Skip to main content

A_TAYLOR_STYLE_NEURAL_NETWORK_IN_FULLBAND_ECHO_CANCELLATION

Xu Weiming (Northwest Polytechnic University); Guo Zhihao (elevoc)

DOI
10.17023/sqm0-r356
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
10 Jun 2023

This paper describes aecX's entry in the ICASSP 2023 (4th) acoustic echo cancellation (AEC) challenge. The proposed method consists of an adaptive filter and a full-band Taylor-style acoustic echo cancellation neural network (TaylorAECNet) as a post-filter. Our proposed method achieves an overall mean opinion score (MOS) of 4.241, a word accuracy (WAcc) ratio of 0.767, and ranks 5th in the non-personalized track (track 1).

Tags:
Signal Processing for Communications and Networking

More Like This

Half-temporal and half-frequency attention U2Net for speech signal improvement
10 Jun 2023

Half-temporal and half-frequency attention U2Net for speech signal improvement

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
THE NERCSLIP-USTC SYSTEM FOR THE L3DAS23 CHALLENGE TASK2: 3D SOUND EVENT LOCALIZATION AND DETECTION (SELD)
10 Jun 2023

THE NERCSLIP-USTC SYSTEM FOR THE L3DAS23 CHALLENGE TASK2: 3D SOUND EVENT LOCALIZATION AND DETECTION (SELD)

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
A Study on the Integration of Pipeline and E2E SLU systems for Spoken Semantic Parsing toward STOP Quality Challenge
10 Jun 2023

A Study on the Integration of Pipeline and E2E SLU systems for Spoken Semantic Parsing toward STOP Quality Challenge

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00