Main content
Evaluation of Automatic Speech Recognition for Conversational Speech in Dutch, English and German: What Goes Missing?
Date created: | Last Updated:
: DOI | ARK
Creating DOI. Please wait...
Category: Project
Description: As voice user interfaces and conversational agents grow in importance, automatic speech recognition (ASR) encounters increasingly free-form and informal input data. Conversational speech is at once the most challenging and the most ecologically relevant type of data for speech recognition in this context. Here we evaluate the performance of several ASR engines on conversational speech in three languages, focusing on the fate of backchannels and other interactionally relevant elements of talk. We propose forms of error analysis based on ngram salience scoring that can complement default measures like word error rates (WER) and are more informative of ASR’s ability to live up to the task of accurately representing real-world interaction.