Comparative intelligibility investigation of single-channel noise-reduction algorithms for Chinese, Japanese, and English
A large number of single-channel noise-reduction algorithms have been proposed based largely on mathematical principles. Most of these algorithms, however, have been evaluated with English speech. Given the different perceptual cues used by native listeners of different languages including tonal lan...
Gespeichert in:
Veröffentlicht in: | The Journal of the Acoustical Society of America 2011-05, Vol.129 (5), p.3291-3301 |
---|---|
Hauptverfasser: | , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 3301 |
---|---|
container_issue | 5 |
container_start_page | 3291 |
container_title | The Journal of the Acoustical Society of America |
container_volume | 129 |
creator | Li, Junfeng Yang, Lin Zhang, Jianping Yan, Yonghong Hu, Yi Akagi, Masato Loizou, Philipos C. |
description | A large number of single-channel noise-reduction algorithms have been proposed based largely on mathematical principles. Most of these algorithms, however, have been evaluated with English speech. Given the different perceptual cues used by native listeners of different languages including tonal languages, it is of interest to examine whether there are any language effects when the same noise-reduction algorithm is used to process noisy speech in different languages. A comparative evaluation and investigation is taken in this study of various single-channel noise-reduction algorithms applied to noisy speech taken from three languages: Chinese, Japanese, and English. Clean speech signals (Chinese words and Japanese words) were first corrupted by three types of noise at two signal-to-noise ratios and then processed by five single-channel noise-reduction algorithms. The processed signals were finally presented to normal-hearing listeners for recognition. Intelligibility evaluation showed that the majority of noise-reduction algorithms did not improve speech intelligibility. Consistent with a previous study with the English language, the Wiener filtering algorithm produced small, but statistically significant, improvements in intelligibility for car and white noise conditions. Significant differences between the performances of noise-reduction algorithms across the three languages were observed. |
doi_str_mv | 10.1121/1.3571422 |
format | Article |
fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_3108396</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1010699897</sourcerecordid><originalsourceid>FETCH-LOGICAL-c499t-aaa6eef6262dd5990b333594117d44f2752b4c2ca5abe516d5493223c026bae23</originalsourceid><addsrcrecordid>eNqNkkuLFDEUhYM4OO3owj8gtREUrDHvSjYD0ow6MuBG1-FWKlUVqUrapLqh_71xuue1GHCVXO7HSe45F6E3BJ8TQskncs5EQzilz9CKCIprJSh_jlYYY1JzLeUpepnz71IKxfQLdEqJkIozvEL7dZw3kGDxO1f5sLhp8oNv_eSXfal3Li9-KN0YqthX2YdhcrUdIQQ3VSH67Orkuq29IWAaYvLLOOeqj6lajz647D5W32EDhxuErrosGj6Pr9BJD1N2r4_nGfr15fLn-lt9_ePr1frzdW251ksNANK5XlJJu05ojVvGmNCckKbjvKeNoC231IKA1gkiO8E1o5RZTGULjrIzdHHQ3Wzb2XXWhSXBZDbJz5D2JoI3jzvBj2aIO8MILm7JIvD-KJDin20xxMw-22JUmSlusyGYUqWkZuo_UIKl1ko3Bf1wQG2KOSfX3_2IYPMvVUPMMdXCvn04wh15G2MB3h0ByBamPkGwPt9znCjSKHXvRbZ-uUn16VcfLIa5XQz2F_ivwWA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1010699897</pqid></control><display><type>article</type><title>Comparative intelligibility investigation of single-channel noise-reduction algorithms for Chinese, Japanese, and English</title><source>MEDLINE</source><source>AIP Journals Complete</source><source>Alma/SFX Local Collection</source><source>AIP Acoustical Society of America</source><creator>Li, Junfeng ; Yang, Lin ; Zhang, Jianping ; Yan, Yonghong ; Hu, Yi ; Akagi, Masato ; Loizou, Philipos C.</creator><creatorcontrib>Li, Junfeng ; Yang, Lin ; Zhang, Jianping ; Yan, Yonghong ; Hu, Yi ; Akagi, Masato ; Loizou, Philipos C.