case study
- NSML: A Machine Learning Platform That Enables You to Focus on Your Models
- Active Learning for Speech Recognition: the Power of Gradients
- Semi-supervised ASR by End-to-end Self-training
- ClovaCall: Korean Goal-Oriented Dialog Speech Corpus for Automatic Speech Recognition of Contact Centers