SpeechAlign: a Framework for Speech Translation Alignment Evaluation

arXiv:2309.11585v2 Announce Type: replace
Abstract: Speech-to-Speech and Speech-to-Text translation are currently dynamic areas of research. In our commitment to advance these fields, we present SpeechAlign, a framework designed to evaluate the underexplored field of source-target alignment in speech models. The SpeechAlign framework has two core components. First, to tackle the absence of suitable evaluation datasets, we introduce the Speech Gold Alignment dataset, built upon a English-German text translation gold alignment dataset. Secondly, we introduce two novel metrics, Speech Alignment Error …

abstract advance alignment arxiv commitment components core cs.cl dynamic evaluation fields framework research speech speech-to-text text translation type