</creatorcontrib><description>A large number of single-channel noise-reduction algorithms have been proposed based largely on mathematical principles. Most of these algorithms, however, have been evaluated with English speech. Given the different perceptual cues used by native listeners of different languages including tonal languages, it is of interest to examine whether there are any language effects when the same noise-reduction algorithm is used to process noisy speech in different languages. A comparative evaluation and investigation is taken in this study of various single-channel noise-reduction algorithms applied to noisy speech taken from three languages: Chinese, Japanese, and English. Clean speech signals (Chinese words and Japanese words) were first corrupted by three types of noise at two signal-to-noise ratios and then processed by five single-channel noise-reduction algorithms. The processed signals were finally presented to normal-hearing listeners for recognition. Intelligibility evaluation showed that the majority of noise-reduction algorithms did not improve speech intelligibility. Consistent with a previous study with the English language, the Wiener filtering algorithm produced small, but statistically significant, improvements in intelligibility for car and white noise conditions. Significant differences between the performances of noise-reduction algorithms across the three languages were observed.</description><identifier>ISSN: 0001-4966</identifier><identifier>EISSN: 1520-8524</identifier><identifier>DOI: 10.1121/1.3571422</identifier><identifier>PMID: 21568430</identifier><identifier>CODEN: JASMAN</identifier><language>eng</language><publisher>Melville, NY: Acoustical Society of America</publisher><subject>Acoustic noise ; Adult ; Algorithms ; Audition ; Biological and medical sciences ; China ; Female ; Fundamental and applied biological sciences. Psychology ; Humans ; Intelligibility ; Japan ; Language ; Male ; Mathematical analysis ; Noise - prevention & control ; Perception ; Perceptual Masking ; Phonetics ; Pitch Perception ; Psychoacoustics ; Psychology. Psychoanalysis. Psychiatry ; Psychology. Psychophysiology ; Recognition ; Signal processing ; Signal Processing, Computer-Assisted ; Signal to noise ratio ; Speech ; Speech Acoustics ; Speech Intelligibility ; Speech Perception ; United States ; Young Adult</subject><ispartof>The Journal of the Acoustical Society of America, 2011-05, Vol.129 (5), p.3291-3301</ispartof><rights>2011 Acoustical Society of America</rights><rights>2015 INIST-CNRS</rights><rights>Copyright © 2011 Acoustical Society of America 2011 Acoustical Society of America</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c499t-aaa6eef6262dd5990b333594117d44f2752b4c2ca5abe516d5493223c026bae23</citedby><cites>FETCH-LOGICAL-c499t-aaa6eef6262dd5990b333594117d44f2752b4c2ca5abe516d5493223c026bae23</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://pubs.aip.org/jasa/article-lookup/doi/10.1121/1.3571422$$EHTML$$P50$$Gscitation$$H</linktohtml><link.rule.ids>207,208,230,314,777,781,791,882,1560,4498,27905,27906,76133</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=24181788$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/21568430$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Li, Junfeng</creatorcontrib><creatorcontrib>Yang, Lin</creatorcontrib><creatorcontrib>Zhang, Jianping</creatorcontrib><creatorcontrib>Yan, Yonghong</creatorcontrib><creatorcontrib>Hu, Yi</creatorcontrib><creatorcontrib>Akagi, Masato</creatorcontrib><creatorcontrib>Loizou, Philipos C.</creatorcontrib><title>Comparative intelligibility investigation of single-channel noise-reduction algorithms for Chinese, Japanese, and English</title><title>The Journal of the Acoustical Society of America</title><addtitle>J Acoust Soc Am</addtitle><description>A large number of single-channel noise-reduction algorithms have been proposed based largely on mathematical principles. Most of these algorithms, however, have been evaluated with English speech. Given the different perceptual cues used by native listeners of different languages including tonal languages, it is of interest to examine whether there are any language effects when the same noise-reduction algorithm is used to process noisy speech in different languages. A comparative evaluation and investigation is taken in this study of various single-channel noise-reduction algorithms applied to noisy speech taken from three languages: Chinese, Japanese, and English. Clean speech signals (Chinese words and Japanese words) were first corrupted by three types of noise at two signal-to-noise ratios and then processed by five single-channel noise-reduction algorithms. The processed signals were finally presented to normal-hearing listeners for recognition. Intelligibility evaluation showed that the majority of noise-reduction algorithms did not improve speech intelligibility. Consistent with a previous study with the English language, the Wiener filtering algorithm produced small, but statistically significant, improvements in intelligibility for car and white noise conditions. Significant differences between the performances of noise-reduction algorithms across the three languages were observed.