File Download
  Links for fulltext
     (May Require Subscription)

Conference Paper: Non-intrusive intelligibility prediction for Mandarin speech in noise

TitleNon-intrusive intelligibility prediction for Mandarin speech in noise
Authors
KeywordsNon-intrusive intelligibility index
Intelligibility prediction
Issue Date2013
PublisherIEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000751
Citation
The 2013 IEEE Region 10 Conference (TENCON 2013), Xi'an, China, 22-25 October 2013. In Conference Proceedings, 2013, p. 1-4 How to Cite?
AbstractMost existing intelligibility indices require access to the input (clean) reference signal to predict speech intelligibility in noise. In some real-world applications, however, only the noise-masked speech is available, rendering existing indices of little use. The present study assessed the performance of an intelligibility measure that could be used to predict non-intrusively (i.e., with no access to the clean input signal) speech intelligibility in noise using only information extracted from the noise-masked speech envelopes. The proposed intelligibility measure (denoted as ModA) was computed by integrating the area of the modulation spectrum (within 0.5 Hz to 10 Hz) of the noise-masked envelopes extracted in four acoustic bands. The ModA measure was evaluated with intelligibility scores obtained by normal-hearing listeners presented with Mandarin sentences corrupted by three types of maskers. High correlation (r=0.90) was obtained between ModA values and listener’s intelligibility scores, suggesting that the modulation-spectrum area could be potentially used as a simple but efficient predictor of speech intelligibility in noisy conditions.
Persistent Identifierhttp://hdl.handle.net/10722/194804
ISBN

 

DC FieldValueLanguage
dc.contributor.authorChen, Fen_US
dc.contributor.authorGuan, Ten_US
dc.date.accessioned2014-02-17T02:10:42Z-
dc.date.available2014-02-17T02:10:42Z-
dc.date.issued2013en_US
dc.identifier.citationThe 2013 IEEE Region 10 Conference (TENCON 2013), Xi'an, China, 22-25 October 2013. In Conference Proceedings, 2013, p. 1-4en_US
dc.identifier.isbn978-1-4799-2827-9-
dc.identifier.urihttp://hdl.handle.net/10722/194804-
dc.description.abstractMost existing intelligibility indices require access to the input (clean) reference signal to predict speech intelligibility in noise. In some real-world applications, however, only the noise-masked speech is available, rendering existing indices of little use. The present study assessed the performance of an intelligibility measure that could be used to predict non-intrusively (i.e., with no access to the clean input signal) speech intelligibility in noise using only information extracted from the noise-masked speech envelopes. The proposed intelligibility measure (denoted as ModA) was computed by integrating the area of the modulation spectrum (within 0.5 Hz to 10 Hz) of the noise-masked envelopes extracted in four acoustic bands. The ModA measure was evaluated with intelligibility scores obtained by normal-hearing listeners presented with Mandarin sentences corrupted by three types of maskers. High correlation (r=0.90) was obtained between ModA values and listener’s intelligibility scores, suggesting that the modulation-spectrum area could be potentially used as a simple but efficient predictor of speech intelligibility in noisy conditions.-
dc.languageengen_US
dc.publisherIEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000751en_US
dc.relation.ispartofIEEE Region 10 International Conference (TENCON) Proceedingsen_US
dc.rightsCreative Commons: Attribution 3.0 Hong Kong Licenseen_US
dc.rights©2013 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.en_US
dc.subjectNon-intrusive intelligibility index-
dc.subjectIntelligibility prediction-
dc.titleNon-intrusive intelligibility prediction for Mandarin speech in noiseen_US
dc.typeConference_Paperen_US
dc.identifier.emailChen, F: feichen1@hku.hken_US
dc.identifier.authorityChen, F=rp01593en_US
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1109/TENCON.2013.6719062en_US
dc.identifier.hkuros227818en_US
dc.identifier.spage1en_US
dc.identifier.epage4en_US
dc.publisher.placeUnited States-
dc.customcontrol.immutablesml 140220-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats