10 papers
AudioChat: Unified Audio Storytelling, Editing, and Understanding with Transfusion Forcing
William Chen, Prem Seetharaman, Rithesh Kumar +4
Despite recent breakthroughs, audio foundation models struggle in processing complex multi-source acoustic scenes. We refer to this challenging domain as audio stories, which can h…
Generative Audio Extension and Morphing
Prem Seetharaman, Oriol Nieto, Justin Salamon
In audio-related creative tasks, sound designers often seek to extend and morph different sounds from their libraries. Generative audio models, capable of creating audio using exam…
TAC: Timestamped Audio Captioning
Sonal Kumar, Prem Seetharaman, Ke Chen +8
Large Audio Language Models struggle to disentangle overlapping events in complex acoustic scenes, yielding temporally inconsistent captions and frequent hallucinations. We introdu…
Audiocards: Structured Metadata Improves Audio Language Models For Sound Design
Sripathi Sridhar, Prem Seetharaman, Oriol Nieto +2
Sound designers search for sounds in large sound effects libraries using aspects such as sound class or visual context. However, the metadata needed for such search is often missin…
Mix2Morph: Learning Sound Morphing from Noisy Mixes
Annie Chu, Hugo Flores GarcÃa, Oriol Nieto +3
We introduce Mix2Morph, a text-to-audio diffusion model fine-tuned to perform sound morphing without a dedicated dataset of morphs. By finetuning on noisy surrogate mixes at higher…
PromptSep: Generative Audio Separation via Multimodal Prompting
Yutong Wen, Ke Chen, Prem Seetharaman +7
Recent breakthroughs in language-queried audio source separation (LASS) have shown that generative models can achieve higher separation audio quality than traditional masking-based…