ML Research Wiki / Benchmarks / Audio captioning / AudioCaps

AudioCaps

Audio captioning Benchmark

Performance Over Time

📊 Showing 13 results | 📏 Metric: SPIDEr

Top Performing Models

Rank Model Paper SPIDEr Date Code
1 SLAM-AAC 📚 SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs 0.84 2024-10-12 📦 X-LANCE/SLAM-LLM
2 AutoCap Taming Data and Transformers for Audio Generation 0.83 2024-06-27 📦 snap-research/GenAU
3 EnCLAP++-large 📚 EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning Performance 0.82 2024-09-02 📦 jaeyeonkim99/enclap
4 LOAE 📚 Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding 0.82 2024-06-19 📦 frankenliu/LOAE
5 EnCLAP++-base 📚 EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning Performance 0.82 2024-09-02 📦 jaeyeonkim99/enclap
6 EnCLAP-large EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning 0.80 2024-01-31 📦 jaeyeonkim99/enclap
7 EnCLAP-base EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning 0.78 2024-01-31 📦 jaeyeonkim99/enclap
8 AL-MixGen Exploring Train and Test-Time Augmentations for Audio-Language Learning 0.76 2022-10-31 -
9 CNN+Transformer Audio Captioning Transformer 0.69 2021-07-21 📦 XinhaoMei/ACT
10 MQ-Cap 📚 Enhancing Retrieval-Augmented Audio Captioning with Generation-Assisted Multimodal Querying and Progressive Learning 0.30 2024-10-14 -

All Papers (13)

X-LANCE/SLAM-LLM
snap-research/GenAU
jaeyeonkim99/enclap
frankenliu/LOAE
jaeyeonkim99/enclap
jaeyeonkim99/enclap
jaeyeonkim99/enclap

Audio Captioning Transformer

2021
CNN+Transformer
XinhaoMei/ACT
naver-intel-co-lab/gaudi-lavcap Hyeongkeun/LAVCap
TXH-mercury/VALOR txh-mercury/vast
TXH-mercury/VALOR