sam-audio
llm_sam_audio_datasam-audio-bench
Citation
If you use SAM Audio Judge in your research, please use the following BibTex entry:
@article{shi2025samaudio,
title={SAM Audio: Segment Anything in Audio},
author={Bowen Shi and Andros Tjandra and John Hoffman and Helin Wang and Yi-Chiao Wu and Luya Gao and Julius Richter and Matt Le and Apoorv Vyas and Sanyuan Chen and Christoph Feichtenhofer and Piotr Doll{\'a}r and Wei-Ning Hsu and Ann Lee},
year={2025},
url={https://arxiv.org/abs/2512.18099}
}
sam_audio_base_test
Audio Source Separation Blind Spots for Musical Instrument Segmentation
This dataset documents blind spots discovered in an audio source separation model when tested on various instrument isolation tasks.
Model Tested
SAM-Audio Base (Segment Anything Model for Audio)
Model: facebook/sam-audio-base
SAM-Audio is a foundation model for isolating sounds in audio using text, visual, or temporal prompts.
I have evaluated the model’s text prompting capability for instrument… See the full description on the dataset page: https://huggingface.co/datasets/amitpant7/sam_audio_base_test.sam-audio-musdb18hq-testsam-audio-benchsam-audio-musdb18hq-test