ParaCLAP -- Towards a general language-audio model for computational
paralinguistic tasks
ParaCLAP -- Towards a general language-audio model for computational
paralinguistic tasks
Contrastive language-audio pretraining (CLAP) has recently emerged as a method for making audio analysis more generalisable. Specifically, CLAP-style models are able to `answer' a diverse set of language queries, extending the capabilities of audio models beyond a closed set of labels. However, CLAP relies on a large set of (audio, …