paper-with-me

Papers

RECAP: Retrieval-Augmented Audio Captioning

2023-09-18 · Sreyan Ghosh, Sonal Kumar, Chandra Kiran Reddy Evuru, Ramani Duraiswami, Dinesh Manocha

We present RECAP (REtrieval-Augmented Audio CAPtioning), a novel and effective audio captioning system that generates captions conditioned on an input audio and other captions similar to the audio retrieved from a datastore. Additionally, our proposed method can transfer to any domain without the need for any additional fine-tuning. To generate a caption for an audio sample, we leverage an audio-text model CLAP to retrieve captions similar to it from a replaceable datastore, which are then used to construct a prompt. Next, we feed this prompt to a GPT-2 decoder and introduce cross-attention layers between the CLAP encoder and GPT-2 to condition the audio for caption generation. Experiments on two benchmark datasets, Clotho and AudioCaps, show that RECAP achieves competitive performance in in-domain settings and significant improvements in out-of-domain settings. Additionally, due to its capability to exploit a large text-captions-only datastore in a training-free fashion, RECAP shows unique capabilities of captioning novel audio events never seen during training and compositional audios with multiple events. To promote research in this space, we also release 150,000+ new weakly labeled captions for AudioSet, AudioCaps, and Clotho.

📄 PDF Abstract BibTeX arXiv:2309.09836

Code (1)

sreyan88/recap 공식 구현 pytorch

Tasks

AudioCapsAudio captioningCaption GenerationDecoderRetrievalRetrieval-augmented Few-shot In-context Audio Captioning

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Residual Connection 설명 없음
Adam 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Discriminative Fine-Tuning Discriminative Fine-Tuning is a fine-tuning strategy that is used for ULMFiT type models. Instead of using the same learning rate…
Weight Decay 설명 없음
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Enhancing Retrieval-Augmented Audio Captioning with Generation-Assisted Multimodal Querying and Progressive Learning

2024-10-14 · Choi Changin, Lim Sungjun, Rhee Wonjong

Retrieval-augmented generation can improve audio captioning by incorporating relevant audio-text pairs from a knowledge base. Existing methods typically rely solely on the input audio as a unimodal retrieval query. In co…

AudioCapsAudio captioningRAGRetrieval+1

ReCap: Event-Aware Image Captioning with Article Retrieval and Semantic Gaussian Normalization

2025-09-01 · Thinh-Phuc Nguyen, Thanh-Hai Nguyen, Gia-Huy Dinh, Lam-Huy Nguyen 외 arxiv

Image captioning systems often produce generic descriptions that fail to capture event-level semantics which are crucial for applications like news reporting and digital archiving. We present ReCap, a novel pipeline for …

Image CaptioningImage Retrieval

Retrieval-Augmented Approach for Unsupervised Anomalous Sound Detection and Captioning without Model Training

2024-10-29 · Ryoya Ogura, Tomoya Nishida, Yohei Kawaguchi

This paper proposes a method for unsupervised anomalous sound detection (UASD) and captioning the reason for detection. While there is a method that captions the difference between given normal and anomalous sound pairs,…

Retrieval

Automated Audio Captioning and Language-Based Audio Retrieval

2022-07-08 · Clive Gomes, Hyejin Park, Patrick Kollman, Yi Song 외

This project involved participation in the DCASE 2022 Competition (Task 6) which had two subtasks: (1) Automated Audio Captioning and (2) Language-Based Audio Retrieval. The first subtask involved the generation of a tex…

Audio captioningRetrieval

DRCap: Decoding CLAP Latents with Retrieval-Augmented Generation for Zero-shot Audio Captioning

2024-10-12 · Xiquan Li, Wenxi Chen, Ziyang Ma, Xuenan Xu 외

While automated audio captioning (AAC) has made notable progress, traditional fully supervised AAC models still face two critical challenges: the need for expensive audio-text pair data for training and performance degra…

Audio captioningLarge Language ModelRetrievalRetrieval-augmented Generation+1