Publications
Papers, preprints, and manuscripts, grouped by publication year. My name is bolded; * indicates equal contribution. See Google Scholar.
2026
Louder, Longer, Livelier: Acoustic Shortcuts and Underspecified Rationales in Speech LLM Judges
arXiv preprint
SpeechCritic: Learning a Diagnostic Speech Judge from Limited Human Preferences
arXiv preprint
Where Speech Enhancement Hurts Recognition: An Inference Time Polar Projection Diagnosis
arXiv preprint
Beyond Semantic Manipulation: Token-Space Attacks on Reward Models
arXiv preprint
TagSpeech: End-to-End Multi-Speaker ASR and Diarization with Fine-Grained Temporal Grounding
ACL 2026 · Main conference · Oral
Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation
ACL 2026 · Main conference
Auden-Voice: General-Purpose Voice Encoder for Speech and Language Understanding
ICASSP 2026
2025
Identifying and Calibrating Overconfidence in Noisy Speech Recognition
ASRU 2025
Beyond Speaker Identity: Text Guided Target Speech Extraction
ICASSP 2025
Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning
ICLR 2025 · Oral
What makes listening comprehension difficult?: A feature-based machine learning approach to understanding item difficulty
Applied Linguistics 47(2), 406–428 · Online first: 2025
2024
Release from same-talker speech-in-speech masking: Effects of masker intelligibility and other contributing factors
The Journal of the Acoustical Society of America 156(5), 2960–2973