国家科技图书文献中心 杭州服务站
首页
资源导航
特色服务
知识发现
关于我们
检索
代查代借

检索历史
浏览历史

订阅
收藏
0 申请单

个人中心
账号设置
充值
全部 |
  • 全部
  • 题名
  • 作者
  • 机构
  • 关键词
  • NSTL主题词
  • 摘要
检索 二次检索 AI检索
高级检索
外文文献 中文文献
筛选条件：

共搜索到3003条信息
?

1. A Secure and Robust Audio Watermarking Scheme Using Secret Sharing in the Transform-Domain NSTL国家科技图书文献中心

Aliya Tabassum Abbas... |  Fuyou Miao... -  《Circuits, systems, and signal processing》 - 2025,44(2) - 1274～1307 - 共34页

摘要： audio watermarking system by incorporating secret |  sharing in the transform domain. Previous audio |  such as imperceptibility, robustness, embedding |  both the encrypted watermark shares and the audio |  the diagonal coefficients of the audio cover with
关键词： Audio watermarking |  Secret sharing |  Discrete wavelet transform |  Discrete cosine transform |  Singular value decomposition |  Imperceptibility |  Robustness |  Watermarking security |  Embedding capacity
文献传递获取全文
文献传递
收藏

2. Transformer-Based Audio Generation Conditioned by 2D Latent Maps: A Demonstration NSTL国家科技图书文献中心

Christian Limberg |  Zhe Zhang... -  《MultiMedia Modeling,Part V》 -  International Conference on MultiMedia Modeling - 2025, - 233～239 - 共7页

摘要： improved framework for audio sample generation using |  work "Mapping the Audio Landscape for Innovative |  audio landscape through different audio features such | -SNE embedding over these features to create a more |  abstract visualization of the audio samples on the map
关键词： Audio generation |  Interactive demo |  Latent maps |  Music production |  Generative models
文献传递获取全文
文献传递
收藏

3. Robust audio watermarking based on a multi-band masking model using a DNN NSTL国家科技图书文献中心

Jiji Zhu -  《Fifth International Conference on Signal Processing and Computer Science (SPCS 2024)》 -  International Conference on Signal Processing and Computer Science - 2025, - 134420Q.1～134420Q.6 - 共6页

摘要：The technique of embedding the owner's valid |  copyright information in an audio signal is known as |  digital audio watermarking. Research in this field has |  imperceptibility, payload, and robustness. Traditionally, audio |  approach for embedding image watermarking information
关键词： Image-audio watermarking |  Short-time fourier transform |  Multiband masking |  Differentiable distortion
文献传递获取全文
文献传递
收藏

4. Robust Audio Watermarking Against Manipulation Attacks Based on Deep Learning NSTL国家科技图书文献中心

Shuangbing Wen |  Qishan Zhang... -  《IEEE signal processing letters》 - 2025,32 - 126～130 - 共5页

摘要： synthetic audio used to disseminate misinformation, which | . However, the current robustness against audio |  a robust audio watermarking method based on deep |  embedding of watermarking information is performed in the |  audio attacks are simulated during iterative training
关键词： Watermarking |  Robustness |  Decoding |  Deep learning |  Noise |  Convolution |  Training |  Signal to noise ratio |  Frequency-domain analysis |  Feature extraction
文献传递获取全文
文献传递
收藏

5. Audio-Driven Face Photo-Sketch Video Generation NSTL国家科技图书文献中心

Siyue Zhou |  Qun Guan... -  《PRICAI 2024,Part III》 -  Pacific Rim International Conference on Artificial Intelligence - 2025, - 443～455 - 共13页

摘要： accompanying audio information, potentially leading to the |  sketches, directly applying existing audio-driven video |  this end, we propose a novel method for audio-driven |  integrates sketch portrait generation, audio feature |  sensitive to audio in sketch style. To enhance the
关键词： Face photo-Sketch synthesis |  Audio-Driven |  Video generation
文献传递获取全文
文献传递
收藏

