今日论文合集：cs.SD语音22篇，eess.AS音频处理23篇。
cs.SD语音
【1】 TalkNCE: Improving Active Speaker Detection with Talk-Aware Contrastive Learning标题：TalkNCE：利用谈话感知对比学习改进主动说话人检测作者：Chaeyoung Jung,Suyeon Lee,Kihyun Nam,Kyeongha Rho,You Jin Kim,Youngjoon Jang,Joon Son Chung机构：Korea Advanced Institute of Science and Technology, South Korea, Naver Cloud Corporation, South Korea链接：http://arxiv.org/pdf/2309.12306v1
【2】 Performance Conditioning for Diffusion-Based Multi-Instrument Music Synthesis标题：基于扩散的多乐器音乐合成中的性能调节作者：Ben Maman,Johannes Zeitler,Meinard Müller,Amit H. Bermano机构：⋆ Tel Aviv University, †International Audio Laboratories Erlangen, Germany备注：5 pages, project page available at benadar293.github.iomidipm链接：http://arxiv.org/pdf/2309.12283v1
【3】 Variational Quantum Harmonizer: Generating Chord Progressions and Other Sonification Methods with the VQE Algorithm标题：变分量子调和器：用VQE算法生成和弦级数和其他发声方法作者：Paulo Vitor Itaboraí,Tim Schwägerl,María Aguado Yáñez,Arianna Crippa,Karl Jansen,Eduardo Reck Miranda,Peter Thomas机构：Eduardo R. Miranda, Interdisciplinary Centre for Computer Music Research – University of Plymouth, Drake Circus - PL,AA - Plymouth - United Kingdom, Centre for Quantum Technologies and Applications – Deutsches Elektronen-Synchrotron DESY备注：Manuscript Accepted to the 2nd International Symposium on Quantum Computing and Musical Creativity (ISQCMC Berlin). Link: this https URL链接：http://arxiv.org/pdf/2309.12254v1【4】 Weakly-supervised Automated Audio Captioning via text only training标题：基于纯文本训练的弱监督自动音频字幕作者：Theodoros Kouzelis,Vassilis Katsouros机构：Institute for Language and Speech Processing, Athena Research Center, Marousi, Greece备注：DCASE Workshop 2023链接：http://arxiv.org/pdf/2309.12242v1【5】 t-EER: Parameter-Free Tandem Evaluation of Countermeasures and Biometric Comparators标题：T-EER：对策和生物特征比较器的无参数串联评估作者：Tomi Kinnunen,Kong Aik Lee,Hemlata Tak,Nicholas Evans,Andreas Nautsch机构：This paper has been accepted for publication in IEEE Transactions on Pattern Analysis and Machine Intelligence. If you would, like to cite the work, please use the following bibliographic entry.备注：To appear in IEEE Transactions on Pattern Analysis and Machine Intelligence. For associated codes, see this https URL (Github) and this https URL (Google Colab)链接：http://arxiv.org/pdf/2309.12237v1【6】 Towards Robust and Truly Large-Scale Audio-Sheet Music Retrieval标题：走向稳健和真正大规模的音表音乐检索作者：Luis Carvalho,Gerhard Widmer机构：Institute of Computational Perception & ,LIT Artificial Intelligence Lab, Johannes Kepler University Linz, Austria备注：Proceedings of the IEEE 6th International Conference on Multimedia Information Processing and Retrieval (MIPR)链接：http://arxiv.org/pdf/2309.12158v1【7】 Self-Supervised Contrastive Learning for Robust Audio-Sheet Music Retrieval Systems标题：基于自监督对比学习的稳健音表音乐检索系统作者：Luis Carvalho,Tobias Washüttl,Gerhard Widmer机构：Institute of Computational Perception, Johannes Kepler University Linz, Austria, LIT Artificial Intelligence LabJournal-ref：Proceedings of the 14th ACM Multimedia Systems Conference (MMSys '23), June 7-10, 2023, Vancouver, BC, Canada链接：http://arxiv.org/pdf/2309.12134v1【8】 