1 citations · 1 across the 4 of their papers we have counts for
6 papers
Learning Compositional Latent Structure with Vector Networks
Niclas Pokel, Benjamin F. Grewe
Deep networks are powerful function approximators, but they typically store many different computations in shared weight matrices, making it difficult to selectively reuse or adapt…
When Audio-Language Models Fail to Leverage Multimodal Context for Dysarthric Speech Recognition
Pehuén Moure, Pehuén Moure, Niclas Pokel +5
Automatic speech recognition (ASR) systems remain brittle on dysarthric and other atypical speech. Recent audio-language models raise the possibility of improving performance by co…
Demonstration of Adapt4Me: An Uncertainty-Aware Authoring Environment for Personalizing Automatic Speech Recognition to Non-normative Speech
Niclas Pokel, Yiming Zhao, Pehuén Moure +2
Personalizing Automatic Speech Recognition (ASR) for non-normative speech remains challenging because data collection is labor-intensive and model training is technically complex.…
Variational Low-Rank Adaptation for Personalized Impaired Speech Recognition
Niclas Pokel, Pehuén Moure, Roman Boehringer +2
Speech impairments resulting from congenital disorders, such as cerebral palsy, down syndrome, or apert syndrome, as well as acquired brain injuries due to stroke, traumatic accide…
Data-Efficient ASR Personalization for Non-Normative Speech Using an Uncertainty-Based Phoneme Difficulty Score for Guided Sampling
Niclas Pokel, Pehuén Moure, Roman Böhringer +1
ASR systems struggle with non-normative speech due to high acoustic variability and data scarcity. We propose a data-efficient method using phoneme-level uncertainty to guide fine-…
Adapting Foundation Speech Recognition Models to Impaired Speech: A Semantic Re-chaining Approach for Personalization of German Speech
Niclas Pokel, Pehuén Moure, Roman Boehringer +1
Speech impairments caused by conditions such as cerebral palsy or genetic disorders pose significant challenges for automatic speech recognition (ASR) systems. Despite recent advan…