Enhancing listening capability of humanoid robot by reduction of stationary ego‐noise

Speech interfaces for household robots utilizing third‐party automatic speech recognition (ASR) services face the challenge of overcoming stationary ego‐noise that decreases ASR accuracy. Previous studies on signal processing have proposed numerous noise reduction methods that increase the signal‐to...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEJ transactions on electrical and electronic engineering 2019-12, Vol.14 (12), p.1815-1822
Hauptverfasser: Wake, Naoki, Fukumoto, Masaaki, Takahashi, Hirokazu, Ikeuchi, Katsushi
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 1822
container_issue 12
container_start_page 1815
container_title IEEJ transactions on electrical and electronic engineering
container_volume 14
creator Wake, Naoki
Fukumoto, Masaaki
Takahashi, Hirokazu
Ikeuchi, Katsushi
description Speech interfaces for household robots utilizing third‐party automatic speech recognition (ASR) services face the challenge of overcoming stationary ego‐noise that decreases ASR accuracy. Previous studies on signal processing have proposed numerous noise reduction methods that increase the signal‐to‐noise ratio of speech audio and subjective speech clarity. However, severe limitations on the cost of hardware of household robots and the use of closed ‘black box’ ASR services require us to re‐examine the efficacy of noise reduction methods in this context. Here we compare the effect of several basic noise filters on the performance of ASR services when speech sounds include the stationary ego‐noise of a humanoid Pepper robot. The result revealed that a spectrum subtraction filter improves the accuracy of ASR services best. We also demonstrate that the filter improves ASR performance on an actual Pepper robot system. This study not only provides practical knowledge on the selection of noise filters for a robot system but also discusses further improvements to the listening capabilities of the robot utilizing ASR. © 2019 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.
doi_str_mv 10.1002/tee.23008
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2315681278</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2315681278</sourcerecordid><originalsourceid>FETCH-LOGICAL-c3638-495d8ad0f4c625f8827cef1f8640950fc284391d2dc80e5963432b5aac24ad223</originalsourceid><addsrcrecordid>eNp1kL1OwzAUhS0EEqUw8AaWmBja-idJnRFV4UeqxFLEaDmO3bpK7WI7Qtl4BJ6RJ8EhiI3pHul-596jA8A1RnOMEFlEpeaEIsROwASXFM-ykuHTP72k5-AihD1CWUEZm4DXyu6ElcZuYWtCVHZQUhxFbVoTe-g03HUHYZ1poHe1i7DuoVdNJ6NxdliHKAYpfA_V1n19fCY2qEtwpkUb1NXvnIKX-2qzepytnx-eVnfrmaQpQEqUN0w0SGeyILlmjCyl0lizIkNljrQkLKMlbkgjGVJ5WdCMkjoXQpJMNITQKbgZ7x69e-tUiHzvOm_TS04ozguGyZIl6nakpHcheKX50ZtDiswx4kNvPPXGf3pL7GJk302r-v9Bvqmq0fENOStwGg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2315681278</pqid></control><display><type>article</type><title>Enhancing listening capability of humanoid robot by reduction of stationary ego‐noise</title><source>Access via Wiley Online Library</source><creator>Wake, Naoki ; Fukumoto, Masaaki ; Takahashi, Hirokazu ; Ikeuchi, Katsushi</creator><creatorcontrib>Wake, Naoki ; Fukumoto, Masaaki ; Takahashi, Hirokazu ; Ikeuchi, Katsushi</creatorcontrib><description>Speech interfaces for household robots utilizing third‐party automatic speech recognition (ASR) services face the challenge of overcoming stationary ego‐noise that decreases ASR accuracy. Previous studies on signal processing have proposed numerous noise reduction methods that increase the signal‐to‐noise ratio of speech audio and subjective speech clarity. However, severe limitations on the cost of hardware of household robots and the use of closed ‘black box’ ASR services require us to re‐examine the efficacy of noise reduction methods in this context. Here we compare the effect of several basic noise filters on the performance of ASR services when speech sounds include the stationary ego‐noise of a humanoid Pepper robot. The result revealed that a spectrum subtraction filter improves the accuracy of ASR services best. We also demonstrate that the filter improves ASR performance on an actual Pepper robot system. This study not only provides practical knowledge on the selection of noise filters for a robot system but also discusses further improvements to the listening capabilities of the robot utilizing ASR. © 2019 Institute of Electrical Engineers of Japan. Published by John Wiley &amp; Sons, Inc.