Estimating confidence scores on ASR results using recurrent neural networks
Kaustubh Kalgaonkar, Chaojun Liu, Yifan Gong, Kaisheng Yao
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.
BibTeX
@inproceedings{icassp2015_estimatingconfid,
title = {Estimating confidence scores on ASR results using recurrent neural networks},
author = {Kaustubh Kalgaonkar and Chaojun Liu and Yifan Gong and Kaisheng Yao},
booktitle = {ICASSP 2015},
year = {2015}
}