About

Shrikanth (Shri) Narayanan is a University Professor and holder of the Niki and Max Nikias Chair in Engineering at the University of Southern California (USC). He serves as the inaugural Vice President for Presidential Initiatives on the Senior Leadership Team of USC's President. He is a Professor in the Signal and Image Processing Institute of USC's Ming Hsieh Electrical & Computer Engineering department with joint appointments in Computer Science, Linguistics, Psychology, Neuroscience, Pediatrics, and Otolaryngology-Head and Neck Surgery. Shri Narayanan is also the inaugural director of the Ming Hsieh Institute, a Research Director for the Information Sciences Institute at USC, and a Visiting Faculty Researcher at Google. His academic background includes a Master's degree, Engineer's degree, and Ph.D. in electrical engineering from UCLA, and a Bachelor's degree from Anna University in India. His research focuses on human-centered sensing, signal processing, and machine intelligence related to human communication, emotions, and behavior, with applications in defense, security, health, media, and the arts. He has published extensively, holds numerous patents, and has contributed to technology commercialization through startups he co-founded, such as Behavioral Signals Technologies and Lyssn.

Research topics

• Computer Science
• Artificial Intelligence
• Speech recognition
• Psychology
• Medicine
• Machine Learning
• Natural Language Processing
• World Wide Web
• Mathematics
• Biology
• Audiology
• Psychotherapist
• Acoustics
• Pathology
• Computer vision
• Psychiatry
• Physics
• Linguistics

Selected publications

• Effects of emotional spillover and exposure to interparental psychological aggression on momentary physiological linkage during naturalistic couple conflicts

  Biological Psychology · 2026-01-01

  article
  PublisherDOI

• A Point Process Model of Skin Conductance Responses in a Stroop Task for Predicting Depression and Suicidal Ideation

  2026-04-21

  articleOpen accessSenior author

  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 capture sympathetic arousal dynamics associated with depression and suicidal ideation. We model the timing of skin conductance responses as a point process whose conditional intensity is modulated by task-based covariates, including stimulus valence, reaction time, and response accuracy. The resulting subject-specific parameter vector serves as input to a machine learning classifier for distinguishing individuals with and without depression. Our results show that the model parameters encode meaningful physiological differences associated with depressive symptomatology and yield superior classification performance compared to conventional feature extraction methods.

  PublisherOA PDFDOI

• Neural Responses to Affective Sentences Reveal Signatures of Depression

  Translational Psychiatry · 2026-05-15

  preprintOpen accessSenior author

  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 are affected. We investigate how depression symptoms alters the temporal dynamics of emotional processing by measuring neural responses to self-referential affective sentences using surface electroencephalography (EEG) in healthy and depressed individuals. Our results reveal significant group-level differences in neural activity during sentence viewing, suggesting disrupted integration of emotional and self-referential information in depression. Deep learning model trained on these responses achieves an area under the receiver operating curve (AUC) of 0.72 in distinguishing healthy from depressed participants, and 0.65 in differentiating depressed subgroups with and without suicidal ideation symptoms. Spatial ablations highlight anterior electrodes associated with semantic and affective processing as key contributors. These findings suggest stable, stimulus-driven neural signatures of depression symptoms that may inform future screening tools.

  PublisherOA PDFDOI

• Looking Into the Past: Eye Movements Characterize Elements of Autobiographical Recall in Interviews with Holocaust Survivors

  arXiv (Cornell University) · 2026-04-23

  preprintOpen accessSenior author

  Eye movement and memory retrieval are deeply and bidirectionally intertwined, however existing literature is generally confined to controlled lab settings. We investigate the relationship between eye gaze and memory recall in free-form autobiographical recall, which comprises both autonoetic consciousness -- the ability to mentally place oneself in the past or future -- and various affective states. Using a large video corpus of semi-naturalistic interviews with Holocaust survivors (N = 806), we examine eye movements with respect to episodic, semantic, affective, and temporal dimensions of traumatic and highly emotional autobiographical recall. We observe gaze patterns vary significantly across certain temporal contexts, most prominently in vertical eye movements. We additionally train intra-subject sequence models to predict temporal context of sentences from segments of gaze features, and find that eye movements entirely preceding sentence onset are sufficient for prediction. Our results corroborate prior findings in literature linking eye movements to memory in controlled and semi-structured settings, reinforcing the role of eye gaze in retrieving and constructing memories, especially in highly emotional and remote memory recall.

  PublisherDOI

• Longitudinal Analysis of IEQ Variability in Office and Home Workspaces: Insights for the Future of Hybrid Work

  2026-01-28

  articleSenior author

  As hybrid work gains traction, understanding exposure to varying indoor environmental quality (IEQ) attributes becomes increasingly important for promoting health, productivity, and equity in workplace models. This longitudinal study investigated key IEQ attributes—temperature, relative humidity (RH), carbon dioxide (CO₂), particulate matter (PM₂.₅), total volatile organic compounds (TVOC), and ambient noise—across 12 participants’ home and office workspaces. Data were collected over 4 months through continuous monitoring and ecological momentary assessments (EMAs). Results revealed significant differences in IEQ variability between the two workspace types. Office workspaces generally maintained more stable conditions due to advanced climate control systems, while home workspaces exhibited greater fluctuations likely influenced by weather, building design, and occupant behaviors. Notably, TVOC and PM₂.₅ levels occasionally exceeded recommended thresholds in some home workspaces, underscoring potential health risks. These findings highlight the need for adaptive strategies, such as improved ventilation, air purification, and occupant education, to enhance IEQ in hybrid workspaces.