</description><subject>Acoustic noise</subject><subject>Adult</subject><subject>Algorithms</subject><subject>Audition</subject><subject>Biological and medical sciences</subject><subject>China</subject><subject>Female</subject><subject>Fundamental and applied biological sciences. Psychology</subject><subject>Humans</subject><subject>Intelligibility</subject><subject>Japan</subject><subject>Language</subject><subject>Male</subject><subject>Mathematical analysis</subject><subject>Noise - prevention & control</subject><subject>Perception</subject><subject>Perceptual Masking</subject><subject>Phonetics</subject><subject>Pitch Perception</subject><subject>Psychoacoustics</subject><subject>Psychology. Psychoanalysis. Psychiatry</subject><subject>Psychology. Psychophysiology</subject><subject>Recognition</subject><subject>Signal processing</subject><subject>Signal Processing, Computer-Assisted</subject><subject>Signal to noise ratio</subject><subject>Speech</subject><subject>Speech Acoustics</subject><subject>Speech Intelligibility</subject><subject>Speech Perception</subject><subject>United States</subject><subject>Young Adult</subject><issn>0001-4966</issn><issn>1520-8524</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2011</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNqNkkuLFDEUhYM4OO3owj8gtREUrDHvSjYD0ow6MuBG1-FWKlUVqUrapLqh_71xuue1GHCVXO7HSe45F6E3BJ8TQskncs5EQzilz9CKCIprJSh_jlYYY1JzLeUpepnz71IKxfQLdEqJkIozvEL7dZw3kGDxO1f5sLhp8oNv_eSXfal3Li9-KN0YqthX2YdhcrUdIQQ3VSH67Orkuq29IWAaYvLLOOeqj6lajz647D5W32EDhxuErrosGj6Pr9BJD1N2r4_nGfr15fLn-lt9_ePr1frzdW251ksNANK5XlJJu05ojVvGmNCckKbjvKeNoC231IKA1gkiO8E1o5RZTGULjrIzdHHQ3Wzb2XXWhSXBZDbJz5D2JoI3jzvBj2aIO8MILm7JIvD-KJDin20xxMw-22JUmSlusyGYUqWkZuo_UIKl1ko3Bf1wQG2KOSfX3_2IYPMvVUPMMdXCvn04wh15G2MB3h0ByBamPkGwPt9znCjSKHXvRbZ-uUn16VcfLIa5XQz2F_ivwWA</recordid><startdate>20110501</startdate><enddate>20110501</enddate><creator>Li, Junfeng</creator><creator>Yang, Lin</creator><creator>Zhang, Jianping</creator><creator>Yan, Yonghong</creator><creator>Hu, Yi</creator><creator>Akagi, Masato</creator><creator>Loizou, Philipos C.</creator><general>Acoustical Society of America</general><general>American Institute of Physics</general><scope>IQODW</scope><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7T9</scope><scope>7SP</scope><scope>7U5</scope><scope>8FD</scope><scope>H8D</scope><scope>L7M</scope><scope>5PM</scope></search><sort><creationdate>20110501</creationdate><title>Comparative intelligibility investigation of single-channel noise-reduction algorithms for Chinese, Japanese, and English</title><author>Li, Junfeng ; Yang, Lin ; Zhang, Jianping ; Yan, Yonghong ; Hu, Yi ; Akagi, Masato ; Loizou, Philipos C.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c499t-aaa6eef6262dd5990b333594117d44f2752b4c2ca5abe516d5493223c026bae23</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Acoustic noise</topic><topic>Adult</topic><topic>Algorithms</topic><topic>Audition</topic><topic>Biological and medical sciences</topic><topic>China</topic><topic>Female</topic><topic>Fundamental and applied biological sciences. Psychology</topic><topic>Humans</topic><topic>Intelligibility</topic><topic>Japan</topic><topic>Language</topic><topic>Male</topic><topic>Mathematical analysis</topic><topic>Noise - prevention & control</topic><topic>Perception</topic><topic>Perceptual Masking</topic><topic>Phonetics</topic><topic>Pitch Perception</topic><topic>Psychoacoustics</topic><topic>Psychology. Psychoanalysis. Psychiatry</topic><topic>Psychology. Psychophysiology</topic><topic>Recognition</topic><topic>Signal processing</topic><topic>Signal Processing, Computer-Assisted</topic><topic>Signal to noise ratio</topic><topic>Speech</topic><topic>Speech Acoustics</topic><topic>Speech Intelligibility</topic><topic>Speech Perception</topic><topic>United States</topic><topic>Young Adult</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Li, Junfeng</creatorcontrib><creatorcontrib>Yang, Lin</creatorcontrib><creatorcontrib>Zhang, Jianping</creatorcontrib><creatorcontrib>Yan, Yonghong</creatorcontrib><creatorcontrib>Hu, Yi</creatorcontrib><creatorcontrib>Akagi, Masato</creatorcontrib><creatorcontrib>Loizou, Philipos C.