今日论文合集：cs.SD语音11篇，eess.AS音频处理11篇。cs.SD语音【1】 Transferable Models for Bioacoustics with Human Language Supervision标题：具有人类语言监督的生物声学可移植模型链接：https://arxiv.org/abs/2308.04978作者：David Robinson,Adelaide Robinson,Lily Akrapongpisak【2】 Representation Learning for Audio Privacy Preservation using Source Separation and Robust Adversarial Learning标题：基于源分离和稳健对抗学习的音频隐私保护表征学习链接：https://arxiv.org/abs/2308.04960作者：Diep Luong,Minh Tran,Shayan Gharib,Konstantinos Drossos,Tuomas Virtanen【3】 Unsupervised Out-of-Distribution Dialect Detection with Mahalanobis Distance标题：基于马氏距离的无监督异地方言检测链接：https://arxiv.org/abs/2308.04886作者：Sourya Dipta Das,Yash Vadi,Abhishek Unnam,Kuldeep Yadav备注：Accepted in Interspeech 2023【4】 DiVa: An Iterative Framework to Harvest More Diverse and Valid Labels from User Comments for Music标题：DIVA：一个迭代框架，可以从用户对音乐的评论中获取更多多样化和有效的标签链接：https://arxiv.org/abs/2308.04805作者：Hongru Liang,Jingyao Liu,Yuanxin Xiang,Jiachen Du,Lanjun Zhou,Shushen Pan,Wenqiang Lei备注：11 pages, 5 figures, published to ACM MM 2023【5】 Induction Network: Audio-Visual Modality Gap-Bridging for Self-Supervised Sound Source Localization标题：感应网络：自监督声源定位的视听通道鸿沟弥合链接：https://arxiv.org/abs/2308.04767作者：Tianyu Liu,Peng Zhang,Wei Huang,Yufei Zha,Tao You,Yanning Zhang备注：Accepted to ACM Multimedia 2023【6】 JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Models标题：Jen-1：文本引导的全方位传播模型的通用音乐生成链接：https://arxiv.org/abs/2308.04729作者：Peike Li,Boyu Chen,Yao Yao,Yikai Wang,Allen Wang,Alex Wang【7】 Speaker Recognition Using Isomorphic Graph Attention Network Based Pooling on Self-Supervised Representation标题：基于同构图注意网络的说话人识别链接：https://arxiv.org/abs/2308.04666作者：Zirui Ge,Xinzhou Xu,Haiyan Guo,Tingting Wang,Zhen Yang备注：9 pages, 4 figures【8】 Deep Learning for Diverse Data Types Steganalysis: A Review标题：不同数据类型的深度学习隐写分析：综述链接：https://arxiv.org/abs/2308.04522作者：Hamza Kheddar,Mustapha Hemis,Yassine Himeur,David Megías,Abbes Amira【9】 Capturing Spectral and Long-term Contextual Information for Speech Emotion Recognition Using Deep Learning Techniques标题：利用深度学习技术获取语音情感识别的频谱和长时上下文信息链接：https://arxiv.org/abs/2308.04517作者：Samiul Islam,Md. Maksudul Haque,Abu Jobayer Md. Sadat备注：the research paper is still in progress【10】 Anonymizing Speech: Evaluating and Designing Speaker Anonymization Techniques标题：语音匿名化：说话人匿名化技术的评估与设计链接：https://arxiv.org/abs/2308.04455作者：Pierre Champion备注：PhD Thesis Pierre Champion | Universit\'e de Lorraine - INRIA Nancy | for associated source code file, see this https URL【11】 Separate Anything You Describe标题：把你描述的任何东西分开链接：https://arxiv.org/abs/2308.05037作者：Xubo Liu,Qiuqiang Kong,Yan Zhao,Haohe Liu,Yi Yuan,Yuzhuo Liu,Rui Xia,Yuxuan Wang,Mark D. Plumbley,Wenwu Wang备注：Project Page: this https URL; Code: this