Prem Seetharaman

PromptSep-Speaker: Generative Target Speaker Extraction via Multimodal Prompting and Semantic Alignment

Generative TSE model PromptSep-Speaker is proposed, a generative TSE model based on latent diffusion that unifies four interchangeable cues: speaker temporal order, transcript, enrollment audio, and speaker caption that achieves state-of-the-art performance over TSE and universal source separation baselines, improving...

CrossEdit: Cross-Modal Training Enables Rich Audio-Visual Editing

CrossEdit is presented, a unified omni-modal editing model for images, audio, and video that performs AV movie scene edits zero-shot through cross-modal transfer and proposes AV-FES, a metric that jointly scores instruction following and consistency.

SMORPH: PLAYABLE SOUND MORPHING WITH DIFFUSION MODELS