publications

publications by categories in reversed chronological order. generated by jekyll-scholar. For latest publications please see [Google Scholar](https://scholar.google.com/citations?user=wiNtxkwAAAAJ&hl=en)

2026

  1. Taxonomy-Driven Performance Analysis of Retrieval-Based Open-ended Factuality Evaluation: A Medical Case Study
    Heyuan Huang, Jirui Dai, Jie Gao, and 5 more authors
    Under Review, ACL ARR May 2026, 2026
  2. Expert Annotation of AI Health Advice as Calibrated Measurement: Lessons from Experience for Rubric Design, Calibration, and Safety Evaluation
    Ryan Moore, Sonal Joshi, Mahsa Yarmohammadi, and 9 more authors
    Under Review, JMIR AI, 2026
  3. A Deployment Specific Safety Framework for Patient Facing Medical AI Chatbots
    Ahmed Hassoon, Heyuan Huang, Alexandra DeLucia, and 8 more authors
    Under Review, Nature, 2026
  4. Same Verdict, Different Reasons: LLM-as-a-Judge and Clinician Disagreement on Medical Chatbot Completeness
    Alexandra DeLucia, Heyuan Huang, Sonal Joshi, and 3 more authors
    arXiv preprint arXiv:2604.16383, 2026

2025

  1. Securing Speech Systems Against Adversarial and Poisoning Attacks
    Sonal Joshi
    PhD thesis, 2025
  2. Multi-Target Backdoor Attacks Against Speaker Recognition
    Alexandrine Fortier, Sonal Joshi, Thomas Thebaud, and 3 more authors
    arXiv preprint arXiv:2508.08559, 2025
  3. MedExpert: An Expert-Annotated Dataset for Medical Chatbot Evaluation
    Mahsa Yarmohammadi, Alexandra DeLucia, Lillian C Chen, and 8 more authors
    In Machine Learning for Health 2025, 2025

2024

  1. Unraveling Adversarial Examples against Speaker Identification–Techniques for Attack Detection and Victim Model Classification
    Sonal Joshi, Thomas Thebaud, Jesús Villalba, and 1 more author
    arXiv preprint arXiv:2402.19355, 2024
  2. Clean Label Attacks Against SLU Systems
    Henry Li Xinyuan, Sonal Joshi, Thomas Thebaud, and 3 more authors
    In 2024 IEEE Spoken Language Technology Workshop (SLT), 2024

2023

  1. Clustering unsupervised representations as defense against poisoning attacks on speech commands classification system
    Thomas Thebaud, Sonal Joshi, Henry Li, and 4 more authors
    In 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2023
  2. Joint Energy-Based Model for Robust Speech Classification System Against Dirty-Label Backdoor Poisoning Attacks
    Martin Sustek, Sonal Joshi, Henry Li, and 4 more authors
    In 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2023

2022

  1. Method and system for generating synthetic multi-conditioned data sets for robust automatic speech recognition
    Meetkumar Hemakshu SONI, Sonal JOSHI, and Ashish Panda
    May 2022
    US Patent 11,335,329
  2. Features search and selection techniques for speaker and speech recognition
    Ashish Panda, Sunilkumar KOPPARAPU, and Sonal Sunil JOSHI
    May 2022
    US Patent 11,322,156
  3. Defense against adversarial attacks on hybrid speech recognition using joint adversarial fine-tuning with denoiser
    Sonal Joshi, Saurabh Kataria, Yiwen Shao, and 4 more authors
    arXiv preprint arXiv:2204.03851, 2022
  4. Advest: Adversarial perturbation estimation to classify and detect adversarial attacks against speaker identification
    Sonal Joshi, Saurabh Kataria, Jesús Villalba, and 1 more author
    arXiv preprint arXiv:2204.03848, 2022
  5. Chunking Defense for Adversarial Attacks on ASR
    Yiwen Shao, Jesús Villalba, Sonal Joshi, and 3 more authors
    Proc. Interspeech 2022, 2022

2021

  1. Adversarial attacks and defenses for speech recognition systems
    Piotr Żelasko, Sonal Joshi, Yiwen Shao, and 4 more authors
    arXiv preprint arXiv:2103.17122, 2021
  2. Study of pre-processing defenses against adversarial attacks on state-of-the-art speaker recognition systems
    Sonal Joshi, Jesús Villalba, Piotr Żelasko, and 2 more authors
    IEEE Transactions on Information Forensics and Security, 2021
  3. Automatic detection and assessment of Alzheimer disease using speech and language technologies in low-resource scenarios.
    Raghavendra Pappagari, Jaejin Cho, Sonal Joshi, and 4 more authors
    In Interspeech, 2021
  4. Representation learning to classify and detect adversarial attacks against speaker and speech recognition systems
    Jesús Villalba, Sonal Joshi, Piotr Żelasko, and 1 more author
    arXiv preprint arXiv:2107.04448, 2021

2019

  1. Comparing front-end enhancement techniques and multiconditioned training for robust automatic speech recognition
    Meet H Soni, Sonal Joshi, and Ashish Panda
    In International Conference on Text, Speech, and Dialogue, 2019
  2. Generative Noise Modeling and Channel Simulation for Robust Speech Recognition in Unseen Conditions.
    Meet H Soni, Sonal Joshi, and Ashish Panda
    In INTERSPEECH, 2019
  3. Front-End Feature Compensation and Denoising for Noise Robust Speech Emotion Recognition.
    Rupayan Chakraborty, Ashish Panda, Meghna Pandharipande, and 2 more authors
    In INTERSPEECH, 2019

2018

  1. NMF based front-end processing in multichannel distant speech recognition
    Nikhil Mohanan, Premanand Nayak, Rajbabu Velmurugan, and 6 more authors
    In Proc. CHiME 2018 Workshop on Speech Processing in Everyday Environments, 2018
  2. CHiME 2018 Workshop: Enhancing beamformed audio using Time Delay Neural Network De-noising Autoencoder
    Sonal Joshi, Ashish Panda, Meet Soni, and 6 more authors
    System, 2018
  3. Enhanced denoising auto-encoder for robust speech recognition in unseen noise conditions
    Sonal Joshi, Ashish Panda, and Biswajit Das
    In International Symposium on Chinese Spoken Language Processing (ISCSLP), 2018