Loading…
Deep Adaptation Control for Stereophonic Acoustic Echo Cancellation
We introduce a general and data-driven adaptation-control framework for stereophonic acoustic-echo cancellation. The adaptation update rule for the filters that estimate the actual echo paths is compactly expressed with the widely-linear model in the complex time domain. A single step-size parameter...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | 5 |
| container_issue | |
| container_start_page | 1 |
| container_title | |
| container_volume | |
| creator | Ivry, Amir Cohen, Israel Berdugo, Baruch |
| description | We introduce a general and data-driven adaptation-control framework for stereophonic acoustic-echo cancellation. The adaptation update rule for the filters that estimate the actual echo paths is compactly expressed with the widely-linear model in the complex time domain. A single step-size parameter that governs the behavior of the adaptation process is optimized by minimizing the misalignment between the actual echo paths and their filtered estimate. The relation between acoustic signals and the optimal step-size is learned via a deep neural network. In test mode, the optimal step-size prediction is inferred by the network and fed to the sign-error nor-malized least mean-squares (SNLMS) adaptive filter for echo-paths tracking. Real and simulated data show advantageous performance in single and double-talk scenarios across various acoustic setups. |
| doi_str_mv | 10.1109/WASPAA58266.2023.10248161 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_10248161</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10248161</ieee_id><sourcerecordid>10248161</sourcerecordid><originalsourceid>FETCH-LOGICAL-i204t-376c027946a22d26ed4c5de5445e404030cfc077c651b36b3e7d4a72f6807f093</originalsourceid><addsrcrecordid>eNo1j81KxDAURqMgOI7zBi7iA7Te3Pw1y1DHURhQGMXlkElvmUptShsXvr3iz-o7m3PgY-xaQCkEuJtXv3vyXldoTImAshSAqhJGnLCVs66SGiRKi-aULYRTthAG3Tm7mOc3AI2VggWrb4lG7psw5pC7NPA6DXlKPW_TxHeZJkrjMQ1d5D6mjzl_wzoeE6_DEKnvf5xLdtaGfqbV3y7Zy936ub4vto-bh9pviw5B5UJaEwGtUyYgNmioUVE3pJXSpECBhNhGsDYaLQ7SHCTZRgWLranAtuDkkl39djsi2o9T9x6mz_3_afkF1l5Lrg</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Deep Adaptation Control for Stereophonic Acoustic Echo Cancellation</title><source>IEEE Xplore All Conference Series</source><creator>Ivry, Amir ; Cohen, Israel ; Berdugo, Baruch</creator><creatorcontrib>Ivry, Amir ; Cohen, Israel ; Berdugo, Baruch</creatorcontrib><description>We introduce a general and data-driven adaptation-control framework for stereophonic acoustic-echo cancellation. The adaptation update rule for the filters that estimate the actual echo paths is compactly expressed with the widely-linear model in the complex time domain. A single step-size parameter that governs the behavior of the adaptation process is optimized by minimizing the misalignment between the actual echo paths and their filtered estimate. The relation between acoustic signals and the optimal step-size is learned via a deep neural network. In test mode, the optimal step-size prediction is inferred by the network and fed to the sign-error nor-malized least mean-squares (SNLMS) adaptive filter for echo-paths tracking. Real and simulated data show advantageous performance in single and double-talk scenarios across various acoustic setups.</description><identifier>EISSN: 1947-1629</identifier><identifier>EISBN: 9798350323726</identifier><identifier>DOI: 10.1109/WASPAA58266.2023.10248161</identifier><language>eng</language><publisher>IEEE</publisher><subject>Acoustics ; adaptation control ; Adaptation models ; Adaptive filters ; deep learning ; Echo cancellers ; Filtering ; Real-time systems ; sign-error NLMS ; Signal processing ; Stereophonic acoustic echo cancellation ; variable step-size</subject><ispartof>2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2023, p.1-5</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10248161$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,27902,54530,54907</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10248161$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Ivry, Amir</creatorcontrib><creatorcontrib>Cohen, Israel</creatorcontrib><creatorcontrib>Berdugo, Baruch</creatorcontrib><title>Deep Adaptation Control for Stereophonic Acoustic Echo Cancellation</title><title>2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)</title><addtitle>WASPAA</addtitle><description>We introduce a general and data-driven adaptation-control framework for stereophonic acoustic-echo cancellation. The adaptation update rule for the filters that estimate the actual echo paths is compactly expressed with the widely-linear model in the complex time domain. A single step-size parameter that governs the behavior of the adaptation process is optimized by minimizing the misalignment between the actual echo paths and their filtered estimate. The relation between acoustic signals and the optimal step-size is learned via a deep neural network. In test mode, the optimal step-size prediction is inferred by the network and fed to the sign-error nor-malized least mean-squares (SNLMS) adaptive filter for echo-paths tracking. Real and simulated data show advantageous performance in single and double-talk scenarios across various acoustic setups.