Prediction of speech intelligibility based on an auditory preprocessing model

• Published in: Speech communication Vol. 52; no. 7; pp. 678 - 692
• Main Authors: Christiansen, Claus, Pedersen, Michael Syskind, Dau, Torsten
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.07.2010; Elsevier
• Subjects: Applied sciences; Auditory processing model; Exact sciences and technology; Ideal binary mask; Information, signal and communications theory; Intelligibility; Masks; Mathematical models; Noise; Preprocessing; Signal processing; Similarity; Speech; Speech intelligibility; Speech intelligibility index; Speech processing; Speech transmission index; Telecommunications and information theory; Training; Speech intelligibility index; Ideal binary mask; Speech intelligibility; Speech transmission index; Auditory processing model; Psychoacoustics; Speech analysis; Acoustic signal; Similarity; Vocoder; Verbal perception; Speech transmission; Learning
• DOI: 10.1016/j.specom.2010.03.004
• ISSN: 0167-6393

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.