File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: EEG-based auditory attention decoding using speech-level-based segmented computational models

TitleEEG-based auditory attention decoding using speech-level-based segmented computational models
Authors
KeywordsEEG
RMS-level-based speech segments
Aditory attention decoding (AAD)
Machine learning
Signal-to-mask ratio (SMR)
Issue Date2021
PublisherInstitute of Physics Pub.. The Journal's web site is located at http://www.iop.org/EJ/journal/JNE
Citation
Journal of Neural Engineering, 2021, v. 18 n. 4 How to Cite?
AbstractObjective.Auditory attention in complex scenarios can be decoded by electroencephalography (EEG)-based cortical speech-envelope tracking. The relative root-mean-square (RMS) intensity is a valuable cue for the decomposition of speech into distinct characteristic segments. To improve auditory attention decoding (AAD) performance, this work proposed a novel segmented AAD approach to decode target speech envelopes from different RMS-level-based speech segments.Approach.Speech was decomposed into higher- and lower-RMS-level speech segments with a threshold of -10 dB relative RMS level. A support vector machine classifier was designed to identify higher- and lower-RMS-level speech segments, using clean target and mixed speech as reference signals based on corresponding EEG signals recorded when subjects listened to target auditory streams in competing two-speaker auditory scenes. Segmented computational models were developed with the classification results of higher- and lower-RMS-level speech segments. Speech envelopes were reconstructed based on segmented decoding models for either higher- or lower-RMS-level speech segments. AAD accuracies were calculated according to the correlations between actual and reconstructed speech envelopes. The performance of the proposed segmented AAD computational model was compared to those of traditional AAD methods with unified decoding functions.Main results.Higher- and lower-RMS-level speech segments in continuous sentences could be identified robustly with classification accuracies that approximated or exceeded 80% based on corresponding EEG signals at 6 dB, 3 dB, 0 dB, -3 dB and -6 dB signal-to-mask ratios (SMRs). Compared with unified AAD decoding methods, the proposed segmented AAD approach achieved more accurate results in the reconstruction of target speech envelopes and in the detection of attentional directions. Moreover, the proposed segmented decoding method had higher information transfer rates (ITRs) and shorter minimum expected switch times compared with the unified decoder.Significance.This study revealed that EEG signals may be used to classify higher- and lower-RMS-level-based speech segments across a wide range of SMR conditions (from 6 dB to -6 dB). A novel finding was that the specific information in different RMS-level-based speech segments facilitated EEG-based decoding of auditory attention. The significantly improved AAD accuracies and ITRs of the segmented decoding method suggests that this proposed computational model may be an effective method for the application of neuro-controlled brain-computer interfaces in complex auditory scenes.
Persistent Identifierhttp://hdl.handle.net/10722/303954
ISSN
2023 Impact Factor: 3.7
2023 SCImago Journal Rankings: 1.094
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorWang, L-
dc.contributor.authorWu, EX-
dc.contributor.authorChen, F-
dc.date.accessioned2021-09-23T08:53:09Z-
dc.date.available2021-09-23T08:53:09Z-
dc.date.issued2021-
dc.identifier.citationJournal of Neural Engineering, 2021, v. 18 n. 4-
dc.identifier.issn1741-2560-
dc.identifier.urihttp://hdl.handle.net/10722/303954-
dc.description.abstractObjective.Auditory attention in complex scenarios can be decoded by electroencephalography (EEG)-based cortical speech-envelope tracking. The relative root-mean-square (RMS) intensity is a valuable cue for the decomposition of speech into distinct characteristic segments. To improve auditory attention decoding (AAD) performance, this work proposed a novel segmented AAD approach to decode target speech envelopes from different RMS-level-based speech segments.Approach.Speech was decomposed into higher- and lower-RMS-level speech segments with a threshold of -10 dB relative RMS level. A support vector machine classifier was designed to identify higher- and lower-RMS-level speech segments, using clean target and mixed speech as reference signals based on corresponding EEG signals recorded when subjects listened to target auditory streams in competing two-speaker auditory scenes. Segmented computational models were developed with the classification results of higher- and lower-RMS-level speech segments. Speech envelopes were reconstructed based on segmented decoding models for either higher- or lower-RMS-level speech segments. AAD accuracies were calculated according to the correlations between actual and reconstructed speech envelopes. The performance of the proposed segmented AAD computational model was compared to those of traditional AAD methods with unified decoding functions.Main results.Higher- and lower-RMS-level speech segments in continuous sentences could be identified robustly with classification accuracies that approximated or exceeded 80% based on corresponding EEG signals at 6 dB, 3 dB, 0 dB, -3 dB and -6 dB signal-to-mask ratios (SMRs). Compared with unified AAD decoding methods, the proposed segmented AAD approach achieved more accurate results in the reconstruction of target speech envelopes and in the detection of attentional directions. Moreover, the proposed segmented decoding method had higher information transfer rates (ITRs) and shorter minimum expected switch times compared with the unified decoder.Significance.This study revealed that EEG signals may be used to classify higher- and lower-RMS-level-based speech segments across a wide range of SMR conditions (from 6 dB to -6 dB). A novel finding was that the specific information in different RMS-level-based speech segments facilitated EEG-based decoding of auditory attention. The significantly improved AAD accuracies and ITRs of the segmented decoding method suggests that this proposed computational model may be an effective method for the application of neuro-controlled brain-computer interfaces in complex auditory scenes.-
dc.languageeng-
dc.publisherInstitute of Physics Pub.. The Journal's web site is located at http://www.iop.org/EJ/journal/JNE-
dc.relation.ispartofJournal of Neural Engineering-
dc.subjectEEG-
dc.subjectRMS-level-based speech segments-
dc.subjectAditory attention decoding (AAD)-
dc.subjectMachine learning-
dc.subjectSignal-to-mask ratio (SMR)-
dc.titleEEG-based auditory attention decoding using speech-level-based segmented computational models-
dc.typeArticle-
dc.identifier.emailWu, EX: ewu@eee.hku.hk-
dc.identifier.authorityWu, EX=rp00193-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1088/1741-2552/abfeba-
dc.identifier.pmid33957606-
dc.identifier.hkuros325445-
dc.identifier.volume18-
dc.identifier.issue4-
dc.identifier.isiWOS:000655389700001-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats