Shrikanth Narayanan
YOU?
Author Swipe
View article: A Point Process Model of Skin Conductance Responses in a Stroop Task for Predicting Depression and Suicidal Ideation
A Point Process Model of Skin Conductance Responses in a Stroop Task for Predicting Depression and Suicidal Ideation Open
Accurate identification of mental health biomarkers can enable earlier detection and objective assessment of compromised mental well-being. In this study, we analyze electrodermal activity recorded during an Emotional Stroop task to captur…
View article: Assessing Visual Privacy Risks in Multimodal AI: A Novel Taxonomy-Grounded Evaluation of Vision-Language Models
Assessing Visual Privacy Risks in Multimodal AI: A Novel Taxonomy-Grounded Evaluation of Vision-Language Models Open
Artificial Intelligence have profoundly transformed the technological landscape in recent years. Large Language Models (LLMs) have demonstrated impressive abilities in reasoning, text comprehension, contextual pattern recognition, and inte…
View article: Effective Elicitation of Stuttering in Magnetic Resonance Imaging Data Collection Using a Suite of Connected Speech Tasks
Effective Elicitation of Stuttering in Magnetic Resonance Imaging Data Collection Using a Suite of Connected Speech Tasks Open
Purpose: Articulatory behaviors during moments of stuttering have been understudied, largely due to the technical difficulty of collecting such data. Tracking moving articulators during stuttering requires advanced instrumentation, and eli…
View article: Decoding Neural Signatures of Semantic Evaluation in Depression and Suicidality.
Decoding Neural Signatures of Semantic Evaluation in Depression and Suicidality. Open
Depression and suicidality profoundly impact cognition and emotion, yet objective neurophysiological biomarkers remain elusive. We investigated the spatiotemporal neural dynamics underlying affective semantic processing in individuals with…
View article: PRECOG: Comprehensive Experimental Design and Stimuli Protocol for Investigating Depression and Suicidal Ideation
PRECOG: Comprehensive Experimental Design and Stimuli Protocol for Investigating Depression and Suicidal Ideation Open
The Multimodal Integration of Neural and Biobehavioral Signals for Predicting Preconscious Responses (PRECOG) project investigated the neural and cognitive mechanisms underlying depression and suicidal ideation through a series of cognitiv…
View article: Estimating Markers of Driving Stress through Multimodal Physiological Monitoring
Estimating Markers of Driving Stress through Multimodal Physiological Monitoring Open
Understanding and mitigating driving stress is vital for preventing accidents and advancing both road safety and driver well-being. While vehicles are equipped with increasingly sophisticated safety systems, many limits exist in their abil…
View article: How to Retrieve Examples in In-context Learning to Improve Conversational Emotion Recognition using Large Language Models?
How to Retrieve Examples in In-context Learning to Improve Conversational Emotion Recognition using Large Language Models? Open
Large language models (LLMs) have enabled a wide variety of real-world applications in various domains. However, creating a high-performing application with high accuracy remains challenging, particularly for subjective tasks like emotion …
Joint ASR and Speaker Role Tagging with Serialized Output Training Open
Automatic Speech Recognition systems have made significant progress with large-scale pre-trained models. However, most current systems focus solely on transcribing the speech without identifying speaker roles, a function that is critical f…
View article: Neural Responses to Affective Sentences Reveal Signatures of Depression
Neural Responses to Affective Sentences Reveal Signatures of Depression Open
Major Depressive Disorder (MDD) is a highly prevalent mental health condition, and a deeper understanding of its neurocognitive foundations is essential for identifying how core functions such as emotional and self-referential processing a…
View article: LSM-2: Learning from Incomplete Wearable Sensor Data
LSM-2: Learning from Incomplete Wearable Sensor Data Open
Foundation models, a cornerstone of recent advancements in machine learning, have predominantly thrived on complete and well-structured data. Wearable sensor data frequently suffers from significant missingness, posing a substantial challe…
View article: Who Said What WSW 2.0? Enhanced Automated Analysis of Preschool Classroom Speech
Who Said What WSW 2.0? Enhanced Automated Analysis of Preschool Classroom Speech Open
This paper introduces an automated framework WSW2.0 for analyzing vocal interactions in preschool classrooms, enhancing both accuracy and scalability through the integration of wav2vec2-based speaker classification and Whisper (large-v2 an…
View article: Deep Learning Characterizes Depression and Suicidal Ideation from Eye Movements
Deep Learning Characterizes Depression and Suicidal Ideation from Eye Movements Open
Identifying physiological and behavioral markers for mental health conditions is a longstanding challenge in psychiatry. Depression and suicidal ideation, in particular, lack objective biomarkers, with screening and diagnosis primarily rel…
View article: Association of machine-learning-rated supportive counseling skills with psychotherapy outcome.
