Yi Zhu

About Me

I am currently a Senior Applied Scientist at Reality Defender. I have obtained my phd from Multisensory Signal Analysis and Enhancement Lab (MuSAE), National Institute of Scientific Research (INRS) (Montreal, Canada) in Feb 2025.

My recent research has been centered around predictive and generative pre-training of speech foundation models, and post-training of audio language models. I am very much interested in the applications of human-centered signals, such as audio and speech, physiological signals (e.g., EMG), humidity, temperature, etc.

Awards

• [June. 2023] Rising Star in Signal Processing at ICASSP 2023 .

News

• [May, 2026] Paper accepted at ICML 2026 on a new voice foundation model pretraining recipe.
• [April, 2026] Paper accepted at ACL 2026 on exploring in-context learning of audio language models for deepfake detection.
• [Oct, 2025] Release a unified audio deepfake detection benchmarking toolkit .
• [Sep, 2025] Foundation model for health applications available now on IEEE-JBHI .

Recent Publications

• [May, 2026] Alethia: A Foundational Encoder for Voice Deepfakes, accepted at ICML 2026
• [April, 2026] ICLAD: In-Context Learning with Comparison-Guidance for Audio Deepfake Detection, accepted at ACL Findings 2026
• [Sept, 2024] SLIM: Style-Linguistics Mismatch Model for Generalized Audio Deepfake Detection, accepted at NeurIPS 2024
• [Sept, 2024] WavRx: a Disease-Agnostic, Generalizable, and Privacy-Preserving Speech Health Diagnostic Model, published at IEEE Journal of Biomedical Health Informatics
• [Aug. 2024] MSPB:a longitudinal multi-sensor dataset with phenotypic trait measurements from honeybees, published at Nature Scientific Data
• [Jan, 2024] On the Impact of Voice Anonymization on Speech-Based Health Diagnostics, published at IEEE Transactions on Information Forensics and Security

Datasets, toolboxes, and other useful resources

• AUDDT: Audio Unified Deepfake Detection Benchmarking Toolkit
• WavRx: a Foundation Model for speech-based health applications
• Multimodal dataset catalog
• Segmented and annotated COVID-19 cough phases
• Modulation Dynamics Block for Generalizable Deepfake Speech Detection
• Speech modulation spectrum toolbox
• Lecture code for the online workshop with UPFE (Brazil)