paper-with-me

Papers

CLAP-ART: Automated Audio Captioning with Semantic-rich Audio Representation Tokenizer

2025-06-01 · Daiki Takeuchi, Binh Thien Nguyen, Masahiro Yasuda, Yasunori Ohishi, Daisuke Niizumi, Noboru Harada

Automated Audio Captioning (AAC) aims to describe the semantic contexts of general sounds, including acoustic events and scenes, by leveraging effective acoustic features. To enhance performance, an AAC method, EnCLAP, employed discrete tokens from EnCodec as an effective input for fine-tuning a language model BART. However, EnCodec is designed to reconstruct waveforms rather than capture the semantic contexts of general sounds, which AAC should describe. To address this issue, we propose CLAP-ART, an AAC method that utilizes ``semantic-rich and discrete'' tokens as input. CLAP-ART computes semantic-rich discrete tokens from pre-trained audio representations through vector quantization. We experimentally confirmed that CLAP-ART outperforms baseline EnCLAP on two AAC benchmarks, indicating that semantic-rich discrete tokens derived from semantically rich AR are beneficial for AAC.

📄 PDF Abstract BibTeX arXiv:2506.00800

Code (0)

등록된 구현이 없습니다.

Tasks

Audio captioningLanguage ModelingLanguage ModellingQuantization

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Adam 설명 없음

Similar Papers 제목 키워드 기반

EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning

2024-01-31 · Jaeyeon Kim, JaeYoon Jung, Jinjoo Lee, Sang Hoon Woo

We propose EnCLAP, a novel framework for automated audio captioning. EnCLAP employs two acoustic representation models, EnCodec and CLAP, along with a pretrained language model, BART. We also introduce a new training obj…

AudioCapsAudio captioningLanguage ModelingLanguage Modelling

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

Semantic-Aware Confidence Calibration for Automated Audio Captioning

2025-12-11 · Lucas Dunker, Sai Akshay Menta, Snigdha Mohana Addepalli, Venkata Krishna Rayalu Garapati arxiv

Automated audio captioning models frequently produce overconfident predictions regardless of semantic accuracy, limiting their reliability in deployment. This deficiency stems from two factors: evaluation metrics based o…

Semantic SimilarityAudio captioning

EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning Performance

2024-09-02 · Jaeyeon Kim, Minjeon Jeon, JaeYoon Jung, Sang Hoon Woo 외

In this work, we aim to analyze and optimize the EnCLAP framework, a state-of-the-art model in automated audio captioning. We investigate the impact of modifying the acoustic encoder components, explore pretraining with …

AudioCapsAudio captioningLanguage ModellingReranking

Training Audio Captioning Models without Audio

2023-09-14 · Soham Deshmukh, Benjamin Elizalde, Dimitra Emmanouilidou, Bhiksha Raj 외

Automated Audio Captioning (AAC) is the task of generating natural language descriptions given an audio stream. A typical AAC system requires manually curated training data of audio segments and corresponding text captio…

Audio captioningDecoder