On Modeling ASR Word Confidence

07/22/2019
by   Woojay Jeon, et al.
0

We present a new method for computing ASR word confidences that effectively mitigates ASR errors for diverse downstream applications, improves the word error rate of the 1-best result, and allows better comparison of scores across different models. We propose 1) a new method for modeling word confidence using a Heterogeneous Word Confusion Network (HWCN) that addresses some key flaws in conventional Word Confusion Networks, and 2) a new score calibration method for facilitating direct comparison of scores from different models. Using a bidirectional lattice recurrent neural network to compute the confidence scores of each word in the HWCN, we show that the word sequence with the best overall confidence is more accurate than the default 1-best result of the recognizer, and that the calibration method greatly improves the reliability of recognizer combination.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/30/2018

Bi-Directional Lattice Recurrent Neural Networks for Confidence Estimation

The standard approach to mitigate errors made by an automatic speech rec...
research
06/30/2021

Sequence-level Confidence Classifier for ASR Utterance Accuracy and Application to Acoustic Models

Scores from traditional confidence classifiers (CCs) in automatic speech...
research
04/26/2021

Multi-Task Learning for End-to-End ASR Word and Utterance Confidence with Deletion Prediction

Confidence scores are very useful for downstream applications of automat...
research
06/07/2023

Lenient Evaluation of Japanese Speech Recognition: Modeling Naturally Occurring Spelling Inconsistency

Word error rate (WER) and character error rate (CER) are standard metric...
research
10/30/2018

Confidence Estimation and Deletion Prediction Using Bidirectional Recurrent Neural Networks

The standard approach to assess reliability of automatic speech transcri...
research
10/25/2019

Confidence Estimation for Black Box Automatic Speech Recognition Systems Using Lattice Recurrent Neural Networks

Recently, there has been growth in providers of speech transcription ser...
research
07/19/2018

Improving Simple Models with Confidence Profiles

In this paper, we propose a new method called ProfWeight for transferrin...

Please sign up or login with your details

Forgot password? Click here to reset