activity
20242026
collaborators
Showing cs.CLShow all

5 papers · 1 filter

cs.CL2026

MoDiCoL: A Modular Diagnostic Continual Learning Dataset for Robust Speech Recognition

Theresa Pekarek Rosin, Matthias Kerzel, Stefan Wermter

Modern Automatic Speech Recognition (ASR) systems have made remarkable progress on standard benchmarks, yet performance gaps have emerged under real-world distribution shifts, caus…

cs.CL2026

Learning to Hear Hesitation: Continual Learning for Disfluency-Aware ASR

Henri-Leon Kordt, Theresa Pekarek Rosin, Jae Hee Lee +1

Despite advances in large-scale Automatic Speech Recognition (ASR), disfluent speech remains challenging, as state-of-the-art systems are often optimized to omit disfluencies, lead…

cs.CL2026

The Expert Strikes Back: Interpreting Mixture-of-Experts Language Models at Expert Level

Jeremy Herbst, Stefan Wermter, Jae Hee Lee

Mixture-of-Experts (MoE) architectures have become the dominant choice for scaling Large Language Models (LLMs), activating only a subset of parameters per token. While MoE archite…

cs.CL2026

SCoPE: Shift-Aware Speaker-Conditioned Priors for Emotion Recognition in Conversations

Burak Can Kaplan, Stefan Wermter

In conversations, human emotions are transient; however, they tend to persist across multiple utterances. For example, we rarely switch instantly between contrasting emotions such…

cs.CL2025

Large Language Model Data Generation for Enhanced Intent Recognition in German Speech

Theresa Pekarek Rosin, Burak Can Kaplan, Stefan Wermter

Intent recognition (IR) for speech commands is essential for artificial intelligence (AI) assistant systems; however, most existing approaches are limited to short commands and are…