</description><identifier>ISSN: 1931-4973</identifier><identifier>EISSN: 1931-4981</identifier><identifier>DOI: 10.1002/tee.23008</identifier><language>eng</language><publisher>Hoboken, USA: John Wiley &amp; Sons, Inc</publisher><subject>Acoustics ; Automatic speech recognition ; distributed robot systems ; ego‐noise ; Face recognition ; Humanoid ; Noise ; Noise reduction ; robot audition ; Robots ; Signal processing ; social human–robot interaction ; Sound filters ; Speech sounds ; Subtraction</subject><ispartof>IEEJ transactions on electrical and electronic engineering, 2019-12, Vol.14 (12), p.1815-1822</ispartof><rights>2019 Institute of Electrical Engineers of Japan. Published by John Wiley &amp; Sons, Inc.</rights><rights>Copyright © 2019 Institute of Electrical Engineers of Japan. Published by John Wiley &amp; Sons, Inc.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c3638-495d8ad0f4c625f8827cef1f8640950fc284391d2dc80e5963432b5aac24ad223</citedby><cites>FETCH-LOGICAL-c3638-495d8ad0f4c625f8827cef1f8640950fc284391d2dc80e5963432b5aac24ad223</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://onlinelibrary.wiley.com/doi/pdf/10.1002%2Ftee.23008$$EPDF$$P50$$Gwiley$$H</linktopdf><linktohtml>$$Uhttps://onlinelibrary.wiley.com/doi/full/10.1002%2Ftee.23008$$EHTML$$P50$$Gwiley$$H</linktohtml><link.rule.ids>314,780,784,1417,27924,27925,45574,45575</link.rule.ids></links><search><creatorcontrib>Wake, Naoki</creatorcontrib><creatorcontrib>Fukumoto, Masaaki</creatorcontrib><creatorcontrib>Takahashi, Hirokazu</creatorcontrib><creatorcontrib>Ikeuchi, Katsushi</creatorcontrib><title>Enhancing listening capability of humanoid robot by reduction of stationary ego‐noise</title><title>IEEJ transactions on electrical and electronic engineering</title><description>Speech interfaces for household robots utilizing third‐party automatic speech recognition (ASR) services face the challenge of overcoming stationary ego‐noise that decreases ASR accuracy. Previous studies on signal processing have proposed numerous noise reduction methods that increase the signal‐to‐noise ratio of speech audio and subjective speech clarity. However, severe limitations on the cost of hardware of household robots and the use of closed ‘black box’ ASR services require us to re‐examine the efficacy of noise reduction methods in this context. Here we compare the effect of several basic noise filters on the performance of ASR services when speech sounds include the stationary ego‐noise of a humanoid Pepper robot. The result revealed that a spectrum subtraction filter improves the accuracy of ASR services best. We also demonstrate that the filter improves ASR performance on an actual Pepper robot system. This study not only provides practical knowledge on the selection of noise filters for a robot system but also discusses further improvements to the listening capabilities of the robot utilizing ASR. © 2019 Institute of Electrical Engineers of Japan. Published by John Wiley &amp; Sons, Inc.</description><subject>Acoustics</subject><subject>Automatic speech recognition</subject><subject>distributed robot systems</subject><subject>ego‐noise</subject><subject>Face recognition</subject><subject>Humanoid</subject><subject>Noise</subject><subject>Noise reduction</subject><subject>robot audition</subject><subject>Robots</subject><subject>Signal processing</subject><subject>social human–robot interaction</subject><subject>Sound filters</subject><subject>Speech sounds</subject><subject>Subtraction</subject><issn>1931-4973</issn><issn>1931-4981</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><recordid>eNp1kL1OwzAUhS0EEqUw8AaWmBja-idJnRFV4UeqxFLEaDmO3bpK7WI7Qtl4BJ6RJ8EhiI3pHul-596jA8A1RnOMEFlEpeaEIsROwASXFM-ykuHTP72k5-AihD1CWUEZm4DXyu6ElcZuYWtCVHZQUhxFbVoTe-g03HUHYZ1poHe1i7DuoVdNJ6NxdliHKAYpfA_V1n19fCY2qEtwpkUb1NXvnIKX-2qzepytnx-eVnfrmaQpQEqUN0w0SGeyILlmjCyl0lizIkNljrQkLKMlbkgjGVJ5WdCMkjoXQpJMNITQKbgZ7x69e-tUiHzvOm_TS04ozguGyZIl6nakpHcheKX50ZtDiswx4kNvPPXGf3pL7GJk302r-v9Bvqmq0fENOStwGg</recordid><startdate>201912</startdate><enddate>201912</enddate><creator>Wake, Naoki</creator><creator>Fukumoto, Masaaki</creator><creator>Takahashi, Hirokazu</creator><creator>Ikeuchi, Katsushi</creator><general>John Wiley &amp; Sons, Inc</general><general>Wiley Subscription