Title: EmphAssess : a Prosodic Benchmark on Assessing Emphasis Transfer in Speech-to-Speech Models
Authors: Maureen de Seyssel, Antony D’Avirro, Adina Williams, Emmanuel Dupoux
Published: 21st December 2023 (Thursday) @ 17:47:33
Link: http://arxiv.org/abs/2312.14069v1
Abstract
We introduce EmphAssess, a prosodic benchmark designed to evaluate the capability of speech-to-speech models to encode and reproduce prosodic emphasis. We apply this to two tasks: speech resynthesis and speech-to-speech translation. In both cases, the benchmark evaluates the ability of the model to encode emphasis in the speech input and accurately reproduce it in the output, potentially across a change of speaker and language. As part of the evaluation pipeline, we introduce EmphaClass, a new model that classifies emphasis at the frame or word level.