Ciencias Exactas y Ciencias de la Salud

Now showing 1 - 2 of 2

Improved emotion recognition in speech by autistics: design, validation, and implementation of acoustically modulated prosodies
(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2023-12-04) Duville, Mathilde Marie; Alonso Valerdi, Luz María; emipsanchez; González Garrido, Andrés Antonio; Martínez Méndez, Rigoberto; Montesinos Silva, Luis Arturo; Escuela de Ingeniería y Ciencias; Campus Monterrey; Ibarra Zarate, David Isaac
The prosodic structure of speech carries emotional information within uncertain acoustic environments where speaker, lexical, phonological, and affective dependencies for perception may exist. Socio-emotional disturbances are among the diagnostic criteria for the autism spectrum disorder, but autistics have been characterized with either impaired or typical emotional prosodies recognition, both at behavioral and neuronal scales. From a Bayesian framework we hypothesize that the oversampling of sensory evidence relative to the confidence ascribed towards internal representations would impair perception within highly variable environments. However, more reliable hierarchical structures of spectral and temporal cues would foster emotion recognition by autistics. Here, pitch, formants’ frequency, lexical stress, harmonics’ intensity, and speech rate have been edited from human voices to create stable acoustic environments. Electroencephalographic data have emphasized impaired emotion recognition while listening to human voices, that was improved when the acoustic volatility and variability of voices was reduced. Observations have been extended to the visual domain by behavioral measurements on a concomitant non-social task consistent with the over-precision ascribed to the environmental variability (sensory processing) that impaired the performance of autistics. To ensure the cultural validity of prosodies, a database adapted to the Mexican shaping of emotional expressions has been firstly developed. The recognition and induction of emotions by human and acoustically modulated voices have been validated by supervised learning and both neuronal and behavioral markers of human perception. This work offers insights into the definition of emotions by acoustic features, the neuronal processing of affective prosodies, its modulation by the acoustic variability of inputs, and the potential of certain environments to foster emotion recognition by autistics.
Evaluation of stimulation conditions for the design of Brain-Computer Interfaces based on visual stimuli.
(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2023-06) Chailloux Peguero, Juan David; CARIÑO ESCOBAR, RUBEN ISAAC; 452466; Antelis Ortiz, Javier M.; puemcuervo, emipsanchez; Cariño Escobar, Ruben Isaac; Ruiz Olaya, Andrés Felipe; Vega Romero, Roberto Ivan; School of Engineering and Sciences; Campus Monterrey; Mendoza Montoya, Omar
Brain-computer interfaces (BCIs) have emerged as promising technologies for enabling direct communication and control between the human brain and external devices. The effectiveness and efficiency of BCIs heavily rely on the selection of optimal specificity criteria, which determine the design parameters used to elicit and interpret brain signals. This thesis presents a comprehensive investigation into the selection of specificity criteria for BCIs based on visual Event-Related Potentials (P300) and Steady-State Visual Evoked Potentials (SSVEP). The study focuses on three main findings. Firstly, it demonstrates the superiority of the Cartoon Face (CF) visual scheme over the Standard Flash (SF) in eliciting a more prominent P300 brain response and achieving better single-trial classification of target elements from non-target elements. Secondly, the investigation reveals that the combination of either the On-Off rectangular (OOR) or sinusoidal (OOS) luminance-modulated visual stimulus, along with the Filter-Bank Canonical Correlation Analysis (FBCCA) as a detection method, yields the best performance for SSVEP-based BCI assessments. Finally, the research highlights the superiority of the sitting posture over the supine posture in P300 paradigm evaluations. The findings of this research have significant implications for the design and implementation of BCIs. Practitioners and designers are recommended to consider incorporating the Cartoon Face visual scheme as it enhances P300 responses and single-trial classification effectiveness. For SSVEP-based BCIs, the use of OOR or OOS visual stimuli with FBCCA as I the detection method should be prioritized. Moreover, adopting the sitting posture during P300 paradigm assessments can lead to improved BCI performance. Despite the valuable insights gained, this research acknowledges certain limitations. The selection of specificity criteria may exclude other relevant factors that could impact BCI performance. Additionally, the research methodology and data collection process may have potential biases that can arise if we have preconceived expectations or preferences for certain outcomes. To address these limitations, future investigations should explore alternative specificity criteria, conduct unbiased data collection and analysis, and evaluate the generalizability of findings in real-world applications. In conclusion, this thesis provides a comprehensive exploration of specificity criteria for BCIs based on P300 and SSVEP. The identified findings underscore the importance of considering visual stimuli, detection methods, and posture in BCI design. By implementing the recommended specificity criteria and addressing the limitations, practitioners and researchers can advance the development of more effective and reliable BCIs, leading to enhanced user experiences and expanding the potential applications of these transformative technologies.

Ciencias Exactas y Ciencias de la Salud

Browse

Filters

Settings

Sort By

Results per page

Search Results