Litcius/Paper detail

TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognition

Hakan Erdoğan, Scott Wisdom, Xuankai Chang, Zalán Borsos, Marco Tagliasacchi, Neil Zeghidour, John R. Hershey

202310 citationsDOI

Topics & Concepts

Speech recognitionComputer scienceVoice activity detectionSpeech processingArtificial intelligenceNatural language processingSpeech Recognition and SynthesisSpeech and Audio ProcessingMusic and Audio Processing
TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognition | Litcius