Audio captioning on Clotho

11개 결과 · ⬇ CSV · JSON

SPIDEr

Rank	Model	SPIDEr	CIDEr	SPICE	BLEU-4	METEOR	ROUGE-L	FENSE	SPIDEr-FL	Extra Training Data	Paper	Code	Year
1	SLAM-AAC	0.332	0.515	0.148	–	0.197	–	0.540	0.330	✓	SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs	X-LANCE/SLAM-LLM	2024
2	LOAE	0.330	0.513	0.147	–	0.197	–	0.538	0.330	✓	Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding	frankenliu/LOAE	2024
3	MQ-Cap	0.319	0.496	0.143	18.1	0.192	–	–	–		Enhancing Retrieval-Augmented Audio Captioning with Generation-Assisted Multimodal Querying and Progressive Learning		2024
4	Ensemble	0.318	0.400	0.137	–	–	–	–	–	✓	THE DCASE 2021 CHALLENGE TASK 6 SYSTEM: AUTOMATED AUDIO CAPTIONING WITH WEAKLY SUPERVISED PRE-TRAING AND WORD SELECTION METHODS		2021
5	Audio Flamingo (Pengi trainset)	0.312	0.489	0.134	17.4	18.7	39.4	–	–	✓	Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities	NVIDIA/audio-flamingo	2024
6	Ensemble-RL	0.295	0.468	0.123	–	–	–	–	–	✓	THE SJTU SYSTEM FOR DCASE2021 CHALLENGE TASK 6: AUDIO CAPTIONING BASED ON ENCODER PRE-TRAINING AND REINFORCEMENT LEARNING	wsntxxn/AudioCaption	2021
7	Qwen-Audio	0.288	0.441	0.136	–	–	–	–	–	✓	Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models	alibaba-damo-academy/FunASR · qwenlm/qwen-audio	2023
8	Ensemble	0.207	0.319	0.094	–	–	–	–	–		The NTT DCASE2020 Challenge Task 6 system: Automated Audio Captioning with Keywords and Sentence Length Estimation		2020
9	VAST	–	0.519	–	19	19.3	40.8	–	–	✓	VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset	TXH-mercury/VALOR · txh-mercury/vast	2023
10	VALOR	–	0.423	–	16.2	17.4	38.2	–	–	✓	VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset	TXH-mercury/VALOR	2023
11	RNN-GRU-EncDec + VGGish + Word2Vec	–	0.18	–	–	–	–	–	–		Audio Captioning using Gated Recurrent Units		2020