We introduce a new approach, the ContrastiveTransformer, that produces acoustic word embeddings (AWE
This research addresses the challenge of developing speech applications for zero-resource languages
We consider hate speech detection through keyword spotting on radio broadcasts. One approach is to b
Cross-Lingual Word Embeddings (CLWEs) are a key component to transfer linguistic information learnt
We predict lexical stress in Arabic varieties from syllable structure, modeling stress assignment as
International Heat, a team of five graduate students, spent the past four months designing a thermal