Services, Inc</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>8FD</scope><scope>L7M</scope></search><sort><creationdate>201912</creationdate><title>Enhancing listening capability of humanoid robot by reduction of stationary ego‐noise</title><author>Wake, Naoki ; Fukumoto, Masaaki ; Takahashi, Hirokazu ; Ikeuchi, Katsushi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c3638-495d8ad0f4c625f8827cef1f8640950fc284391d2dc80e5963432b5aac24ad223</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Acoustics</topic><topic>Automatic speech recognition</topic><topic>distributed robot systems</topic><topic>ego‐noise</topic><topic>Face recognition</topic><topic>Humanoid</topic><topic>Noise</topic><topic>Noise reduction</topic><topic>robot audition</topic><topic>Robots</topic><topic>Signal processing</topic><topic>social human–robot interaction</topic><topic>Sound filters</topic><topic>Speech sounds</topic><topic>Subtraction</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Wake, Naoki</creatorcontrib><creatorcontrib>Fukumoto, Masaaki</creatorcontrib><creatorcontrib>Takahashi, Hirokazu</creatorcontrib><creatorcontrib>Ikeuchi, Katsushi</creatorcontrib><collection>CrossRef</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>IEEJ transactions on electrical and electronic engineering</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wake, Naoki</au><au>Fukumoto, Masaaki</au><au>Takahashi, Hirokazu</au><au>Ikeuchi, Katsushi</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Enhancing listening capability of humanoid robot by reduction of stationary ego‐noise</atitle><jtitle>IEEJ transactions on electrical and electronic engineering</jtitle><date>2019-12</date><risdate>2019</risdate><volume>14</volume><issue>12</issue><spage>1815</spage><epage>1822</epage><pages>1815-1822</pages><issn>1931-4973</issn><eissn>1931-4981</eissn><abstract>Speech interfaces for household robots utilizing third‐party automatic speech recognition (ASR) services face the challenge of overcoming stationary ego‐noise that decreases ASR accuracy. Previous studies on signal processing have proposed numerous noise reduction methods that increase the signal‐to‐noise ratio of speech audio and subjective speech clarity. However, severe limitations on the cost of hardware of household robots and the use of closed ‘black box’ ASR services require us to re‐examine the efficacy of noise reduction methods in this context. Here we compare the effect of several basic noise filters on the performance of ASR services when speech sounds include the stationary ego‐noise of a humanoid Pepper robot. The result revealed that a spectrum subtraction filter improves the accuracy of ASR services best. We also demonstrate that the filter improves ASR performance on an actual Pepper robot system. This study not only provides practical knowledge on the selection of noise filters for a robot system but also discusses further improvements to the listening capabilities of the robot utilizing ASR. © 2019 Institute of Electrical Engineers of Japan. Published by John Wiley &amp; Sons, Inc.</abstract><cop>Hoboken, USA</cop><pub>John Wiley &amp; Sons, Inc</pub><doi>10.1002/tee.23008</doi><tpages>8</tpages></addata></record>
fulltext fulltext
identifier ISSN: 1931-4973
ispartof IEEJ transactions on electrical and electronic engineering, 2019-12, Vol.14 (12), p.1815-1822
issn 1931-4973
1931-4981
language eng
recordid cdi_proquest_journals_2315681278
source Access via Wiley Online Library
subjects Acoustics
Automatic speech recognition
distributed robot systems
ego‐noise
Face recognition
Humanoid
Noise
Noise reduction
robot audition
Robots
Signal processing
social human–robot interaction
Sound filters
Speech sounds
Subtraction
title Enhancing listening capability of humanoid robot by reduction of stationary ego‐noise
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-22T04%3A24%3A57IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Enhancing%20listening%20capability%20of%20humanoid%20robot%20by%20reduction%20of%20stationary%20ego%E2%80%90noise&rft.jtitle=IEEJ%20transactions%20on%20electrical%20and%20electronic%20engineering&rft.au=Wake,%20Naoki&rft.date=2019-12&rft.volume=14&rft.issue=12&rft.spage=1815&rft.epage=1822&rft.pages=1815-1822&rft.issn=1931-4973&rft.eissn=1931-4981&rft_id=info:doi/10.1002/tee.23008&rft_dat=%3Cproquest_cross%3E2315681278%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2315681278&rft_id=info:pmid/&rfr_iscdi=true