3 papers
eess.AS2025
In-context learning capabilities of Large Language Models to detect suicide risk among adolescents from speech transcripts
Filomene Roquefort, Alexandre Ducorroy, Rachid Riad
Early suicide risk detection in adolescents is critical yet hindered by scalability challenges of current assessments. This paper presents our approach to the first SpeechWellness…
eess.AS2025
Robust fine-tuning of speech recognition models via model merging: application to disordered speech
Alexandre Ducorroy, Rachid Riad
Automatic Speech Recognition (ASR) has advanced with Speech Foundation Models (SFMs), yet performance degrades on dysarthric speech due to variability and limited data. This study…
eess.AS2025
Quantized Approximate Signal Processing (QASP): Towards Homomorphic Encryption for audio
Tu Duyen Nguyen, Adrien Lesage, Clotilde Cantini +1
Audio and speech data are increasingly used in machine learning applications such as speech recognition, speaker identification, and mental health monitoring. However, the passive…