Single-trial analysis of the neural correlates of speech quality perception

Anne K. Porbadnigk, Matthias S. Treder, Benjamin Blankertz, Jan Niklas Antons, Robert Schleicher, Sebastian Möller, Gabriel Curio, Klaus Muller

Research output: Contribution to journalArticle

28 Citations (Scopus)

Abstract

Objective. Assessing speech quality perception is a challenge typically addressed in behavioral and opinion-seeking experiments. Only recently, neuroimaging methods were introduced, which were used to study the neural processing of quality at group level. However, our electroencephalography (EEG) studies show that the neural correlates of quality perception are highly individual. Therefore, it became necessary to establish dedicated machine learning methods for decoding subject-specific effects. Approach. The effectiveness of our methods is shown by the data of an EEG study that investigates how the quality of spoken vowels is processed neurally. Participants were asked to indicate whether they had perceived a degradation of quality (signal-correlated noise) in vowels, presented in an oddball paradigm. Main results. We find that the P3 amplitude is attenuated with increasing noise. Single-trial analysis allows one to show that this is partly due to an increasing jitter of the P3 component. A novel classification approach helps to detect trials with presumably non-conscious processing at the threshold of perception. We show that this approach uncovers a non-trivial confounder between neural hits and neural misses. Significance. The combined use of EEG signals and machine learning methods results in a significant 'neural' gain in sensitivity (in processing quality loss) when compared to standard behavioral evaluation; averaged over 11 subjects, this amounts to a relative improvement in sensitivity of 35%.

Original languageEnglish
Article number056003
JournalJournal of Neural Engineering
Volume10
Issue number5
DOIs
Publication statusPublished - 2013 Oct 1

Fingerprint

Speech Perception
Electroencephalography
Learning systems
Processing
Neuroimaging
Noise
Jitter
Decoding
Degradation
Experiments
Machine Learning

ASJC Scopus subject areas

  • Biomedical Engineering
  • Cellular and Molecular Neuroscience

Cite this

Porbadnigk, A. K., Treder, M. S., Blankertz, B., Antons, J. N., Schleicher, R., Möller, S., ... Muller, K. (2013). Single-trial analysis of the neural correlates of speech quality perception. Journal of Neural Engineering, 10(5), [056003]. https://doi.org/10.1088/1741-2560/10/5/056003

Single-trial analysis of the neural correlates of speech quality perception. / Porbadnigk, Anne K.; Treder, Matthias S.; Blankertz, Benjamin; Antons, Jan Niklas; Schleicher, Robert; Möller, Sebastian; Curio, Gabriel; Muller, Klaus.

In: Journal of Neural Engineering, Vol. 10, No. 5, 056003, 01.10.2013.

Research output: Contribution to journalArticle

Porbadnigk, AK, Treder, MS, Blankertz, B, Antons, JN, Schleicher, R, Möller, S, Curio, G & Muller, K 2013, 'Single-trial analysis of the neural correlates of speech quality perception', Journal of Neural Engineering, vol. 10, no. 5, 056003. https://doi.org/10.1088/1741-2560/10/5/056003
Porbadnigk AK, Treder MS, Blankertz B, Antons JN, Schleicher R, Möller S et al. Single-trial analysis of the neural correlates of speech quality perception. Journal of Neural Engineering. 2013 Oct 1;10(5). 056003. https://doi.org/10.1088/1741-2560/10/5/056003
Porbadnigk, Anne K. ; Treder, Matthias S. ; Blankertz, Benjamin ; Antons, Jan Niklas ; Schleicher, Robert ; Möller, Sebastian ; Curio, Gabriel ; Muller, Klaus. / Single-trial analysis of the neural correlates of speech quality perception. In: Journal of Neural Engineering. 2013 ; Vol. 10, No. 5.
@article{771a6399241e452e9a3707ea5b5cc346,
title = "Single-trial analysis of the neural correlates of speech quality perception",
abstract = "Objective. Assessing speech quality perception is a challenge typically addressed in behavioral and opinion-seeking experiments. Only recently, neuroimaging methods were introduced, which were used to study the neural processing of quality at group level. However, our electroencephalography (EEG) studies show that the neural correlates of quality perception are highly individual. Therefore, it became necessary to establish dedicated machine learning methods for decoding subject-specific effects. Approach. The effectiveness of our methods is shown by the data of an EEG study that investigates how the quality of spoken vowels is processed neurally. Participants were asked to indicate whether they had perceived a degradation of quality (signal-correlated noise) in vowels, presented in an oddball paradigm. Main results. We find that the P3 amplitude is attenuated with increasing noise. Single-trial analysis allows one to show that this is partly due to an increasing jitter of the P3 component. A novel classification approach helps to detect trials with presumably non-conscious processing at the threshold of perception. We show that this approach uncovers a non-trivial confounder between neural hits and neural misses. Significance. The combined use of EEG signals and machine learning methods results in a significant 'neural' gain in sensitivity (in processing quality loss) when compared to standard behavioral evaluation; averaged over 11 subjects, this amounts to a relative improvement in sensitivity of 35{\%}.",
author = "Porbadnigk, {Anne K.} and Treder, {Matthias S.} and Benjamin Blankertz and Antons, {Jan Niklas} and Robert Schleicher and Sebastian M{\"o}ller and Gabriel Curio and Klaus Muller",
year = "2013",
month = "10",
day = "1",
doi = "10.1088/1741-2560/10/5/056003",
language = "English",
volume = "10",
journal = "Journal of Neural Engineering",
issn = "1741-2560",
publisher = "IOP Publishing Ltd.",
number = "5",

