Paper at ASRU 2025: 'Evaluation of LLMs in Speech is Often Flawed: Test Set Contamination in Large Language Models for Speech Recognition'
Paper at NeurIPS 2024: 'REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR'
Paper at Interspeech 2024: 'CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems' (with dataset and code)
Paper at ICASSP 2024: 'AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models' (with code and submission platform)
Paper at ICASSP 2023: 'Cascading and Direct Approaches to Unsupervised Constituency Parsing on Spoken Sentences'
Paper at SLT 2022: 'On the Utility of Self-supervised Models for Prosody-related Tasks' (Best Paper Award)