6. UniTalker: Scaling up Audio-Driven 3D Facial Animation Through A Unified Model NSTL国家科技图书文献中心

Xiangyu Fan |  Jiaqi Li... -  《Computer Vision - ECCV 2024,Part XLI》 -  European Conference on Computer Vision - 2025, - 204～221 - 共18页

摘要：Audio-driven 3D facial animation aims to map |  input audio to realistic facial motion. Despite |  pivot identity embedding. To expand the training scale |  audio domains, covering multilingual speech voices and |  model for audio-driven facial animation tasks. Fine
关键词： Audio-driven |  Facial animation |  Unified model
文献传递获取全文
文献传递
收藏

7. Extraction and Filtering of Electric Network Frequency Using Improved Matrix Pencil and Quadratic Box Plot-Empirical Wavelet Transform NSTL国家科技图书文献中心

Xiao Huang |  Alessandro Mingotti... -  《IEEE transactions on industrial informatics》 - 2025,21(1) - 60～69 - 共10页

摘要： authenticity of digital audio. However, there are many |  challenges in accurately extracting ENF from digital audio |  adaptive order determination method. By embedding ENF as |  a watermark into digital audio through encryption | The extraction and filtering of electric
关键词： Matrix decomposition |  Interference |  Phasor measurement units |  Noise |  Anomaly detection |  Bit error rate |  Watermarking |  Encryption |  Discrete Fourier transforms |  Accuracy
文献传递获取全文
文献传递
收藏

8. LightGBM-Based Audio Watermarking Robust to Recapturing and Hybrid Attacks NSTL国家科技图书文献中心

Zhaopin Su |  Zhaofang Weng... -  《IEEE transactions on information forensics and security》 - 2025,20 - 4212～4227 - 共16页

摘要：Digital audio watermarking is a critical | ), named LRAW (LightGBM-based Robust Audio Watermarking | ), which is designed to increase the robustness of audio |  embedded into the audio signal using a quantization rule | , considering the distinct influences of embedding watermark
关键词： Watermarking |  Robustness |  Recording |  Discrete wavelet transforms |  Feature extraction |  Transforms |  Quantization (signal) |  Loudspeakers |  Data mining |  Receivers
文献传递获取全文
文献传递
收藏

9. Squeeze-and-Excitation Self-Attention Mechanism Enhanced Digital Audio Source Recognition Based on Transfer Learning NSTL国家科技图书文献中心

Chunyan Zeng |  Yuhao Zhao... -  《Circuits, systems, and signal processing》 - 2025,44(1) - 480～512 - 共33页

摘要：Recent advances in digital audio source |  processing capabilities crucial for audio source |  embedding the Squeeze-and-Excitation mechanism within both |  digital audio source identification research. These |  self-attention mechanism's effectiveness in audio
关键词： Digital audio forensics |  Deep learning |  Self-attention mechanism |  Transfer learning |  Few-shot learning
文献传递获取全文
文献传递
收藏

10. Multiplex graph aggregation and feature refinement for unsupervised incomplete multimodal emotion recognition NSTL国家科技图书文献中心

Deng, Yuanyue |  Bian, Jintang... -  《Information Fusion》 - 2025,114 - 共15页

摘要： audio, visual, text and physiological signals, to | : Completion, Aggregation, Refinement, and Embedding |  operations on the embedding features to obtain the fused | Multimodal Emotion Recognition (MER) involves |  integrating information of various modalities, including
关键词： Incomplete multimodal learning |  Emotion recognition |  Multiplex graph aggregation |  Contrastive learning
文献传递获取全文
文献传递
收藏

相关推荐

检索结果集分析
检索结果集分析
结构化综述分析
检索条件audio embedding

NSTL主题词

  • NSTL学科导航

服务站

成员单位

友情链接

NSTL官方微信

官方微信

NSTL安卓APP

安卓APP

服务热线：

4008-161-200 800-990-8900

国家科技图书文献中心

国家科技图书文献中心

京ICP备10027328号

© Copyright(C)2023 NSTL.All Rights Reserved 版权所有

杭州服务站

0571-85112211；0571-85058943zj85112211@163.com

地址：浙江省杭州市滨江区信诚路572号 科技大市场A座318室

页面总访问量：32322536