今日论文合集：cs.SD语音13篇，eess.AS音频处理16篇。
cs.SD语音
【1】 MBTFNet: Multi-Band Temporal-Frequency Neural Network For Singing Voice Enhancement标题：MBTFNet：用于歌唱语音增强的多带时频神经网络作者：Weiming Xu,Zhouxuan Chen,Zhili Tan,Shubo Lv,Runduo Han,Wenjiang Zhou,Weifeng Zhao,Lei Xie链接：http://arxiv.org/pdf/2310.04369v1
【2】 Transferring speech-generic and depression-specific knowledge for Alzheimer's disease detection标题：用于阿尔茨海默病检测的语音通用知识和抑郁症特异性知识的传递作者：Ziyun Cui,Wen Wu,Wei-Qiang Zhang,Ji Wu,Chao Zhang备注：8 pages, 4 figures. Accepted by ASRU 2023链接：http://arxiv.org/pdf/2310.04358v1
【3】 U-Style: Cascading U-nets with Multi-level Speaker and Style Modeling for Zero-Shot Voice Cloning标题：U-Style：多级说话人的级联U-Net及Zero-Shot语音克隆风格建模作者：Tao Li,Zhichao Wang,Xinfa Zhu,Jian Cong,Qiao Tian,Yuping Wang,Lei Xie链接：http://arxiv.org/pdf/2310.04004v1【4】 Layer-Adapted Implicit Distribution Alignment Networks for Cross-Corpus Speech Emotion Recognition标题：跨语料库语音情感识别的层次自适应隐式分布对齐网络作者：Yan Zhao,Yuan Zong,Jincen Wang,Hailun Lian,Cheng Lu,Li Zhao,Wenming Zheng链接：http://arxiv.org/pdf/2310.03992v1【5】 Dementia Assessment Using Mandarin Speech with an Attention-based Speech Recognition Encoder标题：使用基于注意力的语音识别编码器的普通话语音进行痴呆评估作者：Zih-Jyun Lin,Yi-Ju Chen,Po-Chih Kuo,Likai Huang,Chaur-Jong Hu,Cheng-Yu Chen备注：submitted to IEEE ICASSP 2024链接：http://arxiv.org/pdf/2310.03985v1【6】 HuBERTopic: Enhancing Semantic Representation of HuBERT through Self-supervision Utilizing Topic Model标题：HuBERTheme：利用主题模型通过自我监督增强Hubert的语义表示作者：Takashi Maekaku,Jiatong Shi,Xuankai Chang,Yuya Fujita,Shinji Watanabe备注：Submitted to IEEE ICASSP 2024链接：http://arxiv.org/pdf/2310.03975v1【7】 Zero-Shot Emotion Transfer For Cross-Lingual Speech Synthesis标题：跨语言语音合成中的Zero-Shot情感传递作者：Yuke Li,Xinfa Zhu,Yi Lei,Hai Li,Junhui Liu,Danming Xie,Lei Xie备注：Accepted by ASRU2023链接：http://arxiv.org/pdf/2310.03963v1【8】 EFFUSE: Efficient Self-Supervised Feature Fusion for E2E ASR in Multilingual and Low Resource Scenarios标题：FUSE：多语言低资源场景下E2E ASR的高效自监督特征融合作者：Tejes Srivastava,Jiatong Shi,William Chen,Shinji Watanabe备注：7 pages, 2 figures, 7 tables链接：http://arxiv.org/pdf/2310.03938v1【9】 Diffusion Models as Masked Audio-Video Learners标题：作为蒙面视听学习者的扩散模型作者：Elvis Nunez,Yanzi Jin,Mohammad Rastegari,Sachin Mehta,Maxwell Horton链接：http://arxiv.org/pdf/2310.03937v1【10】 Securing Voice Biometrics: One-Shot Learning Approach for Audio Deepfake Detection标题：安全语音生物识别：音频深度伪码检测的一次学习方法作者：Awais Khan,Khalid Mahmood Malik链接：http://arxiv.org/pdf/2310.03856v1
【11】 Analysis on the Influence of Synchronization Error on Fixed-filter Active Noise Control标题：同步误差对固定滤波有源噪声控制的影响分析作者：Guo Yu链接：http://arxiv.org/pdf/2310.04249v1【12】 Challenges and Insights: Exploring 3D Spatial Features and Complex Networks on the MISP Dataset标题：挑战与洞察：探索MISP数据集上的3D空间要素和复杂网络作者：Yiwen Shao链接：http://arxiv.org/pdf/2310.03901v1【13】 Audio Event-Relational Graph Representation Learning for Acoustic Scene Classification标题：用于声学场景分类的音频事件关联图表示学习作者：Yuanbo Hou,Siyang Song,Chuang Yu,Wenwu Wang,Dick Botteldooren备注：IEEE Signal Processing Letters, doi: 10.1109LSP.2023.3319233链接：http://arxiv.org/pdf/2310.03889v1
eess.AS音频处理

【1】 Analysis on the Influence of Synchronization Error on Fixed-filter Active Noise Control标题：同步误差对固定滤波有源噪声控制的影响分析作者：Guo Yu链接：http://arxiv.org/pdf/2310.04249v1

【2】 Optimal model-based beamforming and independent steering for spherical loudspeaker arrays标题：基于最优模型的球形扬声器阵列波束形成和独立导引作者：Boaz Rafaely,Dima KhaykinJournal-ref：in IEEE Trans. Audio, Speech, and Lang. Proc., vol. 19, no. 7, pp. 2234-2238, Sept. 2011链接：http://arxiv.org/pdf/2310.04202v1
