Pattern analysis of EEG responses to speech and voice: Influence of feature grouping

Hausfeld, Lars; Martino, Federico De; Bonte, Milene; Formisano, Elia

doi:10.1016/j.neuroimage.2011.11.056

Cited by 36 publications

(42 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Rather, it can discover any kind of spatio-temporal pattern localized in time or unfolding along several time periods of differential activity (Figures 2, 3). This aspect makes it quite different from other decoding methods commonly used in neuroimaging and cognitive studies, which usually explore the decoding performance over predefined time windows or over the whole trial (Philiastides and Sajda, 2006; Simanova et al, 2010; De Vos et al, 2012; Hausfeld et al, 2012). Integrating stimulus-related information that unfolds over multiple time periods of differential activity allows distributed patterns of activations in the discrimination between auditory categories to be taken into account, and leads to a more flexible strategy for optimal decoding performance.…”

Section: Discussionmentioning

confidence: 97%

See 1 more Smart Citation

Robust discrimination between EEG responses to categories of environmental sounds in early coma

et al. 2014

View full text Add to dashboard Cite

Humans can recognize categories of environmental sounds, including vocalizations produced by humans and animals and the sounds of man-made objects. Most neuroimaging investigations of environmental sound discrimination have studied subjects while consciously perceiving and often explicitly recognizing the stimuli. Consequently, it remains unclear to what extent auditory object processing occurs independently of task demands and consciousness. Studies in animal models have shown that environmental sound discrimination at a neural level persists even in anesthetized preparations, whereas data from anesthetized humans has thus far provided null results. Here, we studied comatose patients as a model of environmental sound discrimination capacities during unconsciousness. We included 19 comatose patients treated with therapeutic hypothermia (TH) during the first 2 days of coma, while recording nineteen-channel electroencephalography (EEG). At the level of each individual patient, we applied a decoding algorithm to quantify the differential EEG responses to human vs. animal vocalizations as well as to sounds of living vocalizations vs. man-made objects. Discrimination between vocalization types was accurate in 11 patients and discrimination between sounds from living and man-made sources in 10 patients. At the group level, the results were significant only for the comparison between vocalization types. These results lay the groundwork for disentangling truly preferential activations in response to auditory categories, and the contribution of awareness to auditory category discrimination.

show abstract

Section: Discussionmentioning

confidence: 97%

“…We evaluated the significance of our decoding results across all patients using a similar approach as in previous EEG decoding studies (Hausfeld et al, 2012). We used a binomial test (using the Matlab function binocdf), with n = total number of comparisons and k the number of patients showing significant decoding results.…”

Section: Methodsmentioning

confidence: 99%

Robust discrimination between EEG responses to categories of environmental sounds in early coma

et al. 2014

View full text Add to dashboard Cite

show abstract

“…Our data-driven approach builds upon emerging applications of machine learning methods to model electrophysiological responses (Hausfeld, De Martino, Bonte, & Formisano, 2012; Mesgarani, Cheung, Johnson, & Chang, 2014; Pei, Barbour, Leuthardt, & Schalk, 2011; Yi, Xie, Reetzke, Dimakis, & Chandrasekaran, 2017). The goal of unsupervised machine learning models (Alpaydin, 2014; Mohri, Rostamizadeh, & Talwalkar, 2012) is to learn target patterns (e.g., lexical tones) without being explicitly programmed.…”

Section: Introductionmentioning

confidence: 99%

Hidden Markov modeling of frequency-following responses to Mandarin lexical tones

Llanos

Xie

Chandrasekaran

2017

Journal of Neuroscience Methods

View full text Add to dashboard Cite

Background The frequency-following response (FFR) is a scalp-recorded electrophysiological potential reflecting phase-locked activity from neural ensembles in the auditory system. The FFR is often used to assess the robustness of subcortical pitch processing. Due to low signal-to-noise ratio at the single-trial level, FFRs are typically averaged across thousands of stimulus repetitions. Prior work using this approach has shown that subcortical encoding of linguistically-relevant pitch patterns is modulated by long-term language experience. New method We examine the extent to which a machine learning approach using hidden Markov modeling (HMM) can be utilized to decode Mandarin tone-categories from scalp-record electrophysiolgical activity. We then assess the extent to which the HMM can capture biologically-relevant effects (language experience-driven plasticity). To this end, we recorded FFRs to four Mandarin tones from 14 adult native speakers of Chinese and 14 of native English. We trained a HMM to decode tone categories from the FFRs with varying size of averages. Results and comparisons with existing methods Tone categories were decoded with above-chance accuracies using HMM. The HMM derived metric (decoding accuracy) revealed a robust effect of language experience, such that FFRs from native Chinese speakers yielded greater accuracies than native English speakers. Critically, the language experience-driven plasticity was captured with average sizes significantly smaller than those used in the extant literature. Conclusions Our results demonstrate the feasibility of HMM in assessing the robustness of neural pitch. Machine-learning approaches can complement extant analytical methods that capture auditory function and could reduce the number of trials needed to capture biological phenomena.

show abstract

“…En este contexto, las columnas relevantes son las que están situadas debajo de la superficie de los giros corticales. Como los potenciales de membrana de estas columnas fluctúan, se desarrolla un dipolo eléctrico (áreas adyacentes de carga opuesta) 6,8,9 . Las oscilaciones registradas en el EEG se producen por potenciales postsinapticos excitadores e inhibidores, desencadenados colectivamente por las columnas celulares corticales.…”

Section: Señales Electro-encefalografícas (Seeg)unclassified

Caracterizaciòn de la fonética y escritura de la letra “A” en señales cerebrales usando transformada wavelet

González

Mendoza

2016

BISTUA

View full text Add to dashboard Cite

Resumen: La afasia motriz afecta únicamente el lenguaje, y el área cognitiva queda intacta, esta falla cerebral se presenta sobre el área de broca, donde se manejan los impulsos aferentes de la articulación y modulación del lenguaje. Este trabajo muestra la obtención usando wavelet de patrones característicos de señales encefalografías provenientes de: fonética y escritura de la letra A, esto permitirá en un futuro tener una alternativa de comunicación distinta a pronunciar palabras. Este trabajo se presenta debido a las gran cantidad accidentes cerebrovasculares que afectan la capacidad de dialogo. Mediante la toma de señales electroencefalografías (SEEG) en puntos específicos se puede lograr caracterizar procesos de: gesticulación e interpretación de letras. El estudio se aplicó sobre 10 sujetos con edades de 24 y 25 años, la toma fue en condiciones similares en estado de vigilia. Se registraron 20 señales de la letra pronunciada, 20 de la letra escrita y 5 del sujeto en reposo. Se demostró que existen patrones diferentes que caracterizan la pronunciación y escritura de la letra "A" en una representación de SEEG.Palabras clave: Afasia, fonética, encefalografícas, procesamiento.A characterization of phonetics and writing of the letter "A" in cerebral signals using transformed wavelet AbstractThe motive aphasia affects only the language, and the cognitive area remains intact, this cerebral fault appears on the area of reel, where they handle the impulses afferents of the joint and modulation of the

show abstract

Pattern analysis of EEG responses to speech and voice: Influence of feature grouping

Cited by 36 publications

References 32 publications

Robust discrimination between EEG responses to categories of environmental sounds in early coma

Robust discrimination between EEG responses to categories of environmental sounds in early coma

Hidden Markov modeling of frequency-following responses to Mandarin lexical tones

Caracterizaciòn de la fonética y escritura de la letra “A” en señales cerebrales usando transformada wavelet

Contact Info

Product

Resources

About