Unsupervised Uncertainty Measures of Automatic Speech Recognition for Non-intrusive Speech Intelligibility Prediction

04/08/2022
by   Zehai Tu, et al.
0

Non-intrusive intelligibility prediction is important for its application in realistic scenarios, where a clean reference signal is difficult to access. The construction of many non-intrusive predictors require either ground truth intelligibility labels or clean reference signals for supervised learning. In this work, we leverage an unsupervised uncertainty estimation method for predicting speech intelligibility, which does not require intelligibility labels or reference signals to train the predictor. Our experiments demonstrate that the uncertainty from state-of-the-art end-to-end automatic speech recognition (ASR) models is highly correlated with speech intelligibility. The proposed method is evaluated on two databases and the results show that the unsupervised uncertainty measures of ASR models are more correlated with speech intelligibility from listening results than the predictions made by widely used intrusive methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/08/2022

Exploiting Hidden Representations from a DNN-based Speech Recogniser for Speech Intelligibility Prediction in Hearing-impaired Listeners

An accurate objective speech intelligibility prediction algorithms is of...
research
08/13/2019

End-to-End Multi-Speaker Speech Recognition using Speaker Embeddings and Transfer Learning

This paper presents our latest investigation on end-to-end automatic spe...
research
11/24/2021

Non-Intrusive Binaural Speech Intelligibility Prediction from Discrete Latent Representations

Non-intrusive speech intelligibility (SI) prediction from binaural signa...
research
04/09/2019

Performance Monitoring for End-to-End Speech Recognition

Measuring performance of an automatic speech recognition (ASR) system wi...
research
03/17/2022

Prediction of speech intelligibility with DNN-based performance measures

This paper presents a speech intelligibility model based on automatic sp...
research
01/14/2021

WER-BERT: Automatic WER Estimation with BERT in a Balanced Ordinal Classification Paradigm

Automatic Speech Recognition (ASR) systems are evaluated using Word Erro...
research
09/06/2020

Non causal deep learning based dereverberation

In this paper we demonstrate the effectiveness of non-causal context for...

Please sign up or login with your details

Forgot password? Click here to reset