Objective Metrics to Evaluate Residual-Echo Suppression during Double-Talk

Amir Ivry, Israel Cohen, Baruch Berdugo

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

5 Scopus citations

Abstract

Human subjective evaluation is optimal to assess speech quality for human perception. The recently introduced deep noise suppression mean opinion score (DNSMOS) metric was shown to estimate human ratings with great accuracy. The signal-to-distortion ratio (SDR) metric is widely used to evaluate residual-echo suppression (RES) systems by estimating speech quality during double-talk. However, since the SDR is affected by both speech distortion and residual-echo presence, it does not correlate well with human ratings according to the DNSMOS. To address that, we introduce two objective metrics to separately quantify the desired-speech maintained level (DSML) and residual-echo suppression level (RESL) during double-talk. These metrics are evaluated using a deep learning-based RES-system with a tunable design parameter. Using 280 hours of real and simulated recordings, we show that the DSML and RESL correlate well with the DNSMOS with high generalization to various setups. Also, we empirically investigate the relation between tuning the RES-system design parameter and the DSML-RESL tradeoff it creates and offer a practical design scheme for dynamic system requirements.

Original languageEnglish
Title of host publication2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages101-105
Number of pages5
ISBN (Electronic)9781665448703
DOIs
StatePublished - 2021
Externally publishedYes
Event2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2021 - New Paltz, United States
Duration: 17 Oct 202120 Oct 2021

Publication series

NameIEEE Workshop on Applications of Signal Processing to Audio and Acoustics
Volume2021-October
ISSN (Print)1931-1168
ISSN (Electronic)1947-1629

Conference

Conference2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2021
Country/TerritoryUnited States
CityNew Paltz
Period17/10/2120/10/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Keywords

  • Residual-echo suppression
  • deep learning
  • echo cancellation
  • objective metrics
  • perceptual speech quality

Fingerprint

Dive into the research topics of 'Objective Metrics to Evaluate Residual-Echo Suppression during Double-Talk'. Together they form a unique fingerprint.

Cite this