https URLeess.AS音频处理【1】 Separate Anything You Describe标题：把你描述的任何东西分开链接：https://arxiv.org/abs/2308.05037作者：Xubo Liu,Qiuqiang Kong,Yan Zhao,Haohe Liu,Yi Yuan,Yuzhuo Liu,Rui Xia,Yuxuan Wang,Mark D. Plumbley,Wenwu Wang备注：Project Page: this https URL; Code: this https URL【2】 Transferable Models for Bioacoustics with Human Language Supervision标题：具有人类语言监督的生物声学可移植模型链接：https://arxiv.org/abs/2308.04978作者：David Robinson,Adelaide Robinson,Lily Akrapongpisak【3】 Representation Learning for Audio Privacy Preservation using Source Separation and Robust Adversarial Learning标题：基于源分离和稳健对抗学习的音频隐私保护表征学习链接：https://arxiv.org/abs/2308.04960作者：Diep Luong,Minh Tran,Shayan Gharib,Konstantinos Drossos,Tuomas Virtanen【4】 Unsupervised Out-of-Distribution Dialect Detection with Mahalanobis Distance标题：基于马氏距离的无监督异地方言检测链接：https://arxiv.org/abs/2308.04886作者：Sourya Dipta Das,Yash Vadi,Abhishek Unnam,Kuldeep Yadav备注：Accepted in Interspeech 2023【5】 DiVa: An Iterative Framework to Harvest More Diverse and Valid Labels from User Comments for Music标题：DIVA：一个迭代框架，可以从用户对音乐的评论中获取更多多样化和有效的标签链接：https://arxiv.org/abs/2308.04805作者：Hongru Liang,Jingyao Liu,Yuanxin Xiang,Jiachen Du,Lanjun Zhou,Shushen Pan,Wenqiang Lei备注：11 pages, 5 figures, published to ACM MM 2023【6】 Induction Network: Audio-Visual Modality Gap-Bridging for Self-Supervised Sound Source Localization标题：感应网络：自监督声源定位的视听通道鸿沟弥合链接：https://arxiv.org/abs/2308.04767作者：Tianyu Liu,Peng Zhang,Wei Huang,Yufei Zha,Tao You,Yanning Zhang备注：Accepted to ACM Multimedia 2023【7】 JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Models标题：Jen-1：文本引导的全方位传播模型的通用音乐生成链接：https://arxiv.org/abs/2308.04729作者：Peike Li,Boyu Chen,Yao Yao,Yikai Wang,Allen Wang,Alex Wang【8】 Speaker Recognition Using Isomorphic Graph Attention Network Based Pooling on Self-Supervised Representation标题：基于同构图注意网络的说话人识别链接：https://arxiv.org/abs/2308.04666作者：Zirui Ge,Xinzhou Xu,Haiyan Guo,Tingting Wang,Zhen Yang备注：9 pages, 4 figures【9】 Deep Learning for Diverse Data Types Steganalysis: A Review标题：不同数据类型的深度学习隐写分析：综述链接：https://arxiv.org/abs/2308.04522作者：Hamza Kheddar,Mustapha Hemis,Yassine Himeur,David Megías,Abbes Amira【10】 Capturing Spectral and Long-term Contextual Information for Speech Emotion Recognition Using Deep Learning Techniques标题：利用深度学习技术获取语音情感识别的频谱和长时上下文信息链接：https://arxiv.org/abs/2308.04517作者：Samiul Islam,Md. Maksudul Haque,Abu Jobayer Md. Sadat备注：the research paper is still in progress【11】 Anonymizing Speech: Evaluating and Designing Speaker Anonymization Techniques标题：语音匿名化：说话人匿名化技术的评估与设计链接：https://arxiv.org/abs/2308.04455作者：Pierre Champion备注：PhD Thesis Pierre Champion | Universit\'e de Lorraine - INRIA Nancy | for associated source code file, see this https URL机器翻译，仅供参考
每日语音速递