Passage Summarization with Recurrent Models for Audio-Sheet Music Retrieval标题：基于递归模型的音表音乐检索小结作者：Luis Carvalho,Gerhard Widmer机构：Institute of Computational Perception & ,LIT Artificial Intelligence Lab, Johannes Kepler University Linz, Austria备注：In Proceedings of the 24th Conference of the International Society for Music Information Retrieval (ISMIR 2023), Milan, Italy链接：http://arxiv.org/pdf/2309.12111v1【9】 Improving Language Model-Based Zero-Shot Text-to-Speech Synthesis with Multi-Scale Acoustic Prompts标题：利用多尺度声学提示改进基于语言模型的零发声文语合成作者：Shun Lei,Yixuan Zhou,Liyang Chen,Dan Luo,Zhiyong Wu,Xixin Wu,Shiyin Kang,Tao Jiang,Yahui Zhou,Yuxing Han,Helen Meng机构：Shenzhen International Graduate School, Tsinghua University, Shenzhen, Skywork AI PTE. LTD., Beijing , The Chinese University of Hong Kong, Hong Kong SAR备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.11977v1【10】 Audio Contrastive based Fine-tuning标题：基于音频对比度的微调作者：Yang Wang,Qibin Liang,Chenghao Xiao,Yizhi Li,Noura Al Moubayed,Chenghua Lin机构：Department of Computer Science, The University of Sheffield, UK, Department of Computer Science, The University of Manchester, UK, Department of Computer Science, Durham University, UK, Automated Analytics, UK ,Rainbow-Flower AI, China备注：Under review in ICASSP链接：http://arxiv.org/pdf/2309.11895v1【11】 A Discourse-level Multi-scale Prosodic Model for Fine-grained Emotion Analysis标题：面向细粒度情感分析的语篇级多尺度韵律模型作者：Xianhao Wei,Jia Jia,Xiang Li,Zhiyong Wu,Ziyi Wang机构：Department of Computer Science and Technology, Tsinghua University, Beijing, China, Shenzhen International Graduate School, Shenzhen, China, Academy of Arts and Design备注：ChinaMM 2023链接：http://arxiv.org/pdf/2309.11849v1【12】 TMac: Temporal Multi-Modal Graph Learning for Acoustic Event Classification标题：TMAC：用于声事件分类的时态多模图学习作者：Meng Liu,Ke Liang,Dayu Hu,Hao Yu,Yue Liu,Lingyuan Meng,Wenxuan Tu,Sihang Zhou,Xinwang Liu机构：National University of Defense, Technology链接：http://arxiv.org/pdf/2309.11845v1【13】 Frame Pairwise Distance Loss for Weakly-supervised Sound Event Detection标题：弱监督声事件检测中的帧对距离损失算法作者：Rui Tao,Yuxing Huang,Xiangdong Wang,Long Yan,Lufeng Zhai,Kazushige Ouchi,Taihao Li机构：Toshiba China R&D Center, Beijing, China., Zhejiang Lab, Zhejiang, China., Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China.备注：siibmited to ICASSP 2024链接：http://arxiv.org/pdf/2309.11783v1【14】 FluentEditor: Text-based Speech Editing by Considering Acoustic and Prosody Consistency标题：考虑声学和韵律一致性的基于文本的语音编辑作者：Rui Liu,Jiatian Xi,Ziyue Jiang,Haizhou Li机构：Inner Mongolia University, Hohhot, China , Zhejiang University, China, Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), China, National University of Singapore, Singapore备注：Submitted to ICASSP'2024链接：http://arxiv.org/pdf/2309.11725v1【15】 A Multiscale Autoencoder (MSAE) Framework for End-to-End Neural Network Speech Enhancement标题：端到端神经网络语音增强的多尺度自动编码器框架作者：Bengt J. Borgstrom,Michael S. Brandstein机构：This material is based upon work supported by theDepartment of Defense under Air Force Contract No, conclusions or recommendations expressed in thismaterial are those of the author(s) and do not necessarily reflect the views ofthe Department of Defense备注：13 pages, 9 figures链接：http://arxiv.org/pdf/2309.12121v1【16】 Is the Ideal Ratio Mask Really the Best? -- Exploring the Best Extraction Performance and Optimal Mask of Mask-based Beamformers标题：理想的比例掩模真的是最好的吗？