Litcius/Paper detail

Self-Supervised Speech Representations are More Phonetic than Semantic

Kwanghee Choi, Ankita Pasad, Tomohiko Nakamura, Satoru Fukayama, Karen Livescu, Shinji Watanabe

202422 citationsDOI

Topics & Concepts

Computer scienceNatural language processingSpeech recognitionArtificial intelligenceSpeech and dialogue systemsSpeech Recognition and SynthesisNatural Language Processing Techniques
Self-Supervised Speech Representations are More Phonetic than Semantic | Litcius