Association of machine-learning-rated supportive counseling skills with psychotherapy outcome. Open
Therapist exploration of clients' experience and expression of understanding may be important skills that are associated with clients' better outcomes. This study highlights the importance of support counseling skills, as well as the poten…
View article: Large Language Models Do Multi-Label Classification Differently
Large Language Models Do Multi-Label Classification Differently Open
Multi-label classification is prevalent in real-world settings, but the behavior of Large Language Models (LLMs) in this setting is understudied. We investigate how autoregressive LLMs perform multi-label classification, focusing on subjec…
View article: Formant Tracking by Combining Deep Neural Network and Linear Prediction
Formant Tracking by Combining Deep Neural Network and Linear Prediction Open
Formant tracking is an area of speech science that has recently undergone a technology shift from classical model-driven signal processing methods to modern data-driven deep learning methods. In this study, these two domains are combined i…
View article: Developing Personalized Algorithms for Sensing Mental Health Symptoms in Daily Life
Developing Personalized Algorithms for Sensing Mental Health Symptoms in Daily Life Open
The integration of artificial intelligence (AI) and pervasive computing offers new ways to sense mental health symptoms and deliver real-time interventions via mobile devices. This study explores personalized versus generalized machine lea…
View article: Biased Bots: An Empirical Demonstration of How AI Bias Could Compromise Mental Healthcare
Biased Bots: An Empirical Demonstration of How AI Bias Could Compromise Mental Healthcare Open
Background: The proliferation of artificial intelligence (AI) applications for mental health has advanced in recent years and shows promise to increase the reach, scope, and impact of mental healthcare. However, biases in algorithms design…
View article: Benchmarking machine learning missing data imputation methods in large-scale mental health survey databases
Benchmarking machine learning missing data imputation methods in large-scale mental health survey databases Open
Databases tied to mental and behavioral health surveys suffer from the issue of missing data when participants skip the entire survey, which affects the data quality and sample size. These missing data patterns were investigated and the im…
View article: Direct articulatory observation reveals phoneme recognition performance characteristics of a self-supervised speech model
Direct articulatory observation reveals phoneme recognition performance characteristics of a self-supervised speech model Open
Variability in speech pronunciation is widely observed across different linguistic backgrounds, which impacts modern automatic speech recognition performance. Here, we evaluate the performance of a self-supervised speech model in phoneme r…
View article: Can a Machine Distinguish High and Low Amount of Social Creak in Speech?
Can a Machine Distinguish High and Low Amount of Social Creak in Speech? Open
Objectives: ncreased prevalence of social creak particularly among female speakers has been reported in several studies. The study of social creak has been previously conducted by combining perceptual evaluation of speech with conventional…
View article: Vertical larynx actions and intergestural timing stability in Hausa ejectives and implosives
Vertical larynx actions and intergestural timing stability in Hausa ejectives and implosives Open
The current project undertakes a kinematic examination of vertical larynx actions and intergestural timing stability within multi-gesture complex segments such as ejectives and implosives that may possess specific temporal goals critical t…
View article: Aggregation Artifacts in Subjective Tasks Collapse Large Language Models' Posteriors
Aggregation Artifacts in Subjective Tasks Collapse Large Language Models' Posteriors Open
In-context Learning (ICL) has become the primary method for performing natural language tasks with Large Language Models (LLMs). The knowledge acquired during pre-training is crucial for this few-shot capability, providing the model with t…
View article: Scaling Wearable Foundation Models
Scaling Wearable Foundation Models Open
Wearable sensors have become ubiquitous thanks to a variety of health tracking features. The resulting continuous and longitudinal measurements from everyday life generate large volumes of data; however, making sense of these observations …