</creatorcontrib><collection>Pascal-Francis</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Linguistics and Language Behavior Abstracts (LLBA)</collection><collection>Electronics & Communications Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>Technology Research Database</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>The Journal of the Acoustical Society of America</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Li, Junfeng</au><au>Yang, Lin</au><au>Zhang, Jianping</au><au>Yan, Yonghong</au><au>Hu, Yi</au><au>Akagi, Masato</au><au>Loizou, Philipos C.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Comparative intelligibility investigation of single-channel noise-reduction algorithms for Chinese, Japanese, and English</atitle><jtitle>The Journal of the Acoustical Society of America</jtitle><addtitle>J Acoust Soc Am</addtitle><date>2011-05-01</date><risdate>2011</risdate><volume>129</volume><issue>5</issue><spage>3291</spage><epage>3301</epage><pages>3291-3301</pages><issn>0001-4966</issn><eissn>1520-8524</eissn><coden>JASMAN</coden><abstract>A large number of single-channel noise-reduction algorithms have been proposed based largely on mathematical principles. Most of these algorithms, however, have been evaluated with English speech. Given the different perceptual cues used by native listeners of different languages including tonal languages, it is of interest to examine whether there are any language effects when the same noise-reduction algorithm is used to process noisy speech in different languages. A comparative evaluation and investigation is taken in this study of various single-channel noise-reduction algorithms applied to noisy speech taken from three languages: Chinese, Japanese, and English. Clean speech signals (Chinese words and Japanese words) were first corrupted by three types of noise at two signal-to-noise ratios and then processed by five single-channel noise-reduction algorithms. The processed signals were finally presented to normal-hearing listeners for recognition. Intelligibility evaluation showed that the majority of noise-reduction algorithms did not improve speech intelligibility. Consistent with a previous study with the English language, the Wiener filtering algorithm produced small, but statistically significant, improvements in intelligibility for car and white noise conditions. Significant differences between the performances of noise-reduction algorithms across the three languages were observed.</abstract><cop>Melville, NY</cop><pub>Acoustical Society of America</pub><pmid>21568430</pmid><doi>10.1121/1.3571422</doi><tpages>11</tpages><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0001-4966 |
ispartof | The Journal of the Acoustical Society of America, 2011-05, Vol.129 (5), p.3291-3301 |
issn | 0001-4966 1520-8524 |
language | eng |
recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_3108396 |
source | MEDLINE; AIP Journals Complete; Alma/SFX Local Collection; AIP Acoustical Society of America |
subjects | Acoustic noise Adult Algorithms Audition Biological and medical sciences China Female Fundamental and applied biological sciences. Psychology Humans Intelligibility Japan Language Male Mathematical analysis Noise - prevention & control Perception Perceptual Masking Phonetics Pitch Perception Psychoacoustics Psychology. Psychoanalysis. Psychiatry Psychology. Psychophysiology Recognition Signal processing Signal Processing, Computer-Assisted Signal to noise ratio Speech Speech Acoustics Speech Intelligibility Speech Perception United States Young Adult |
title | Comparative intelligibility investigation of single-channel noise-reduction algorithms for Chinese, Japanese, and English |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-17T23%3A12%3A25IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Comparative%20intelligibility%20investigation%20of%20single-channel%20noise-reduction%20algorithms%20for%20Chinese,%20Japanese,%20and%20English&rft.jtitle=The%20Journal%20of%20the%20Acoustical%20Society%20of%20America&rft.au=Li,%20Junfeng&rft.date=2011-05-01&rft.volume=129&rft.issue=5&rft.spage=3291&rft.epage=3301&rft.pages=3291-3301&rft.issn=0001-4966&rft.eissn=1520-8524&rft.coden=JASMAN&rft_id=info:doi/10.1121/1.3571422&rft_dat=%3Cproquest_pubme%3E1010699897%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1010699897&rft_id=info:pmid/21568430&rfr_iscdi=true |