今日论文合集：cs.SD语音7篇，eess.AS音频处理11篇。cs.SD语音【1】 Self-Supervised Visual Acoustic Matching标题：自监督视觉声学匹配链接：https://arxiv.org/abs/2307.15064作者：Arjun Somayazulu,Changan Chen,Kristen Grauman机构：University of Texas at Austin, FAIR【2】 Graph-based Polyphonic Multitrack Music Generation标题：基于图形的复调多声道音乐生成链接：https://arxiv.org/abs/2307.14928作者：Emanuele Cosenza,Andrea Valenti,Davide Bacciu机构：University of Pisa【3】 Complete and separate: Conditional separation with missing target source attribute completion标题：完成和分离：条件分离，缺少目标源属性完成链接：https://arxiv.org/abs/2307.14609作者：Dimitrios Bralios,Efthymios Tzinis,Paris Smaragdis机构：University of Illinois Urbana-Champaign, Department of Computer Science, Urbana, IL, USA备注：Accepted to IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2023【4】 Modality-Agnostic Audio-Visual Deepfake Detection标题：与通道无关的视听深伪检测链接：https://arxiv.org/abs/2307.14491作者：Cai Yu,Peng Chen,Jiahe Tian,Jin Liu,Jiao Dai,Xi Wang,Yesheng Chai,Jizhong Han机构：Institute of Information Engineering, Chinese Academy of Sciences, Haidian, Beijing, China, RealAI, Datasets, Dual-Label, Deepfake Detection, Audio-Visual, Speech Recognition, video & audio, Transcribed Text, transfer learned, speech correlation, Stage , J: Video Real, L: Video Fake【5】 Single Channel Speech Enhancement Using U-Net Spiking Neural Networks标题：基于U网尖峰神经网络的单通道语音增强链接：https://arxiv.org/abs/2307.14464作者：Abir Riahi,Éric Plourde机构：Department of Electrical and Computer Engineering, Universit´e de Sherbrooke, Sherbrooke, Quebec, Canada, ´Eric Plourde【6】 Mitigating Cross-Database Differences for Learning Unified HRTF Representation标题：减少跨数据库差异以学习统一HRTF表示链接：https://arxiv.org/abs/2307.14547作者：Yutong Wen,You Zhang,Zhiyao Duan机构：University of Rochester, Rochester, NY, USA备注：5 pages, 4 figures, accepted by IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2023【7】 The Effect of Spoken Language on Speech Enhancement using Self-Supervised Speech Representation Loss Functions标题：基于自监督语音表征损失函数的口语对语音增强的影响链接：https://arxiv.org/abs/2307.14502作者：George Close,Thomas Hain,Stefan Goetze机构：Speech and Hearing Group, Department of Computer Science, University of Sheffield, United Kingdom备注：Accepted at WASPAA 2023eess.AS音频处理【1】 Emotion4MIDI: a Lyrics-based Emotion-Labeled Symbolic Music Dataset标题：Emotion4MIDI：一个基于歌词的情感标注符号音乐数据集链接：https://arxiv.org/abs/2307.14783作者：Serkan Sulun,Pedro Oliveira,Paula Viana机构：Institute for Systems and Computer Engineering, Technology and Science (INESC, TEC), Porto, Portugal, University of Porto, Porto, Portugal, ISEP, Polytechnic of Porto, School of Engineering, Porto, Portugal备注：Accepted to 22nd EPIA Conference on Artificial Intelligence (2023)【2】 Audio Inputs for Active Speaker Detection and Localization via Microphone Array标题：利用麦克风阵列实现有源说话人检测和定位的音频输入链接：https://arxiv.org/abs/2307.14739作者：Davide Berghi,Philip J. B. Jackson机构：Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK.【3】 Physics Informed Neural Network for Head-Related Transfer Function Upsampling标题：头部相关传递函数上采样的物理信息神经网络链接：https://arxiv.org/abs/2307.14650作者：Fei Ma,Thushara D. Abhayapala,Prasanga N. Samarasinghe,Xingyu Chen【4】 Mitigating Cross-Database Differences for Learning Unified HRTF Representation标题：减少跨数据库差异以学习统一HRTF表示链接：https://arxiv.org/abs/2307.14547作者：Yutong Wen,You Zhang,Zhiyao Duan机构：University of Rochester, Rochester, NY, USA备注：5 pages, 4 figures, accepted by IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2023【5】 The Effect of Spoken Language on Speech Enhancement using Self-Supervised Speech Representation Loss Functions标题：基于自监督语音表征损失函数的口语对语音增强的影响链接：https://arxiv.org/abs/2307.14502作者：George Close,Thomas Hain,Stefan Goetze机构：Speech and Hearing Group, Department of Computer Science, University of Sheffield, United Kingdom备注：Accepted at WASPAA 2023【6】 Diff-E: Diffusion-based Learning for Decoding Imagined Speech EEG标题：Diff-E：基于扩散的想象语音脑电解码学习链接：https://arxiv.org/abs/2307.14389作者：Soowon Kim,Young-Eun Lee,Seo-Hyun Lee,Seong-Whan Lee机构：Department of Artificial Intelligence, Korea University, Republic of Korea, Department of Brain and Cognitive Engineering, Korea University, Republic of Korea备注：Accepted to Interspeech 2023【7】 Self-Supervised Visual Acoustic Matching标题：自监督视觉声学匹配链接：https://arxiv.org/abs/2307.15064作者：Arjun Somayazulu,Changan Chen,Kristen Grauman机构：University of Texas at Austin, FAIR【8】 Graph-based Polyphonic Multitrack Music Generation标题：基于图形的复调多声道音乐生成链接：https://arxiv.org/abs/2307.14928作者：Emanuele Cosenza,Andrea Valenti,Davide Bacciu机构：University of Pisa【9】 Complete and separate: Conditional separation with missing target source attribute completion标题：完成和分离：条件分离，缺少目标源属性完成链接：https://arxiv.org/abs/2307.14609作者：Dimitrios Bralios,Efthymios Tzinis,Paris Smaragdis机构：University of Illinois Urbana-Champaign, Department of Computer Science, Urbana, IL, USA备注：Accepted to IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2023【10】 Modality-Agnostic Audio-Visual Deepfake Detection标题：与通道无关的视听深伪检测链接：https://arxiv.org/abs/2307.14491作者：Cai Yu,Peng Chen,Jiahe Tian,Jin Liu,Jiao Dai,Xi Wang,Yesheng Chai,Jizhong Han机构：Institute of Information Engineering, Chinese Academy of Sciences, Haidian, Beijing, China, RealAI, Datasets, Dual-Label, Deepfake Detection, Audio-Visual, Speech Recognition, video & audio, Transcribed Text, transfer learned, speech correlation, Stage , J: Video Real, L: Video Fake【11】 Single Channel Speech Enhancement Using U-Net Spiking Neural Networks标题：基于U网尖峰神经网络的单通道语音增强链接：https://arxiv.org/abs/2307.14464作者：Abir Riahi,Éric Plourde机构：Department of Electrical and Computer Engineering, Universit´e de Sherbrooke, Sherbrooke, Quebec, Canada, ´Eric Plourde机器翻译，仅供参考
每日语音速递
