SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline

๐Ÿ‘‹ Introduction: Extract the target voice from mixture speech given an enrollment speech.

๐Ÿ’ก To extract sound effects or music from audio, try using SoloAudio.

๐Ÿ”— Learn more about ๐ŸŽฏSoloSpeech on the SoloSpeech Repo.

Select Test Demo