File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TENCON.2013.6719062
- Scopus: eid_2-s2.0-84894348299
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Non-intrusive intelligibility prediction for Mandarin speech in noise
Title | Non-intrusive intelligibility prediction for Mandarin speech in noise |
---|---|
Authors | |
Keywords | Non-intrusive intelligibility index Intelligibility prediction |
Issue Date | 2013 |
Publisher | IEEE. 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? |
Abstract | Most 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 Identifier | http://hdl.handle.net/10722/194804 |
ISBN |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chen, F | en_US |
dc.contributor.author | Guan, T | en_US |
dc.date.accessioned | 2014-02-17T02:10:42Z | - |
dc.date.available | 2014-02-17T02:10:42Z | - |
dc.date.issued | 2013 | en_US |
dc.identifier.citation | The 2013 IEEE Region 10 Conference (TENCON 2013), Xi'an, China, 22-25 October 2013. In Conference Proceedings, 2013, p. 1-4 | en_US |
dc.identifier.isbn | 978-1-4799-2827-9 | - |
dc.identifier.uri | http://hdl.handle.net/10722/194804 | - |
dc.description.abstract | Most 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.language | eng | en_US |
dc.publisher | IEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000751 | en_US |
dc.relation.ispartof | IEEE Region 10 International Conference (TENCON) Proceedings | en_US |
dc.subject | Non-intrusive intelligibility index | - |
dc.subject | Intelligibility prediction | - |
dc.title | Non-intrusive intelligibility prediction for Mandarin speech in noise | en_US |
dc.type | Conference_Paper | en_US |
dc.identifier.email | Chen, F: feichen1@hku.hk | en_US |
dc.identifier.authority | Chen, F=rp01593 | en_US |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/TENCON.2013.6719062 | en_US |
dc.identifier.scopus | eid_2-s2.0-84894348299 | - |
dc.identifier.hkuros | 227818 | en_US |
dc.identifier.spage | 1 | en_US |
dc.identifier.epage | 4 | en_US |
dc.publisher.place | United States | - |
dc.customcontrol.immutable | sml 140220 | - |