--探讨掩模波束形成器的最佳提取性能和最佳掩模作者：Atsuo Hiroe,Katsutoshi Itoyama,Kazuhiro Nakadai机构：∗ Department of Systems and Control Engineering, School of Engineering, Tokyo Institute of Technology, Tokyo, Japan, † Honda Research Institute Japan Co., Ltd., Saitama, Japan备注：Accepted in APSIPA 2023链接：http://arxiv.org/pdf/2309.12065v1【17】 Multi-Channel MOSRA: Mean Opinion Score and Room Acoustics Estimation Using Simulated Data and a Teacher Model标题：多通道MOSRA：使用模拟数据和教师模型的平均意见得分和房间声学估计作者：Jozef Coldenhoff,Andrew Harper,Paul Kendrick,Tijana Stojkovic,Milos Cernak机构：Logitech Europe S.A., Lausanne, Switzerland, ´Ecole Polytechnique F´ed´erale de Lausanne (EPFL), Lausanne, Switzerland链接：http://arxiv.org/pdf/2309.11976v1【18】 Cluster-based pruning techniques for audio data标题：基于簇的音频数据剪枝技术作者：Boris Bergsma,Marta Brzezinska,Oleg V. Yazyev,Milos Cernak机构：Institute of Physics, Ecole Polytechnique F´ed´erale de Lausanne (EPFL), CH-, Lausanne, Switzerland, Logitech Europe S.A., Lausanne, Switzerland, ∗equal contribution链接：http://arxiv.org/pdf/2309.11922v1【19】 The Impact of Silence on Speech Anti-Spoofing标题：沉默对语音反欺骗的影响作者：Yuxiang Zhang,Zhuo Li,Jingze Lu,Hua Hua,Wenchao Wang,Pengyuan Zhang机构：)The authors are with Key Laboratory of Speech Acoustics and ContentUnderstanding, Institute of Acoustics, China and also with University of Chinese Academy of Sciences备注：16 pages, 9 figures, 13 tables链接：http://arxiv.org/pdf/2309.11827v1【20】 CoMFLP: Correlation Measure based Fast Search on ASR Layer Pruning标题：CoMFLP：基于相关性度量的ASR层剪枝快速搜索作者：Wei Liu,Zhiyuan Peng,Tan Lee机构：Department of Electronic Engineering, The Chinese University of Hong Kong备注：Accepted by Interspeech 2023链接：http://arxiv.org/pdf/2309.11768v1【21】 Sparsely Shared LoRA on Whisper for Child Speech Recognition标题：用于儿童语音识别的稀疏共享Lora on Whisper作者：Wei Liu,Ying Qin,Zhiyuan Peng,Tan Lee机构：Department of Electronic Engineering, The Chinese University of Hong Kong, Institute of Information Science, Beijing Jiaotong University, Beijing , China备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.11756v1【22】 Leveraging In-the-Wild Data for Effective Self-Supervised Pretraining in Speaker Recognition标题：在说话人识别中利用野外数据进行有效的自我监督预训练作者：Shuai Wang,Qibing Bai,Qi Liu,Jianwei Yu,Zhengyang Chen,Bing Han,Yanmin Qian,Haizhou Li机构：Shenzhen Research Institute of Big Data, Shenzhen, China, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), China, Tencent, Shenzhen, China, Shanghai Jiao Tong University, Shanghai, China备注：submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.11730v1

eess.AS音频处理
