Prediction of speech intelligibility based on an auditory preprocessing model

Publication: Research - peer-reviewJournal article – Annual report year: 2010

View graph of relations

Classical speech intelligibility models, such as the speech transmission index (STI) and the speech intelligibility index (SII) are based on calculations on the physical acoustic signals. The present study predicts speech intelligibility by combining a psychoacoustically validated model of auditory preprocessing [Dau et al., 1997. J. Acoust. Soc. Am. 102, 2892-2905] with a simple central stage that describes the similarity of the test signal with the corresponding reference signal at a level of the internal representation of the signals. The model was compared with previous approaches, whereby a speech in noise experiment was used for training and an ideal binary mask experiment was used for evaluation. All three models were able to capture the trends in the speech in noise training data well, but the proposed model provides a better prediction of the binary mask test data, particularly when the binary masks degenerate to a noise vocoder.
Original languageEnglish
JournalSpeech Communication
Publication date2010
Volume52
Issue7-8
Pages678-692
ISSN0167-6393
DOIs
StatePublished
CitationsWeb of Science® Times Cited: 20

Keywords

  • Auditory processing model, Ideal binary mask, Speech transmission index, peech intelligibility, Speech intelligibility index
Download as:
Download as PDF
Select render style:
APAAuthorCBEHarvardMLAStandardVancouverShortLong
PDF
Download as HTML
Select render style:
APAAuthorCBEHarvardMLAStandardVancouverShortLong
HTML
Download as Word
Select render style:
APAAuthorCBEHarvardMLAStandardVancouverShortLong
Word

ID: 4637131