5 papers
When Entanglement Lower-Bounds Disparity: Auditing and Repairing Demographic Fairness in Audio Understanding Models
Kian Shamsaie, Iman Modarressi
Speech technology penalizes some voices: recognition errs nearly twice as often for Black speakers, and accuracy declines for second-language accents and older speakers. We introdu…
Psychoacoustically Aligned Latent Smoothing for Adversarial Robustness of Full-Duplex Speech-to-Speech Dialogue Models
Kian Shamsaie, Iman Modarressi
End-to-end speech-to-speech dialogue models listen and speak simultaneously, so a continuously open acoustic channel is exposed to adversarial manipulation. We formalize impercepti…
Neither Silence nor Overlap Is Failure: Intent-Conditioned Evaluation of Turn-Taking in Full-Duplex Spoken Dialogue Models
Kian Shamsaie, Iman Modarressi
Benchmarks for full-duplex spoken dialogue models score turn-taking with binary fixed-window rules that reward immediate response or silence by completeness of the prior turn. We a…
A Contrastive Teacher-Student Framework for Novelty Detection under Style Shifts
Hossein Mirzaei, Mojtaba Nafez, Moein Madadi +12
There have been several efforts to improve Novelty Detection (ND) performance. However, ND methods often suffer significant performance drops under minor distribution shifts caused…
Scanning Trojaned Models Using Out-of-Distribution Samples
Hossein Mirzaei, Ali Ansari, Bahar Dibaei Nia +10
Scanning for trojan (backdoor) in deep neural networks is crucial due to their significant real-world applications. There has been an increasing focus on developing effective gener…