  PublisherDOI

• Looking Into the Past: Eye Movements Characterize Elements of Autobiographical Recall in Interviews with Holocaust Survivors

  ArXiv.org · 2026-04-23

  articleOpen accessSenior author

  Eye movement and memory retrieval are deeply and bidirectionally intertwined, however existing literature is generally confined to controlled lab settings. We investigate the relationship between eye gaze and memory recall in free-form autobiographical recall, which comprises both autonoetic consciousness -- the ability to mentally place oneself in the past or future -- and various affective states. Using a large video corpus of semi-naturalistic interviews with Holocaust survivors (N = 806), we examine eye movements with respect to episodic, semantic, affective, and temporal dimensions of traumatic and highly emotional autobiographical recall. We observe gaze patterns vary significantly across certain temporal contexts, most prominently in vertical eye movements. We additionally train intra-subject sequence models to predict temporal context of sentences from segments of gaze features, and find that eye movements entirely preceding sentence onset are sufficient for prediction. Our results corroborate prior findings in literature linking eye movements to memory in controlled and semi-structured settings, reinforcing the role of eye gaze in retrieving and constructing memories, especially in highly emotional and remote memory recall.

  PublisherOA PDF

• Dominance and complementarity in cross-modal representation learning for wearable time series

  Information Fusion · 2026-04-30

  articleOpen access
  PublisherDOI

• PRECOG: Comprehensive Experimental Design and Stimuli Protocol for Investigating Depression and Suicidal Ideation

  2025-07-21

  preprintOpen access

  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 cognitive tasks paired with continuous multimodal physiological and neurophysiological recordings. A total of 160 college-aged participants, including healthy controls, individuals with depression without suicidal ideation, and individuals with depression and suicidal ideation, were recruited based on screening using the Patient Health Questionnaire-9 (PHQ-9) and the Suicide Ideation Scale (SIS).The experimental protocol included three primary cognitive tasks: (1) an emotional Stroop task to assess attentional biases toward affectively charged and suicide-related words, (2) a sentence processing task examining neural responses to self-referential statements varying in emotional and suicidal content, and (3) the Death-Brief Implicit Association Task (D-BIAT) to measure implicit associations with life and death. EEG and other physiological signals were recorded continuously throughout all tasks. Additionally, resting-state recordings (with eyes open and eyes closed) were obtained before, between, and after the emotional Stroop and sentence tasks.Neurophysiological data were acquired using 64-channel electroencephalography (EEG), electrooculography (EOG), electrocardiography (ECG), and galvanic skin response (GSR), and were supplemented with eye tracking and high-frame-rate facial video recordings. By integrating neural, behavioral, and physiological measures, the PRECOG study aimed to advance our understanding of cognitive and emotional processing in depression and suicidality, ultimately contributing to more precise risk assessment and targeted clinical intervention.

  PublisherDOI

• 75-Speaker Annot-16: A benchmark dataset for speech articulatory rt-MRI annotation with articulator contours and phonetic alignment

  2025-08-17

  articleOpen accessSenior author

  <p>High-quality speech articulatory databases are essential for advancing speech science and technology research. However, the lack of standardized annotations limits their full potential use and broad accessibility. In this context, we introduce 75-Speaker Annot-16, a comprehensive annotation dataset derived from the 75-Speaker vocal tract MRI database. Annot-16 provides phonetic alignments, articulator contour annotations, and handmade ground-truth articulator contours. Our annotation process integrates automated algorithms with expert verification to ensure accuracy and efficiency. To demonstrate its utility, we establish three benchmark tasks: speech phoneme recognition, articulatory contour segmentation, and articulatory phoneme recognition. Annot-16 can serve as a valuable resource for speech modeling, computer vision, and cross-modal learning, bridging engineering applications, speech science, and linguistic research.</p>

  PublisherOA PDFDOI

• Synergetic Usage of Hyperspectral Remote Sensing and Machine Learning in Detection and Mapping of Iron Ore Deposit Hotspots: A Case Study from Northern Odisha, India

  Journal of the Indian Society of Remote Sensing · 2025-07-12

  article1st authorCorresponding
  PublisherDOI

Recent grants

• Dynamics of Vocal Tract Shaping

  NIH · $416k · 2005–2009

• Collaborative Research: Modeling Creative and Emotive Improvisation in Theater Performance

  NSF · $422k · 2008–2012

• Dynamics of Vocal Tract Shaping

  NIH · $5.7M · 2005–2021

• Be a Scientist!

  NSF · $344k · 2010–2017

• Collaborative Research: Computational Behavioral Science: Modeling, Analysis, and Visualization of Social and Communicative Behavior

  NSF · $1.5M · 2010–2017

Frequent coauthors

• Athina P. Petropulu

  Rutgers, The State University of New Jersey

  488 shared

• Tülay Adalı

  University of Maryland, Baltimore County

  488 shared

• Ahmed H. Tewfik

  Apple (United Kingdom)

  488 shared

• Sergios Theodoridis

  National and Kapodistrian University of Athens

  486 shared

• Fernando Pereira

  426 shared

• R Baseil

  Indian Institute of Science Bangalore

  356 shared

• Vice Presdient

  The University of Texas at Austin

  320 shared

• K.V.S. Hari

  Indian Institute of Science Bangalore

  292 shared

Education

• Ph.D., Electrical Engineering

  University of California, Los Angeles

  1989

• M.S., Electrical Engineering

  University of California, Los Angeles

  1984

• B.S., Electrical Engineering

  Indian Institute of Technology, Madras

  1982

Awards & honors

• IEEE James L. Flanagan Speech and Audio Processing Award (20…
• Edward J. McCluskey Technical Achievement Award from the IEE…
• ISCA Medal for Scientific Achievement (2023)
• IEEE SPS Claude Shannon-Harry Nyquist Technical Achievement…
• ACM ICMI Sustained Accomplishment Award (2020)