logo
科言猫学术研究的AI总结
language
手机端手机端
  • Phone Feature微信小程序
简体中文简体中文
notice消息通知
博客博客
delete
arrow
返回

Zero-shot diverse audio captioning with diffusion models

delete2025-12-29
delete0
PRE
AI
Y
Yonggang Zhu
Z
Zhang, Yiming
L
Li Xiao
W
Wenwu Wang
A
Aidong Men
DOI：10.1016/j.knosys.2025.115205delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
• 首次将多样性(diversity)和零样本学习(zero-shot)能力结合应用于音频字幕生成。 • 发现噪声引起的条件退化问题，并采用条件平铺(condition tiling)方法加以解决。 • 无需音频输入即可适配对齐模型，以实现检索引导的Langevin动力学(retrieval-guided Langevin dynamics)。 • 在主要基准测试中，超越先前零样本工作的多样性表现，并弥补基线准确率差距。

期刊

K
Knowledge-Based Systems
IF:
7.6
论文数:
1.2W
被引数:
4.5W

机构

B
Beijing University of Posts and Telecommunications
学者数:
2.6K
论文数: 1.2K
被引数: 4.2K
U
University of Surrey
学者数:
1.2W
论文数: 1.3W
被引数: 22
引用论文

引用论文

Diff-PC: Identity-preserving and 3D-aware controllable diffusion for zero-shot portrait customizationDiff-PC：保持身份特征且具有3D感知能力的可控扩散模型，用于零样本肖像定制
errINFORMATION FUSION
IF15.5
err2025-05-01
err1
PREAI
errZhai, Benxiang; Zhang, Chenyu; Li, Ming; Li, Yang; Du, Sidan
err分享
err收藏
Acoustic Scene Classification Across Cities and Devices via Feature Disentanglement
errIEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
IF5.1
err2024-01-01
err5
errOAAI
errTan, Yizhou; Ai, Haojun; Li, Shengchen; Plumbley, Mark D.
err分享
err收藏
WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal ResearchWavCaps: 用于音频语言多模态研究的ChatGPT辅助弱标记音频字幕数据集
errIEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
IF5.1
err2024-01-01
err8
errOAAI
errMei, Xinhao; Meng, Chutong; Liu, Haohe; Kong, Qiuqiang; Ko, Tom; Zhao, Chengqi; Plumbley, Mark D.; Zou, Yuexian; Wang, Wenwu
err分享
err收藏
err
IF0
err
err0
PREAI
err
err分享
err收藏
Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio GenerationAuffusion: 利用扩散和大型语言模型的力量进行文本到音频的生成
errIEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
IF5.1
err2024-01-01
err0
PREAI
errXue, Jinlong; Deng, Yayue; Gao, Yingming; Li, Ya
err分享
err收藏
AudioLDM 2: Learning Holistic Audio Generation With Self-Supervised Pretraining
errIEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
IF5.1
err2024-01-01
err8
errOAAI
errLiu, Haohe; Yuan, Yi; Liu, Xubo; Mei, Xinhao; Kong, Qiuqiang; Tian, Qiao; Wang, Yuping; Wang, Wenwu; Wang, Yuxuan; Plumbley, Mark D.
err分享
err收藏
Beyond the Status Quo: A Contemporary Survey of Advances and Challenges in Audio Captioning
errIEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
IF5.1
err2024-01-01
err6
errOAAI
errXu, Xuenan; Xie, Zeyu; Wu, Mengyue; Yu, Kai
err分享
err收藏
On Local Temporal Embedding for Semi-Supervised Sound Event Detection
errIEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
IF5.1
err2024-01-01
err5
PREAI
errGao, Lijian; Mao, Qirong; Dong, Ming
err分享
err收藏
Automated audio captioning: an overview of recent progress and new challenges
errEURASIP Journal on Audio, Speech, and Music Processing
IF0
err2022-10-09
err0
errOAAI
errXinhao Mei; Xubo Liu; Mark D. Plumbley; Wenwu Wang
err分享
err收藏
AudioSetCaps: An Enriched Audio-Caption Dataset Using Automated Generation Pipeline With Large Audio and Language Models
errIEEE Transactions on Audio, Speech and Language Processing
IF0
err2025-01-01
err0
PREAI
errBai,Jisheng; Liu,Haohe; Wang,Mou; Shi,Dongyuan; Wang,Wenwu; Plumbley,Mark D.; Gan,Woon-Seng; Chen,Jianfeng
err分享
err收藏
学者 查看更多内容