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

> Research article (INTERSPEECH 2023, 2023) · cited 10× · AI/ML

**Wikidata**: [openalex:W4385822255](https://www.wikidata.org/wiki/openalex:W4385822255)  
**Source**: https://4ort.xyz/entity/tokensplit-using-discrete-speech-representations-for-direct-refined-and-transcript-conditioned-speech-separation-and-rec