Phase estimation in single-channel speech enhancement using phase invariance constraints

Michael Pirolt, Johannes Stahl, Pejman Mowlaee Beikzadehmahaleh, Vasili I. Vorobiov , Siarhei Y. Barysenka , Andrew G. Davydov

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

Abstract

Phase-aware signal processing has received increasing interest in many speech applications. The success of phase-aware processing depends strongly on the robustness of the clean spectral phase estimates to be obtained from a noisy observation. In this paper, we propose a novel harmonic phase estimator relying on the phase invariance property exploiting relations between harmonics using the phase structure. We present speech quality results achieved in speech enhancement to justify the effectiveness of the proposed phase estimator compared to noisy phase and other phase estimation benchmarks.
Original languageEnglish
Title of host publicationICASSP 2017
DOIs
Publication statusPublished - 19 Jun 2017
Event2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - New Orleans, United States
Duration: 5 Mar 20179 Mar 2017

Conference

Conference2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017
CountryUnited States
CityNew Orleans
Period5/03/179/03/17

Fingerprint

Speech enhancement
Invariance
Phase structure
Signal processing
Processing

Fields of Expertise

  • Information, Communication & Computing

Cite this

Phase estimation in single-channel speech enhancement using phase invariance constraints. / Pirolt, Michael; Stahl, Johannes; Mowlaee Beikzadehmahaleh, Pejman; Vorobiov , Vasili I. ; Barysenka , Siarhei Y. ; Davydov, Andrew G. .

ICASSP 2017. 2017.

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

Pirolt, M, Stahl, J, Mowlaee Beikzadehmahaleh, P, Vorobiov , VI, Barysenka , SY & Davydov, AG 2017, Phase estimation in single-channel speech enhancement using phase invariance constraints. in ICASSP 2017. 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017, New Orleans, United States, 5/03/17. https://doi.org/10.1109/ICASSP.2017.7953225
Pirolt, Michael ; Stahl, Johannes ; Mowlaee Beikzadehmahaleh, Pejman ; Vorobiov , Vasili I. ; Barysenka , Siarhei Y. ; Davydov, Andrew G. . / Phase estimation in single-channel speech enhancement using phase invariance constraints. ICASSP 2017. 2017.
@inproceedings{2f040dba0b2249529ccb53265a23c4f6,
title = "Phase estimation in single-channel speech enhancement using phase invariance constraints",
abstract = "Phase-aware signal processing has received increasing interest in many speech applications. The success of phase-aware processing depends strongly on the robustness of the clean spectral phase estimates to be obtained from a noisy observation. In this paper, we propose a novel harmonic phase estimator relying on the phase invariance property exploiting relations between harmonics using the phase structure. We present speech quality results achieved in speech enhancement to justify the effectiveness of the proposed phase estimator compared to noisy phase and other phase estimation benchmarks.",
author = "Michael Pirolt and Johannes Stahl and {Mowlaee Beikzadehmahaleh}, Pejman and Vorobiov, {Vasili I.} and Barysenka, {Siarhei Y.} and Davydov, {Andrew G.}",
year = "2017",
month = "6",
day = "19",
doi = "10.1109/ICASSP.2017.7953225",
language = "English",
booktitle = "ICASSP 2017",

}

TY - GEN

T1 - Phase estimation in single-channel speech enhancement using phase invariance constraints

AU - Pirolt, Michael

AU - Stahl, Johannes

AU - Mowlaee Beikzadehmahaleh, Pejman

AU - Vorobiov , Vasili I.

AU - Barysenka , Siarhei Y.

AU - Davydov, Andrew G.

PY - 2017/6/19

Y1 - 2017/6/19

N2 - Phase-aware signal processing has received increasing interest in many speech applications. The success of phase-aware processing depends strongly on the robustness of the clean spectral phase estimates to be obtained from a noisy observation. In this paper, we propose a novel harmonic phase estimator relying on the phase invariance property exploiting relations between harmonics using the phase structure. We present speech quality results achieved in speech enhancement to justify the effectiveness of the proposed phase estimator compared to noisy phase and other phase estimation benchmarks.

AB - Phase-aware signal processing has received increasing interest in many speech applications. The success of phase-aware processing depends strongly on the robustness of the clean spectral phase estimates to be obtained from a noisy observation. In this paper, we propose a novel harmonic phase estimator relying on the phase invariance property exploiting relations between harmonics using the phase structure. We present speech quality results achieved in speech enhancement to justify the effectiveness of the proposed phase estimator compared to noisy phase and other phase estimation benchmarks.

U2 - 10.1109/ICASSP.2017.7953225

DO - 10.1109/ICASSP.2017.7953225

M3 - Conference contribution

BT - ICASSP 2017

ER -