}

TY - JOUR

T1 - Single-trial analysis of the neural correlates of speech quality perception

AU - Porbadnigk, Anne K.

AU - Treder, Matthias S.

AU - Blankertz, Benjamin

AU - Antons, Jan Niklas

AU - Schleicher, Robert

AU - Möller, Sebastian

AU - Curio, Gabriel

AU - Muller, Klaus

PY - 2013/10/1

Y1 - 2013/10/1

N2 - Objective. Assessing speech quality perception is a challenge typically addressed in behavioral and opinion-seeking experiments. Only recently, neuroimaging methods were introduced, which were used to study the neural processing of quality at group level. However, our electroencephalography (EEG) studies show that the neural correlates of quality perception are highly individual. Therefore, it became necessary to establish dedicated machine learning methods for decoding subject-specific effects. Approach. The effectiveness of our methods is shown by the data of an EEG study that investigates how the quality of spoken vowels is processed neurally. Participants were asked to indicate whether they had perceived a degradation of quality (signal-correlated noise) in vowels, presented in an oddball paradigm. Main results. We find that the P3 amplitude is attenuated with increasing noise. Single-trial analysis allows one to show that this is partly due to an increasing jitter of the P3 component. A novel classification approach helps to detect trials with presumably non-conscious processing at the threshold of perception. We show that this approach uncovers a non-trivial confounder between neural hits and neural misses. Significance. The combined use of EEG signals and machine learning methods results in a significant 'neural' gain in sensitivity (in processing quality loss) when compared to standard behavioral evaluation; averaged over 11 subjects, this amounts to a relative improvement in sensitivity of 35%.

AB - Objective. Assessing speech quality perception is a challenge typically addressed in behavioral and opinion-seeking experiments. Only recently, neuroimaging methods were introduced, which were used to study the neural processing of quality at group level. However, our electroencephalography (EEG) studies show that the neural correlates of quality perception are highly individual. Therefore, it became necessary to establish dedicated machine learning methods for decoding subject-specific effects. Approach. The effectiveness of our methods is shown by the data of an EEG study that investigates how the quality of spoken vowels is processed neurally. Participants were asked to indicate whether they had perceived a degradation of quality (signal-correlated noise) in vowels, presented in an oddball paradigm. Main results. We find that the P3 amplitude is attenuated with increasing noise. Single-trial analysis allows one to show that this is partly due to an increasing jitter of the P3 component. A novel classification approach helps to detect trials with presumably non-conscious processing at the threshold of perception. We show that this approach uncovers a non-trivial confounder between neural hits and neural misses. Significance. The combined use of EEG signals and machine learning methods results in a significant 'neural' gain in sensitivity (in processing quality loss) when compared to standard behavioral evaluation; averaged over 11 subjects, this amounts to a relative improvement in sensitivity of 35%.

UR - http://www.scopus.com/inward/record.url?scp=84885435765&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84885435765&partnerID=8YFLogxK

U2 - 10.1088/1741-2560/10/5/056003

DO - 10.1088/1741-2560/10/5/056003

M3 - Article

C2 - 23902853

AN - SCOPUS:84885435765

VL - 10

JO - Journal of Neural Engineering

JF - Journal of Neural Engineering

SN - 1741-2560

IS - 5

M1 - 056003

ER -