【1】 A Multiscale Autoencoder (MSAE) Framework for End-to-End Neural Network Speech Enhancement标题：端到端神经网络语音增强的多尺度自动编码器框架作者：Bengt J. Borgstrom,Michael S. Brandstein机构： This material is based upon work supported by theDepartment of Defense under Air Force Contract No, conclusions or recommendations expressed in thismaterial are those of the author(s) and do not necessarily reflect the views ofthe Department of Defense备注：13 pages, 9 figures链接：http://arxiv.org/pdf/2309.12121v1
【2】 Is the Ideal Ratio Mask Really the Best? -- Exploring the Best Extraction Performance and Optimal Mask of Mask-based Beamformers标题：理想的比例掩模真的是最好的吗？--探讨掩模波束形成器的最佳提取性能和最佳掩模作者：Atsuo Hiroe,Katsutoshi Itoyama,Kazuhiro Nakadai机构：∗ Department of Systems and Control Engineering, School of Engineering, Tokyo Institute of Technology, Tokyo, Japan, † Honda Research Institute Japan Co., Ltd., Saitama, Japan备注：Accepted in APSIPA 2023链接：http://arxiv.org/pdf/2309.12065v1
【3】 Multi-Channel MOSRA: Mean Opinion Score and Room Acoustics Estimation Using Simulated Data and a Teacher Model标题：多通道MOSRA：使用模拟数据和教师模型的平均意见得分和房间声学估计作者：Jozef Coldenhoff,Andrew Harper,Paul Kendrick,Tijana Stojkovic,Milos Cernak机构：Logitech Europe S.A., Lausanne, Switzerland, ´Ecole Polytechnique F´ed´erale de Lausanne (EPFL), Lausanne, Switzerland链接：http://arxiv.org/pdf/2309.11976v1【4】 Cluster-based pruning techniques for audio data标题：基于簇的音频数据剪枝技术作者：Boris Bergsma,Marta Brzezinska,Oleg V. Yazyev,Milos Cernak机构：Institute of Physics, Ecole Polytechnique F´ed´erale de Lausanne (EPFL), CH-, Lausanne, Switzerland, Logitech Europe S.A., Lausanne, Switzerland, ∗equal contribution链接：http://arxiv.org/pdf/2309.11922v1【5】 The Impact of Silence on Speech Anti-Spoofing标题：沉默对语音反欺骗的影响作者：Yuxiang Zhang,Zhuo Li,Jingze Lu,Hua Hua,Wenchao Wang,Pengyuan Zhang机构：)The authors are with Key Laboratory of Speech Acoustics and ContentUnderstanding, Institute of Acoustics, China and also with University of Chinese Academy of Sciences备注：16 pages, 9 figures, 13 tables链接：http://arxiv.org/pdf/2309.11827v1【6】 CoMFLP: Correlation Measure based Fast Search on ASR Layer Pruning标题：CoMFLP：基于相关性度量的ASR层剪枝快速搜索作者：Wei Liu,Zhiyuan Peng,Tan Lee机构：Department of Electronic Engineering, The Chinese University of Hong Kong备注：Accepted by Interspeech 2023链接：http://arxiv.org/pdf/2309.11768v1【7】 Sparsely Shared LoRA on Whisper for Child Speech Recognition标题：用于儿童语音识别的稀疏共享Lora on Whisper作者：Wei Liu,Ying Qin,Zhiyuan Peng,Tan Lee机构： Department of Electronic Engineering, The Chinese University of Hong Kong, Institute of Information Science, Beijing Jiaotong University, Beijing , China备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.11756v1【8】 Leveraging In-the-Wild Data for Effective Self-Supervised Pretraining in Speaker Recognition标题：在说话人识别中利用野外数据进行有效的自我监督预训练作者：Shuai Wang,Qibing Bai,Qi Liu,Jianwei Yu,Zhengyang Chen,Bing Han,Yanmin Qian,Haizhou Li机构：Shenzhen Research Institute of Big Data, Shenzhen, China, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), China, Tencent, Shenzhen, China, Shanghai Jiao Tong University, Shanghai, China备注：submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.11730v1【9】 TalkNCE: Improving Active Speaker Detection with Talk-Aware Contrastive Learning标题：TalkNCE：利用谈话感知对比学习改进主动说话人检测作者：Chaeyoung Jung,Suyeon Lee,Kihyun Nam,Kyeongha