【3】 Zones of quiet in a broadband diffuse sound field标题：宽带漫射声场中的静区作者：Boaz RafaelyJournal-ref：J. Acoust. Soc. Am., vol. 110, no. 1, pp. 296-302, July 2001链接：http://arxiv.org/pdf/2310.04191v1【4】 Spatial sampling and beamforming for spherical microphone arrays标题：球形传声器阵列的空间采样和波束形成作者：Boaz RafaelyJournal-ref：2008 Hands-Free Speech Communication and Microphone Arrays, Trento, Italy, 2008, pp. 5-8链接：http://arxiv.org/pdf/2310.04169v1【5】 A privacy-preserving method using secret key for convolutional neural network-based speech classification标题：一种基于卷积神经网络语音分类的密钥隐私保护方法作者：Shoko Niwa,Sayaka Shiota,Hitoshi Kiya备注：To appear in the 31st European Signal Processing Conference (EUSIPCO 2023)链接：http://arxiv.org/pdf/2310.04035v1【6】 Challenges and Insights: Exploring 3D Spatial Features and Complex Networks on the MISP Dataset标题：挑战与洞察：探索MISP数据集上的3D空间要素和复杂网络作者：Yiwen Shao链接：http://arxiv.org/pdf/2310.03901v1【7】 Audio Event-Relational Graph Representation Learning for Acoustic Scene Classification标题：用于声学场景分类的音频事件关联图表示学习作者：Yuanbo Hou,Siyang Song,Chuang Yu,Wenwu Wang,Dick Botteldooren备注：IEEE Signal Processing Letters, doi: 10.1109LSP.2023.3319233链接：http://arxiv.org/pdf/2310.03889v1
【8】 MBTFNet: Multi-Band Temporal-Frequency Neural Network For Singing Voice Enhancement标题：MBTFNet：用于歌唱语音增强的多带时频神经网络作者：Weiming Xu,Zhouxuan Chen,Zhili Tan,Shubo Lv,Runduo Han,Wenjiang Zhou,Weifeng Zhao,Lei Xie链接：http://arxiv.org/pdf/2310.04369v1【9】 Transferring speech-generic and depression-specific knowledge for Alzheimer's disease detection标题：用于阿尔茨海默病检测的语音通用知识和抑郁症特异性知识的传递作者：Ziyun Cui,Wen Wu,Wei-Qiang Zhang,Ji Wu,Chao Zhang备注：8 pages, 4 figures. Accepted by ASRU 2023链接：http://arxiv.org/pdf/2310.04358v1【10】 U-Style: Cascading U-nets with Multi-level Speaker and Style Modeling for Zero-Shot Voice Cloning标题：U-Style：多级说话人的级联U-Net及Zero-Shot语音克隆风格建模作者：Tao Li,Zhichao Wang,Xinfa Zhu,Jian Cong,Qiao Tian,Yuping Wang,Lei Xie链接：http://arxiv.org/pdf/2310.04004v1【11】 Layer-Adapted Implicit Distribution Alignment Networks for Cross-Corpus Speech Emotion Recognition标题：跨语料库语音情感识别的层次自适应隐式分布对齐网络作者：Yan Zhao,Yuan Zong,Jincen Wang,Hailun Lian,Cheng Lu,Li Zhao,Wenming Zheng链接：http://arxiv.org/pdf/2310.03992v1
【12】 Dementia Assessment Using Mandarin Speech with an Attention-based Speech Recognition Encoder标题：使用基于注意力的语音识别编码器的普通话语音进行痴呆评估作者：Zih-Jyun Lin,Yi-Ju Chen,Po-Chih Kuo,Likai Huang,Chaur-Jong Hu,Cheng-Yu Chen备注：submitted to IEEE ICASSP 2024链接：http://arxiv.org/pdf/2310.03985v1【13】 Zero-Shot Emotion Transfer For Cross-Lingual Speech Synthesis标题：跨语言语音合成中的Zero-Shot情感传递作者：Yuke Li,Xinfa Zhu,Yi Lei,Hai Li,Junhui Liu,Danming Xie,Lei Xie备注：Accepted by ASRU2023链接：http://arxiv.org/pdf/2310.03963v1【14】 EFFUSE: Efficient Self-Supervised Feature Fusion for E2E ASR in Multilingual and Low Resource Scenarios标题：FUSE：多语言低资源场景下E2E ASR的高效自监督特征融合作者：Tejes Srivastava,Jiatong Shi,William Chen,Shinji Watanabe备注：7 pages, 2 figures, 7 tables链接：http://arxiv.org/pdf/2310.03938v1【15】 Diffusion Models as Masked Audio-Video Learners标题：作为蒙面视听学习者的扩散模型作者：Elvis Nunez,Yanzi Jin,Mohammad Rastegari,Sachin Mehta,Maxwell Horton链接：http://arxiv.org/pdf/2310.03937v1【16】 Securing Voice Biometrics: One-Shot Learning Approach for Audio Deepfake Detection标题：安全语音生物识别：音频深度伪码检测的一次学习方法作者：Awais Khan,Khalid Mahmood Malik链接：http://arxiv.org/pdf/2310.03856v1
机器翻译，仅供参考