Riccardo Fusaroli

Vocal markers of autism: assessing the generalizability of machine learning models

This study evaluates how well machine learning models identify autism from speech across different contexts and languages, finding limited generalizability.

Towards a cumulative science of vocal markers of autism: a cross-linguistic meta-analysis-based investigation of acoustic markers in American and Danish autistic children

The paper conducts a cross-linguistic meta-analysis of acoustic markers in autistic children, identifying reliable but small acoustic differences and highlighting the need for more diverse datasets.

A Generalizable Speech Emotion Recognition Model Reveals Depression and Remission

This paper develops a speech emotion recognition model trained on non-clinical data to detect depression and remission in clinical speech, achieving an AUC of 0.71.

Acoustic Measures of Prosody in Right-Hemisphere Damage: A Systematic Review and Meta-Analysis

This paper reviews acoustic prosody studies in right-hemisphere damage, finding weak effects and highlighting methodological limitations.

Voice Patterns in Schizophrenia: A Systematic Review and Bayesian Meta-Analysis

This paper conducts a systematic review and Bayesian meta-analysis of voice atypicalities in schizophrenia, identifying weak to moderate acoustic differences linked to negative symptoms and social impairments.