Zahra Omidi

Zahra Omidi

PhD Candidate · Speech AI
Speech AI · Human-Centered Machine Learning

About Me

I am a PhD student in Computer Science at the University of Texas at Dallas, advised by Dr. John H. L. Hansen at the Center for Robust Speech Systems. My research focuses on speech systems that can recognize and evaluate speaker state, paralinguistic cues, and perceptual uncertainty in naturalistic speech.

Interests

  • Speech Foundation Models
  • Vocal Effort, Stress & Emotion in Speech
  • Human-Centered AI
  • Self-Supervised Representation Learning

Education

  • 🎓
    Ph.D. in Computer Science, 2023 – Present University of Texas at Dallas
  • 🎓
    M.S. in Computer Science, 2025 University of Texas at Dallas
  • 🎓
    M.S. in Computer Science, 2019 – 2022 University of Tehran
  • 🎓
    B.S. in Computer Science, 2014 – 2018 University of Tehran
Publications

Selected Publications

Entropy-aware curriculum for speech emotion recognition
Learning from Annotation Uncertainty: Entropy-Aware Curriculum for Speech Emotion Recognition
Zahra Omidi and John H. L. Hansen · arXiv preprint, 2026
Entropy-aware curriculum learning for speech emotion recognition under annotator disagreement, using distribution-based supervision to better model perceptual uncertainty in speech.
PDFarXivCodeWebsite
Vocal effort classification with WavLM
Advancing Speaker Based Vocal Effort Classification with WavLM and Data Augmentation in Naturalistic Non-Calibrated Speech Recordings
Zahra Omidi and John H. L. Hansen · ICASSP 2026
Speaker-based vocal effort classification using WavLM representations and augmentation strategies for robust paralinguistic speech modeling in naturalistic recordings.
PDFPublisherCode coming soon
Handwritten digit string recognition
On Usage of an End-to-End Deep Neural Architecture for Handwritten Digit String Recognition
Zahra Omidi and Bagher BabaAli · Signal, Image and Video Processing, 2024
End-to-end handwritten digit string recognition with gated convolutional modeling, CTC loss, and augmentation strategies.
PublisherCode unavailable
Experience

Research Experience

2023 — Present
Ph.D. Researcher
Center for Robust Speech Systems, University of Texas at Dallas
Advised by Dr. John H. L. Hansen. My research develops speech foundation model methods for understanding how people speak beyond words, including emotion, vocal effort, physical stress, and other speaker-state cues in naturalistic speech.
Contact

Get in touch

I am open to research internship opportunities in speech AI, audio understanding, speech foundation models, and human-centered machine learning.

Email Google Scholar GitHub LinkedIn