AVID: A speech database for machine learning studies on vocal intensity

Paavo Alku, Manila Kodali, Laura Laaksonen, Sudarsana Reddy Kadiri

Abstract: Highlights•An open database called AVID is launched to support research of vocal intensity.•AVID includes calibrated recordings of speech produced in four intensity categories.•Both speech and electroglottography signals are provided by AVID.•AVID provides a rich set of labels for ML studies of vocal intensity.•Classification of intensity category and prediction of SPL are studied with ML.