11 papers
JASTIN: Aligning LLMs for Zero-Shot Audio and Speech Evaluation via Natural Language Instructions
Leying Zhang, Bowen Shi, Haibin Wu +2
The rapid advancement of generative audio models has outpaced the development of robust evaluation methodologies. Existing objective metrics and general multimodal large language m…
SAM Audio Judge: A Unified Multimodal Framework for Perceptual Evaluation of Audio Separation
Helin Wang, Bowen Shi, Andros Tjandra +6
The performance evaluation remains a complex challenge in audio separation, and existing evaluation metrics are often misaligned with human perception, course-grained, relying on g…
Mosaic: Unlocking Long-Context Inference for Diffusion LLMs via Global Memory Planning and Dynamic Peak Taming
Liang Zheng, Bowen Shi, Yitao Hu +5
Diffusion-based large language models (dLLMs) have emerged as a promising paradigm, utilizing simultaneous denoising to enable global planning and iterative refinement. While these…
SAM Audio: Segment Anything in Audio
Bowen Shi, Andros Tjandra, John Hoffman +11
General audio source separation is a key capability for multimodal AI systems that can perceive and reason about sound. Despite substantial progress in recent years, existing separ…
MR-FlowDPO: Multi-Reward Direct Preference Optimization for Flow-Matching Text-to-Music Generation
Alon Ziv, Sanyuan Chen, Andros Tjandra +3
A key challenge in music generation models is their lack of direct alignment with human preferences, as music evaluation is inherently subjective and varies widely across individua…
Audiobox TTA-RAG: Improving Zero-Shot and Few-Shot Text-To-Audio with Retrieval-Augmented Generation
Mu Yang, Bowen Shi, Matthew Le +2
This work focuses on improving Text-To-Audio (TTA) generation on zero-shot and few-shot settings (i.e. generating unseen or uncommon audio events). Inspired by the success of Retri…