SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline
๐ Introduction: Extract the target voice from mixture speech given an enrollment speech.
๐ก To extract sound effects or music from audio, try using SoloAudio.
๐ Learn more about ๐ฏSoloSpeech on the SoloSpeech Repo.