Supervised graph-based processing for sequential transient interference suppression

Ronen Talmon; Israel Cohen; Sharon Gannot; Ronald R. Coifman

doi:10.1109/tasl.2012.2205243

Supervised graph-based processing for sequential transient interference suppression

Ronen Talmon, Israel Cohen, Sharon Gannot, Ronald R. Coifman

Bar-Ilan University - The Alexander Kofkin Faculty of Engineering

Research output: Contribution to journal › Article › peer-review

27 Scopus citations

Abstract

In this paper, we present a supervised graph-based framework for sequential processing and employ it to the problem of transient interference suppression. Transients typically consist of an initial peak followed by decaying short-duration oscillations. Such sounds, e.g., keyboard typing and door knocking, often arise as an interference in everyday applications: hearing aids, hands-free accessories, mobile phones, and conference-room devices. We describe a graph construction using a noisy speech signal and training recordings of typical transients. The main idea is to capture the transient interference structure, which may emerge from the construction of the graph. The graph parametrization is then viewed as a data-driven model of the transients and utilized to define a filter that extracts the transients from noisy speech measurements. Unlike previous transient interference suppression studies, in this work the graph is constructed in advance from training recordings. Then, the graph is extended to newly acquired measurements, providing a sequential filtering framework of noisy speech.

Original language	English
Article number	6220851
Pages (from-to)	2528-2538
Number of pages	11
Journal	IEEE Transactions on Audio, Speech and Language Processing
Volume	20
Issue number	9
DOIs	https://doi.org/10.1109/tasl.2012.2205243
State	Published - 2012

Bibliographical note

Funding Information:
Manuscript received January 09, 2012; revised April 21, 2012; accepted May 31, 2012. Date of publication June 19, 2012; date of current version August 24, 2012. The work of R. Talmon and I. Cohen work was supported by the Israel Science Foundation under Grant 1130/11. The work of R. Talmon was supported in part by the Viterbi Fellowship, Technion. The work of R. Coifman work was supported by DARPA and the SPAWAR System Center Pacific under Contract N66001-11-C-4092. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Emmanuel Vincent.

Keywords

Acoustic noise
graph filtering
speech enhancement
speech processing
transient noise

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/tasl.2012.2205243

Cite this

@article{8d0358e766e44179ae1c4f0f53ebe660,

title = "Supervised graph-based processing for sequential transient interference suppression",

abstract = "In this paper, we present a supervised graph-based framework for sequential processing and employ it to the problem of transient interference suppression. Transients typically consist of an initial peak followed by decaying short-duration oscillations. Such sounds, e.g., keyboard typing and door knocking, often arise as an interference in everyday applications: hearing aids, hands-free accessories, mobile phones, and conference-room devices. We describe a graph construction using a noisy speech signal and training recordings of typical transients. The main idea is to capture the transient interference structure, which may emerge from the construction of the graph. The graph parametrization is then viewed as a data-driven model of the transients and utilized to define a filter that extracts the transients from noisy speech measurements. Unlike previous transient interference suppression studies, in this work the graph is constructed in advance from training recordings. Then, the graph is extended to newly acquired measurements, providing a sequential filtering framework of noisy speech.",

keywords = "Acoustic noise, graph filtering, speech enhancement, speech processing, transient noise",

author = "Ronen Talmon and Israel Cohen and Sharon Gannot and Coifman, {Ronald R.}",

note = "Funding Information: Manuscript received January 09, 2012; revised April 21, 2012; accepted May 31, 2012. Date of publication June 19, 2012; date of current version August 24, 2012. The work of R. Talmon and I. Cohen work was supported by the Israel Science Foundation under Grant 1130/11. The work of R. Talmon was supported in part by the Viterbi Fellowship, Technion. The work of R. Coifman work was supported by DARPA and the SPAWAR System Center Pacific under Contract N66001-11-C-4092. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Emmanuel Vincent.",

year = "2012",

doi = "10.1109/tasl.2012.2205243",

language = "אנגלית",

volume = "20",

pages = "2528--2538",

journal = "IEEE Transactions on Audio, Speech and Language Processing",

issn = "1558-7916",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "9",

}

TY - JOUR

T1 - Supervised graph-based processing for sequential transient interference suppression

AU - Talmon, Ronen

AU - Cohen, Israel

AU - Gannot, Sharon

AU - Coifman, Ronald R.

N1 - Funding Information: Manuscript received January 09, 2012; revised April 21, 2012; accepted May 31, 2012. Date of publication June 19, 2012; date of current version August 24, 2012. The work of R. Talmon and I. Cohen work was supported by the Israel Science Foundation under Grant 1130/11. The work of R. Talmon was supported in part by the Viterbi Fellowship, Technion. The work of R. Coifman work was supported by DARPA and the SPAWAR System Center Pacific under Contract N66001-11-C-4092. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Emmanuel Vincent.

PY - 2012

Y1 - 2012

N2 - In this paper, we present a supervised graph-based framework for sequential processing and employ it to the problem of transient interference suppression. Transients typically consist of an initial peak followed by decaying short-duration oscillations. Such sounds, e.g., keyboard typing and door knocking, often arise as an interference in everyday applications: hearing aids, hands-free accessories, mobile phones, and conference-room devices. We describe a graph construction using a noisy speech signal and training recordings of typical transients. The main idea is to capture the transient interference structure, which may emerge from the construction of the graph. The graph parametrization is then viewed as a data-driven model of the transients and utilized to define a filter that extracts the transients from noisy speech measurements. Unlike previous transient interference suppression studies, in this work the graph is constructed in advance from training recordings. Then, the graph is extended to newly acquired measurements, providing a sequential filtering framework of noisy speech.

AB - In this paper, we present a supervised graph-based framework for sequential processing and employ it to the problem of transient interference suppression. Transients typically consist of an initial peak followed by decaying short-duration oscillations. Such sounds, e.g., keyboard typing and door knocking, often arise as an interference in everyday applications: hearing aids, hands-free accessories, mobile phones, and conference-room devices. We describe a graph construction using a noisy speech signal and training recordings of typical transients. The main idea is to capture the transient interference structure, which may emerge from the construction of the graph. The graph parametrization is then viewed as a data-driven model of the transients and utilized to define a filter that extracts the transients from noisy speech measurements. Unlike previous transient interference suppression studies, in this work the graph is constructed in advance from training recordings. Then, the graph is extended to newly acquired measurements, providing a sequential filtering framework of noisy speech.

KW - Acoustic noise

KW - graph filtering

KW - speech enhancement

KW - speech processing

KW - transient noise

UR - http://www.scopus.com/inward/record.url?scp=84865696193&partnerID=8YFLogxK

U2 - 10.1109/tasl.2012.2205243

DO - 10.1109/tasl.2012.2205243

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:84865696193

SN - 1558-7916

VL - 20

SP - 2528

EP - 2538

JO - IEEE Transactions on Audio, Speech and Language Processing

JF - IEEE Transactions on Audio, Speech and Language Processing

IS - 9

M1 - 6220851

ER -

Supervised graph-based processing for sequential transient interference suppression

Abstract

Bibliographical note

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this