PL-EESR: Perceptual Loss Based End-to-End Robust Speaker Representation Extraction

Yi Ma, Kong Aik Lee, Ville Hautamaki, Haizhou Li

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

7 Citations (Scopus)

Abstract

Speech enhancement aims to improve the perceptual quality of the speech signal by suppression of the background noise. However, excessive suppression may lead to speech distortion and speaker information loss, which degrades the performance of speaker embedding extraction. To alleviate this problem, we propose an end-to-end deep learning framework, dubbed PL-EESR, for robust speaker representation extraction. This framework is optimized based on the feedback of the speaker identification task and the high-level perceptual deviation between the raw speech signal and its noisy version. We conducted speaker verification tasks in both noisy and clean environment respectively to evaluate our system. Compared to the baseline, our method shows better performance in both clean and noisy environments, which means our method can not only enhance the speaker relative information but also avoid adding distortions.

Original languageEnglish
Title of host publication2021 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2021 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages106-113
Number of pages8
ISBN (Electronic)9781665437394
DOIs
Publication statusPublished - Dec 2021
Externally publishedYes
Event2021 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2021 - Cartagena, Colombia
Duration: 13 Dec 202117 Dec 2021

Publication series

Name2021 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2021 - Proceedings

Conference

Conference2021 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2021
Country/TerritoryColombia
CityCartagena
Period13/12/2117/12/21

Keywords

  • End-to-end training
  • Perceptual Loss
  • Speaker representation
  • Speech enhancement

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'PL-EESR: Perceptual Loss Based End-to-End Robust Speaker Representation Extraction'. Together they form a unique fingerprint.

Cite this