Blind estimation of reverberation time using binaural complex ideal ratio mask

Ming Yang Chai, Tiantian Li, Mengyao Zhu, Tao Wang, Wen Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

Accurate estimation of reverberation time T60 proved to have a positive effect on the automatic speech recognition (ASR) used in the voice-controlled devices and the reconstruction of the acoustic field. Recently, researchers have proposed some algorithms to estimate T60. However, few of them directly use the spatial information about the acoustic environment contained in the speech for accurate T60 estimation. We propose a deep learning approach as a regression problem to use binaural reverberant speech generated by the clean speech convolved with simulated Room Impulse Response (RIR) to estimate T60. Adaptive cIRM estimator firstly estimates the complex Ideal Ratio Mask (cIRM), which is strongly correlated with T60, and then a CNN-based T60 estimator is used to estimate T60 with cIRM. The experimental results show that our proposed approach outperforms the state-of-the-art method of T60 estimation.

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages378-383
Number of pages6
ISBN (Electronic)9781538692141
DOIs
StatePublished - Jul 2019
Event2019 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2019 - Shanghai, China
Duration: 8 Jul 201912 Jul 2019

Publication series

NameProceedings - 2019 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2019

Conference

Conference2019 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2019
Country/TerritoryChina
CityShanghai
Period8/07/1912/07/19

Keywords

  • cIRM
  • Deep learning
  • Reverberation time

Fingerprint

Dive into the research topics of 'Blind estimation of reverberation time using binaural complex ideal ratio mask'. Together they form a unique fingerprint.

Cite this