On Non-Reference Speech Intelligibility Estimation Using DNN De-reverberation

Reverberation distorts speech leading to degradation of speech intelligibility and speech quality. We have been investigating methods to predict speech intelligibility without clean speech which are more difficult than prediction with actual clean speech. In this paper, we attempt to estimate speech...

Full description

Saved in:
Bibliographic Details
Published in2020 IEEE 9th Global Conference on Consumer Electronics (GCCE) pp. 721 - 722
Main Authors Nakazawa, Kazushi, Kondo, Kazuhiro
Format Conference Proceeding
LanguageEnglish
Published IEEE 13.10.2020
Subjects
Conferences
Consumer electronics
Correlation
De-reverberation
Deep neural networks
Degradation
Estimation
Neural networks
Reverberation
Speech intelligibility
Online AccessGet full text

Cover

More Information
Summary:Reverberation distorts speech leading to degradation of speech intelligibility and speech quality. We have been investigating methods to predict speech intelligibility without clean speech which are more difficult than prediction with actual clean speech. In this paper, we attempt to estimate speech intelligibility by simulating the full-reference (F-R) method, substituting the predicted clean speech with clean speech. The correlation between the predicted and measured intelligibility was 0.99945 and the RMSE was 0.00353 with the proposed method.
DOI:10.1109/GCCE50665.2020.9292054