Estimating confidence scores on ASR results using recurrent neural networks
Authors:
- 1 April 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 4999-5003
Abstract
In this paper we present a confidence estimation system using recurrent neural networks (RNN) and compare it to a traditional multilayered perception (MLP) based system. The ability of RNN to capture sequence information and improve decisions using processed history was main motivation to explore RNN's for confidence estimation. In this paper we also explore two subtle variations of confidence estimator: one that uses objective extracted over the entire sequence for training, and other that uses dynamic programming to decode and estimate confidence on all the words of the sequence jointly. In our experiments, we observed that for a constant false positive (FP) rate of 3% we can secure a relative reduction of 10% in false negative (FN) rate when we replaced a MLP in confidence estimator with a RNN.We also observed that relative gains achieved by a RNN based confidence estimator are directly proportional to the number of word in the utterances.Keywords
This publication has 19 references indexed in Scilit:
- Confidence measures for speech recognition: A surveySpeech Communication, 2005
- Rejection for connected digit recognition based on GPD segmental discrimination2002
- Neural-network based measures of confidence for word recognition2002
- Word-based confidence measures as a guide for stack search in speech recognition2002
- A probabilistic approach to confidence estimation and evaluation2002
- Understanding and improving speech recognition performance through the use of diagnostic tools2002
- Confidence measures for large vocabulary continuous speech recognitionIEEE Transactions on Speech and Audio Processing, 2001
- Evaluation of word confidence for speech recognition systemsComputer Speech & Language, 1999
- Vocabulary independent discriminative utterance verification for nonkeyword rejection in subword based speech recognitionIEEE Transactions on Speech and Audio Processing, 1996
- Finding structure in timeCognitive Science, 1990