MAD Speech: Measures of Acoustic Diversity of Speech

arXiv:2404.10419v1 Announce Type: cross
Abstract: Generative spoken language models produce speech in a wide range of voices, prosody, and recording conditions, seemingly approaching the diversity of natural speech. However, the extent to which generated speech is acoustically diverse remains unclear due to a lack of appropriate metrics. We address this gap by developing lightweight metrics of acoustic diversity, which we collectively refer to as MAD Speech. We focus on measuring five facets of acoustic diversity: voice, gender, emotion, accent, and …

abstract arxiv cs.cl diverse diversity eess.as gap generated generative however language language models metrics natural recording speech spoken type voices