Active learning and semi-supervised learning for speech recognition: A unified framework using the global entropy reduction maximization criterion

• Published in: Computer speech & language 2010-07, Vol.24 (3), p.433-444
• Main Authors: Yu, Dong, Varadarajan, Balakrishnan, Deng, Li, Acero, Alex
• Format: Article
• Language: English
• Subjects: Acoustic model; Active learning; Collective information; Confidence; Entropy reduction; Lattice; Semi-supervised learning
• ISSN: 0885-2308; 1095-8363
• DOI: 10.1016/j.csl.2009.03.004

We propose a unified global entropy reduction maximization (GERM) framework for active learning and semi-supervised learning for speech recognition. Active learning aims to select a limited subset of utterances for transcribing from a large amount of un-transcribed utterances, while semi-supervised learning addresses the problem of selecting right transcriptions for un-transcribed utterances, so that the accuracy of the automatic speech recognition system can be maximized. We show that both the traditional confidence-based active learning and semi-supervised learning approaches can be improved by maximizing the lattice entropy reduction over the whole dataset. We introduce our criterion and framework, show how the criterion can be simplified and approximated, and describe how these approaches can be combined. We demonstrate the effectiveness of our new framework and algorithm with directory assistance data collected under the real usage scenarios and show that our GERM based active learning and semi-supervised learning algorithms consistently outperform the confidence-based counterparts by a significant margin. Using our new active learning algorithm cuts the number of utterances needed for transcribing by 50% to achieve the same recognition accuracy obtained using the confidence-based active learning approach, and by 60% compared to the random sampling approach. Using our new semi-supervised algorithm we can determine the cutoff point in determining which utterance-transcription pair to use in a principled way by demonstrating that the point it finds is very close to the achievable peak point.