14 citations · 17 across the 6 of their papers we have counts for
5 papers · 1 filter
Local Prototype Reconstruction for Text-Compatible Speech-to-LLM Bridge Pretraining
Xinnian Zhao, Chia-Hua Wu, Pu Wang +1
Speech-to-LLM systems often connect a frozen speech encoder to a frozen large language model (LLM) through a small trainable bridge. The bridge is usually treated as plumbing, but…
Selective Lookahead for Attention-Based Streaming ASR
Yichen Jia, Bastiaan Tamm, Hugo Van hamme
End-to-end attention-based speech recognition is accurate offline but hard to stream: outputs can depend on future audio, and a little future context per layer makes the lookahead…
ROAM-ASD: Robust Open-World Active Speaker Detection with Flexible Multimodal Fusion
Pu Wang, Hugo Van hamme
Active speaker detection (ASD) requires reliable association between visible faces and acoustic speech, yet existing systems often degrade under challenging domains or incomplete o…
CGaLore: Curvature-Guided GaLore for Memory-Efficient Continual Adaptation of ASR Foundation Models
Steven Vander Eeckt, Hugo Van hamme
Automatic speech recognition models suffer from catastrophic forgetting when adapted to new domains, accents, or downstream tasks. This problem becomes increasingly important with…
Leveraging Beam Search Information for Confidence Estimation in E2E ASR
Yichen Jia, Hugo Van hamme
To estimate confidence for end-to-end Automatic Speech Recognition (ASR) systems, recent research has proposed Confidence Estimation Modules that incorporate features from the back…