Rho,You Jin Kim,Youngjoon Jang,Joon Son Chung机构：Korea Advanced Institute of Science and Technology, South Korea, Naver Cloud Corporation, South Korea链接：http://arxiv.org/pdf/2309.12306v1【10】 Performance Conditioning for Diffusion-Based Multi-Instrument Music Synthesis标题：基于扩散的多乐器音乐合成中的性能调节作者：Ben Maman,Johannes Zeitler,Meinard Müller,Amit H. Bermano机构：⋆ Tel Aviv University, †International Audio Laboratories Erlangen, Germany备注：5 pages, project page available at benadar293.github.iomidipm链接：http://arxiv.org/pdf/2309.12283v1【11】 Variational Quantum Harmonizer: Generating Chord Progressions and Other Sonification Methods with the VQE Algorithm标题：变分量子调和器：用VQE算法生成和弦级数和其他发声方法作者：Paulo Vitor Itaboraí,Tim Schwägerl,María Aguado Yáñez,Arianna Crippa,Karl Jansen,Eduardo Reck Miranda,Peter Thomas机构： Eduardo R. Miranda, Interdisciplinary Centre for Computer Music Research – University of Plymouth, Drake Circus - PL,AA - Plymouth - United Kingdom, Centre for Quantum Technologies and Applications – Deutsches Elektronen-Synchrotron DESY备注：Manuscript Accepted to the 2nd International Symposium on Quantum Computing and Musical Creativity (ISQCMC Berlin). Link: this https URL链接：http://arxiv.org/pdf/2309.12254v1【12】 Weakly-supervised Automated Audio Captioning via text only training标题：基于纯文本训练的弱监督自动音频字幕作者：Theodoros Kouzelis,Vassilis Katsouros机构：Institute for Language and Speech Processing, Athena Research Center, Marousi, Greece备注：DCASE Workshop 2023链接：http://arxiv.org/pdf/2309.12242v1【13】 t-EER: Parameter-Free Tandem Evaluation of Countermeasures and Biometric Comparators标题：T-EER：对策和生物特征比较器的无参数串联评估作者：Tomi Kinnunen,Kong Aik Lee,Hemlata Tak,Nicholas Evans,Andreas Nautsch机构：This paper has been accepted for publication in IEEE Transactions on Pattern Analysis and Machine Intelligence. If you would, like to cite the work, please use the following bibliographic entry.备注：To appear in IEEE Transactions on Pattern Analysis and Machine Intelligence. For associated codes, see this https URL (Github) and this https URL (Google Colab)链接：http://arxiv.org/pdf/2309.12237v1【14】 Bridging the Gaps of Both Modality and Language: Synchronous Bilingual CTC for Speech Translation and Speech Recognition标题：弥合情态和语言的鸿沟：用于语音翻译和语音识别的同步双语CTC作者：Chen Xu,Xiaoqian Liu,Erfeng He,Yuhao Zhang,Qianqian Dong,Tong Xiao,Jingbo Zhu,Dapeng Man,Wu Yang机构：Harbin Engineering University, School of Computer Science and Engineering, Northeastern University, Shenyang, China, ByteDance, NiuTrans Research, Shenyang, China备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.12234v1【15】 Towards Robust and Truly Large-Scale Audio-Sheet Music Retrieval标题：走向稳健和真正大规模的音表音乐检索作者：Luis Carvalho,Gerhard Widmer机构：Institute of Computational Perception & ,LIT Artificial Intelligence Lab, Johannes Kepler University Linz, Austria备注：Proceedings of the IEEE 6th International Conference on Multimedia Information Processing and Retrieval (MIPR)链接：http://arxiv.org/pdf/2309.12158v1【16】 Self-Supervised Contrastive Learning for Robust Audio-Sheet Music Retrieval Systems标题：基于自监督对比学习的稳健音表音乐检索系统作者：Luis