activity
20242026
collaborators

13 papers

eess.AS2026

Phoneme-First Prediction for LLM-Based Speech Recognition

Jakob Poncelet, Hugo Van hamme

Recent research has explored integrating Large Language Models (LLMs) with speech encoders to create speech-augmented LLMs capable of contextualized speech recognition. The main ch…

eess.AS2026

Speech Encoder Fusion for LLM-based Automatic Speech Recognition

Jakob Poncelet, Hugo Van hamme

Speech-aware large language models (LLMs) can incorporate speech through pre-trained acoustic encoders that project speech features into the LLM embedding space. While the choice o…

eess.AS2026

Towards Deep Contextual Reasoning from Broad Descriptions for ASR with Speech-LLM via Metadata-Driven Reasoning Chains

Jakob Poncelet, Hugo Van hamme

Speech recognition often fails on rare, domain-specific terms and context-related named entities. Existing contextualization techniques typically bias decoding with keywords or phr…

eess.AS2026

Parameter-Efficient Continual Learning for Automatic Speech Recognition

Steven Vander Eeckt, Hugo Van hamme

Speech foundation models enable strong general-purpose ASR and are attractive for downstream adaptation. However, their size and the catastrophic forgetting induced by sequential f…

cs.CL2026

GLoRIA: Gated Low-Rank Interpretable Adaptation for Dialectal ASR

Pouya Mehralian, Melissa Farasyn, Anne Breitbarth +2

Automatic Speech Recognition (ASR) in dialect-heavy settings remains challenging due to strong regional variation and limited labeled data. We propose GLoRIA, a parameter-efficient…

eess.AS2026

Inverse-Hessian Regularization for Continual Learning in ASR

Steven Vander Eeckt, Hugo Van hamme

Catastrophic forgetting remains a major challenge for continual learning (CL) in automatic speech recognition (ASR), where models must adapt to new domains without losing performan…