Single-channel speech enhancement using inter-component phase relations

Siarhei Y. Barysenka, Vasili I. Vorobiov, Pejman Mowlaee

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Phase-aware processing has recently attracted lots of interest among researchers in speech signal processing field as successful results have been reported for various applications including automatic speech/speaker recognition, noise reduction, anti-spoofing and speech synthesis. In all these applications, the success of the applied phase-aware processing method is predominantly affected by the robustness and the accuracy of the provided estimate of the clean spectral phase to be obtained from noisy observation. Therefore, in this paper, we first consider the inter-component phase relations of poly-harmonic signals as speech captured by Phase Invariance, Phase Quasi-Invariance and Bi-Phase constraints. Then, relying on these constraints between harmonics as phase structure, we propose phase estimators. Throughout various experiments we demonstrate the usefulness of the newly proposed methods. We further report the achievable speech enhancement performance by the proposed phase estimators and compare them with the benchmark methods in terms of perceived quality, speech intelligibility and phase estimation accuracy. The proposed methods show improved performance averaged over different noise scenarios and signal-to-noise ratios.

Original languageEnglish
Pages (from-to)144-160
Number of pages17
JournalSpeech Communication
Volume99
DOIs
Publication statusPublished - 1 May 2018

Fingerprint

Speech Enhancement
Speech enhancement
Invariance
Speech intelligibility
Speech synthesis
Phase structure
Processing
Noise abatement
Speech recognition
Signal to noise ratio
Signal processing
Experiments
performance
Enhancement
Harmonic
Quasi-invariance
Speech Intelligibility
Estimator
Speech Processing
Speaker Recognition

Keywords

  • Bi-phase
  • Phase estimation
  • Phase invariance
  • Speech enhancement
  • Speech intelligibility
  • Speech quality

ASJC Scopus subject areas

  • Software
  • Modelling and Simulation
  • Communication
  • Language and Linguistics
  • Linguistics and Language
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Cite this

Single-channel speech enhancement using inter-component phase relations. / Barysenka, Siarhei Y.; Vorobiov, Vasili I.; Mowlaee, Pejman.

In: Speech Communication, Vol. 99, 01.05.2018, p. 144-160.

Research output: Contribution to journalArticleResearchpeer-review

Barysenka, Siarhei Y. ; Vorobiov, Vasili I. ; Mowlaee, Pejman. / Single-channel speech enhancement using inter-component phase relations. In: Speech Communication. 2018 ; Vol. 99. pp. 144-160.
@article{16e1216da62c457394045b6b4dbd930b,
title = "Single-channel speech enhancement using inter-component phase relations",
abstract = "Phase-aware processing has recently attracted lots of interest among researchers in speech signal processing field as successful results have been reported for various applications including automatic speech/speaker recognition, noise reduction, anti-spoofing and speech synthesis. In all these applications, the success of the applied phase-aware processing method is predominantly affected by the robustness and the accuracy of the provided estimate of the clean spectral phase to be obtained from noisy observation. Therefore, in this paper, we first consider the inter-component phase relations of poly-harmonic signals as speech captured by Phase Invariance, Phase Quasi-Invariance and Bi-Phase constraints. Then, relying on these constraints between harmonics as phase structure, we propose phase estimators. Throughout various experiments we demonstrate the usefulness of the newly proposed methods. We further report the achievable speech enhancement performance by the proposed phase estimators and compare them with the benchmark methods in terms of perceived quality, speech intelligibility and phase estimation accuracy. The proposed methods show improved performance averaged over different noise scenarios and signal-to-noise ratios.",
keywords = "Bi-phase, Phase estimation, Phase invariance, Speech enhancement, Speech intelligibility, Speech quality",
author = "Barysenka, {Siarhei Y.} and Vorobiov, {Vasili I.} and Pejman Mowlaee",
year = "2018",
month = "5",
day = "1",
doi = "10.1016/j.specom.2018.03.009",
language = "English",
volume = "99",
pages = "144--160",
journal = "Speech Communication",
issn = "0167-6393",
publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Single-channel speech enhancement using inter-component phase relations

AU - Barysenka, Siarhei Y.

AU - Vorobiov, Vasili I.

AU - Mowlaee, Pejman

PY - 2018/5/1

Y1 - 2018/5/1

N2 - Phase-aware processing has recently attracted lots of interest among researchers in speech signal processing field as successful results have been reported for various applications including automatic speech/speaker recognition, noise reduction, anti-spoofing and speech synthesis. In all these applications, the success of the applied phase-aware processing method is predominantly affected by the robustness and the accuracy of the provided estimate of the clean spectral phase to be obtained from noisy observation. Therefore, in this paper, we first consider the inter-component phase relations of poly-harmonic signals as speech captured by Phase Invariance, Phase Quasi-Invariance and Bi-Phase constraints. Then, relying on these constraints between harmonics as phase structure, we propose phase estimators. Throughout various experiments we demonstrate the usefulness of the newly proposed methods. We further report the achievable speech enhancement performance by the proposed phase estimators and compare them with the benchmark methods in terms of perceived quality, speech intelligibility and phase estimation accuracy. The proposed methods show improved performance averaged over different noise scenarios and signal-to-noise ratios.

AB - Phase-aware processing has recently attracted lots of interest among researchers in speech signal processing field as successful results have been reported for various applications including automatic speech/speaker recognition, noise reduction, anti-spoofing and speech synthesis. In all these applications, the success of the applied phase-aware processing method is predominantly affected by the robustness and the accuracy of the provided estimate of the clean spectral phase to be obtained from noisy observation. Therefore, in this paper, we first consider the inter-component phase relations of poly-harmonic signals as speech captured by Phase Invariance, Phase Quasi-Invariance and Bi-Phase constraints. Then, relying on these constraints between harmonics as phase structure, we propose phase estimators. Throughout various experiments we demonstrate the usefulness of the newly proposed methods. We further report the achievable speech enhancement performance by the proposed phase estimators and compare them with the benchmark methods in terms of perceived quality, speech intelligibility and phase estimation accuracy. The proposed methods show improved performance averaged over different noise scenarios and signal-to-noise ratios.

KW - Bi-phase

KW - Phase estimation

KW - Phase invariance

KW - Speech enhancement

KW - Speech intelligibility

KW - Speech quality

UR - http://www.scopus.com/inward/record.url?scp=85044596552&partnerID=8YFLogxK

U2 - 10.1016/j.specom.2018.03.009

DO - 10.1016/j.specom.2018.03.009

M3 - Article

VL - 99

SP - 144

EP - 160

JO - Speech Communication

JF - Speech Communication

SN - 0167-6393

ER -