</description><subject>Acoustics</subject><subject>adaptation control</subject><subject>Adaptation models</subject><subject>Adaptive filters</subject><subject>deep learning</subject><subject>Echo cancellers</subject><subject>Filtering</subject><subject>Real-time systems</subject><subject>sign-error NLMS</subject><subject>Signal processing</subject><subject>Stereophonic acoustic echo cancellation</subject><subject>variable step-size</subject><issn>1947-1629</issn><isbn>9798350323726</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2023</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNo1j81KxDAURqMgOI7zBi7iA7Te3Pw1y1DHURhQGMXlkElvmUptShsXvr3iz-o7m3PgY-xaQCkEuJtXv3vyXldoTImAshSAqhJGnLCVs66SGiRKi-aULYRTthAG3Tm7mOc3AI2VggWrb4lG7psw5pC7NPA6DXlKPW_TxHeZJkrjMQ1d5D6mjzl_wzoeE6_DEKnvf5xLdtaGfqbV3y7Zy936ub4vto-bh9pviw5B5UJaEwGtUyYgNmioUVE3pJXSpECBhNhGsDYaLQ7SHCTZRgWLranAtuDkkl39djsi2o9T9x6mz_3_afkF1l5Lrg</recordid><startdate>20231022</startdate><enddate>20231022</enddate><creator>Ivry, Amir</creator><creator>Cohen, Israel</creator><creator>Berdugo, Baruch</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>20231022</creationdate><title>Deep Adaptation Control for Stereophonic Acoustic Echo Cancellation</title><author>Ivry, Amir ; Cohen, Israel ; Berdugo, Baruch</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i204t-376c027946a22d26ed4c5de5445e404030cfc077c651b36b3e7d4a72f6807f093</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Acoustics</topic><topic>adaptation control</topic><topic>Adaptation models</topic><topic>Adaptive filters</topic><topic>deep learning</topic><topic>Echo cancellers</topic><topic>Filtering</topic><topic>Real-time systems</topic><topic>sign-error NLMS</topic><topic>Signal processing</topic><topic>Stereophonic acoustic echo cancellation</topic><topic>variable step-size</topic><toplevel>online_resources</toplevel><creatorcontrib>Ivry, Amir</creatorcontrib><creatorcontrib>Cohen, Israel</creatorcontrib><creatorcontrib>Berdugo, Baruch</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Xplore</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ivry, Amir</au><au>Cohen, Israel</au><au>Berdugo, Baruch</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Deep Adaptation Control for Stereophonic Acoustic Echo Cancellation</atitle><btitle>2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)</btitle><stitle>WASPAA</stitle><date>2023-10-22</date><risdate>2023</risdate><spage>1</spage><epage>5</epage><pages>1-5</pages><eissn>1947-1629</eissn><eisbn>9798350323726</eisbn><abstract>We introduce a general and data-driven adaptation-control framework for stereophonic acoustic-echo cancellation. The adaptation update rule for the filters that estimate the actual echo paths is compactly expressed with the widely-linear model in the complex time domain. A single step-size parameter that governs the behavior of the adaptation process is optimized by minimizing the misalignment between the actual echo paths and their filtered estimate. The relation between acoustic signals and the optimal step-size is learned via a deep neural network. In test mode, the optimal step-size prediction is inferred by the network and fed to the sign-error nor-malized least mean-squares (SNLMS) adaptive filter for echo-paths tracking. Real and simulated data show advantageous performance in single and double-talk scenarios across various acoustic setups.</abstract><pub>IEEE</pub><doi>10.1109/WASPAA58266.2023.10248161</doi><tpages>5</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | EISSN: 1947-1629 |
| ispartof | 2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2023, p.1-5 |
| issn | 1947-1629 |
| language | eng |
| recordid | cdi_ieee_primary_10248161 |
| source | IEEE Xplore All Conference Series |
| subjects | Acoustics adaptation control Adaptation models Adaptive filters deep learning Echo cancellers Filtering Real-time systems sign-error NLMS Signal processing Stereophonic acoustic echo cancellation variable step-size |
| title | Deep Adaptation Control for Stereophonic Acoustic Echo Cancellation |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-10T14%3A22%3A46IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Deep%20Adaptation%20Control%20for%20Stereophonic%20Acoustic%20Echo%20Cancellation&rft.btitle=2023%20IEEE%20Workshop%20on%20Applications%20of%20Signal%20Processing%20to%20Audio%20and%20Acoustics%20(WASPAA)&rft.au=Ivry,%20Amir&rft.date=2023-10-22&rft.spage=1&rft.epage=5&rft.pages=1-5&rft.eissn=1947-1629&rft_id=info:doi/10.1109/WASPAA58266.2023.10248161&rft.eisbn=9798350323726&rft_dat=%3Cieee_CHZPO%3E10248161%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i204t-376c027946a22d26ed4c5de5445e404030cfc077c651b36b3e7d4a72f6807f093%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=10248161&rfr_iscdi=true |