Speech Intelligibility Predicted from Neural Entrainment of the Speech Envelope
- 861 Downloads
Speech intelligibility is currently measured by scoring how well a person can identify a speech signal. The results of such behavioral measures reflect neural processing of the speech signal, but are also influenced by language processing, motivation, and memory. Very often, electrophysiological measures of hearing give insight in the neural processing of sound. However, in most methods, non-speech stimuli are used, making it hard to relate the results to behavioral measures of speech intelligibility. The use of natural running speech as a stimulus in electrophysiological measures of hearing is a paradigm shift which allows to bridge the gap between behavioral and electrophysiological measures. Here, by decoding the speech envelope from the electroencephalogram, and correlating it with the stimulus envelope, we demonstrate an electrophysiological measure of neural processing of running speech. We show that behaviorally measured speech intelligibility is strongly correlated with our electrophysiological measure. Our results pave the way towards an objective and automatic way of assessing neural processing of speech presented through auditory prostheses, reducing confounds such as attention and cognitive capabilities. We anticipate that our electrophysiological measure will allow better differential diagnosis of the auditory system, and will allow the development of closed-loop auditory prostheses that automatically adapt to individual users.
KeywordsNeural decoding Auditory evoked potentials EEG measures Objective measures Speech understanding
The authors thank Lise Goris and Eline Verschueren for their help with the data acquisition.
Compliance with Ethical Standards
Before each experiment, the subjects signed an informed consent form approved by the Medical Ethics Committee UZ KU Leuven/Research (KU Leuven) with reference S59040.
Conflict of Interest
The authors declare that they have no conflict of interest.
- Biesmans W, Das N, Francart T, Bertrand A (2017) Auditory-inspired speech envelope extraction methods for improved eeg-based auditory attention detection in a cocktail party scenario. IEEE Trans Neural Syst Rehabil Eng 25(5):402–412. https://doi.org/10.1109/TNSRE.2016.2571900
- Dillon H (2012) Hearing aids. Thieme, StuttgartGoogle Scholar
- Luts H, Jansen S, Dreschler W, Wouters J (2015) Development and normative data for the Flemish/Dutch matrix test. KU Leuven. https://lirias.kuleuven.be/bitstream/123456789/474335/1/Documentation+Flemish-Dutch+Matrix_December2014.pdf. Accessed 5 Feb 2018
- O’Sullivan JA, Power AJ, Mesgarani N, Rajaram S, Foxe JJ, Shinn-Cunningham BG, Slaney M, Shamma SA, Lalor EC (2015) Attentional selection in a cocktail party environment can be decoded from single-trial eeg. Cereb Cortex 25(7):1697–1706. https://doi.org/10.1093/cercor/bht355
- Søndergaard PL, Torrésani B, Balazs P (2012) The linear time frequency analysis toolbox. Int J Wavelets Multiresolution Inf Process 10(4):1250032. https://doi.org/10.1142/S0219691312500324
- Yang M, Sheth SA, Schevon CA, McKhann II GM, Mesgarani N (2015) Speech reconstruction from human auditory cortex with deep neural networks. In: Sixteenth Annual Conference of the International Speech Communication Association, Dresden, Germany, pp 1121–1125Google Scholar