Active learning: theory and applications to automatic speech recognition

  • Riccardi G
  • Hakkani-Tur D
  • 31

    Readers

    Mendeley users who have this article in their library.
  • N/A

    Citations

    Citations of this article.

Abstract

We are interested in the problem of adaptive learning in the context of automatic speech recognition (ASR). In this paper, we propose an active learning algorithm for ASR. Automatic speech recognition systems are trained using human supervision to provide transcriptions of speech utterances. The goal of Active Learning is to minimize the human supervision for training acoustic and language models and to maximize the performance given the transcribed and untranscribed data. Active learning aims at reducing the number of training examples to be labeled by automatically processing the unlabeled examples, and then selecting the most informative ones with respect to a given cost function for a human to label. In this paper we describe how to estimate the confidence score for each utterance through an on-line algorithm using the lattice output of a speech recognizer. The utterance scores are filtered through the informativeness function and an optimal subset of training samples is selected. The active learning algorithm has been applied to both batch and on-line learning scheme and we have experimented with different selective sampling algorithms. Our experiments show that by using active learning the amount of labeled data needed for a given word accuracy can be reduced by more than 60% with respect to random sampling.

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Authors

  • G. Riccardi

  • D. Hakkani-Tur

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free