Carvalho,Tobias Washüttl,Gerhard Widmer机构：Institute of Computational Perception, Johannes Kepler University Linz, Austria, LIT Artificial Intelligence LabJournal-ref：Proceedings of the 14th ACM Multimedia Systems Conference (MMSys '23), June 7-10, 2023, Vancouver, BC, Canada链接：http://arxiv.org/pdf/2309.12134v1【17】 Passage Summarization with Recurrent Models for Audio-Sheet Music Retrieval标题：基于递归模型的音表音乐检索小结作者：Luis Carvalho,Gerhard Widmer机构：Institute of Computational Perception & ,LIT Artificial Intelligence Lab, Johannes Kepler University Linz, Austria备注：In Proceedings of the 24th Conference of the International Society for Music Information Retrieval (ISMIR 2023), Milan, Italy链接：http://arxiv.org/pdf/2309.12111v1【18】 Improving Language Model-Based Zero-Shot Text-to-Speech Synthesis with Multi-Scale Acoustic Prompts标题：利用多尺度声学提示改进基于语言模型的零发声文语合成作者：Shun Lei,Yixuan Zhou,Liyang Chen,Dan Luo,Zhiyong Wu,Xixin Wu,Shiyin Kang,Tao Jiang,Yahui Zhou,Yuxing Han,Helen Meng机构： Shenzhen International Graduate School, Tsinghua University, Shenzhen, Skywork AI PTE. LTD., Beijing , The Chinese University of Hong Kong, Hong Kong SAR备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.11977v1【19】 Audio Contrastive based Fine-tuning标题：基于音频对比度的微调作者：Yang Wang,Qibin Liang,Chenghao Xiao,Yizhi Li,Noura Al Moubayed,Chenghua Lin机构：Department of Computer Science, The University of Sheffield, UK, Department of Computer Science, The University of Manchester, UK, Department of Computer Science, Durham University, UK, Automated Analytics, UK ,Rainbow-Flower AI, China备注：Under review in ICASSP链接：http://arxiv.org/pdf/2309.11895v1【20】 A Discourse-level Multi-scale Prosodic Model for Fine-grained Emotion Analysis标题：面向细粒度情感分析的语篇级多尺度韵律模型作者：Xianhao Wei,Jia Jia,Xiang Li,Zhiyong Wu,Ziyi Wang机构：Department of Computer Science and Technology, Tsinghua University, Beijing, China, Shenzhen International Graduate School, Shenzhen, China, Academy of Arts and Design备注：ChinaMM 2023链接：http://arxiv.org/pdf/2309.11849v1【21】 TMac: Temporal Multi-Modal Graph Learning for Acoustic Event Classification标题：TMAC：用于声事件分类的时态多模图学习作者：Meng Liu,Ke Liang,Dayu Hu,Hao Yu,Yue Liu,Lingyuan Meng,Wenxuan Tu,Sihang Zhou,Xinwang Liu机构：National University of Defense, Technology链接：http://arxiv.org/pdf/2309.11845v1【22】 Frame Pairwise Distance Loss for Weakly-supervised Sound Event Detection标题：弱监督声事件检测中的帧对距离损失算法作者：Rui Tao,Yuxing Huang,Xiangdong Wang,Long Yan,Lufeng Zhai,Kazushige Ouchi,Taihao Li机构： Toshiba China R&D Center, Beijing, China., Zhejiang Lab, Zhejiang, China., Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China.备注：siibmited to ICASSP 2024链接：http://arxiv.org/pdf/2309.11783v1
【23】 FluentEditor: Text-based Speech Editing by Considering Acoustic and Prosody Consistency标题：考虑声学和韵律一致性的基于文本的语音编辑作者：Rui Liu,Jiatian Xi,Ziyue Jiang,Haizhou Li机构： Inner Mongolia University, Hohhot, China , Zhejiang University, China, Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), China, National University of Singapore, Singapore备注：Submitted to ICASSP'2024链接：http://arxiv.org/pdf/2309.11725v1
机器翻译，仅供参考