今日论文合集：cs.SD语音50篇，eess.AS音频处理52篇。
cs.SD语音
【1】 Augmenting conformers with structured state space models for online speech recognition标题：利用结构化状态空间模型增强一致性以用于在线语音识别作者：Haozhe Shan,Albert Gu,Zhong Meng,Weiran Wang,Krzysztof Choromanski,Tara Sainath机构：Google LLC.链接：http://arxiv.org/pdf/2309.08551v1
【2】 Audio-Visual Active Speaker Extraction for Sparsely Overlapped Multi-talker Speech标题：稀疏重叠多人语音的视听主动说话人提取作者：Junjie Li,Ruijie Tao,Zexu Pan,Meng Ge,Shuai Wang,Haizhou Li机构：Shenzhen Research Institute of Big Data, Shenzhen, China, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), China, Department of Electrical and Computer Engineering, National University of Singapore, Singapore备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08408v1【3】 Exploring Meta Information for Audio-based Zero-shot Bird Classification标题：基于音频的零拍鸟分类的元信息探索作者：Alexander Gebhard,Andreas Triantafyllopoulos,Teresa Bez,Lukas Christ,Alexander Kathan,Björn W. Schuller机构：Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany, GLAM – Group on Language, Audio, & Music, Imperial College London, UK备注：This work has been submitted to the IEEE for possible publication链接：http://arxiv.org/pdf/2309.08398v1【4】 HM-Conformer: A Conformer-based audio deepfake detection system with hierarchical pooling and multi-level classification token aggregation methods标题：HM-Conform：一种基于Conform的分级池化多级分类令牌聚合音频深度伪检测系统作者：Hyun-seo Shin,Jungwoo Heo,Ju-ho Kim,Chan-yeong Lim,Wonbin Kim,Ha-Jin Yu机构：School of Computer Science, University of Seoul备注：Submitted to 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2024)链接：http://arxiv.org/pdf/2309.08208v1【5】 TF-SepNet: An Efficient 1D Kernel Design in CNNs for Low-Complexity Acoustic Scene Classification标题：TF-SepNet：一种用于低复杂度声学场景分类的高效一维CNN核设计作者：Yiqiang Cai,Peihong Zhang,Shengchen Li机构：School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Ren’ai Road, Suzhou, China备注：Submitted to the 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024)链接：http://arxiv.org/pdf/2309.08200v1【6】 Controllable Residual Speaker Representation for Voice Conversion标题：用于语音转换的可控剩余说话人表示作者：Le Xu,Jiangyan Yi,Jianhua Tao,Tao Wang,Yong Ren,Rongxiu Zhong机构：School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China, State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Department of Automation, Tsinghua University, Beijing, China备注：submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08166v1【7】 Unimodal Aggregation for CTC-based Speech Recognition标题：用于基于CTC的语音识别的单峰聚集作者：Ying Fang,Xiaofei Li机构：Zhejiang University, Hangzhou, China, Westlake University & Westlake Institute for Advanced Study, Hangzhou, China链接：http://arxiv.org/pdf/2309.08150v1【8】 Syn-Att: Synthetic Speech Attribution via Semi-Supervised Unknown Multi-Class Ensemble of CNNs标题：SYN-ATT：基于半监督未知CNN多类集成的合成语音属性作者：Md Awsafur Rahman,Bishmoy Paul,Najibul Haque Sarker,Zaber Ibn Abdul Hakim,Shaikh Anowarul Fattah,Mohammad Saquib机构：Dept. of EEE, BUET, Bangladesh, Dept. of CSE, BUET, Bangladesh, Dept. of EE, UT Dallas, Texas, USA备注：Winning Solution of IEEE SP Cup at ICASSP 2022链接：http://arxiv.org/pdf/2309.08146v1【9】 Two-Step Knowledge Distillation for Tiny Speech Enhancement标题：用于微小语音增强的两步知识提取作者：Rayan Daod Nathoo,Mikolaj Kegler,Marko Stamenovic机构：Bose Corporation, USA备注：Under review ICASSP 2024链接：http://arxiv.org/pdf/2309.08144v1【10】 Diversity-based core-set selection for text-to-speech with linguistic and acoustic features标题：基于多样性的具有语言和声学特征的文语转换核集选择作者：Kentaro Seki,Shinnosuke Takamichi,Takaaki Saeki,Hiroshi Saruwatari机构：The University of Tokyo, Japan.链接：http://arxiv.org/pdf/2309.08127v1【11】 Foundation Model Assisted Automatic Speech Emotion Recognition: Transcribing, Annotating, and Augmenting标题：基础模型辅助的自动语音情感识别：转录、标注和增强作者：Tiantian Feng,Shrikanth Narayanan机构：Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, USA备注：Under review链接：http://arxiv.org/pdf/2309.08108v1【12】 Characterizing the temporal dynamics of universal speech representations for generalizable deepfake detection标题：用于泛化深度伪检测的通用语音表示的时间动力学特征作者：Yi Zhu,Saurabh Powar,Tiago H. Falk机构：Institut national de la recherche scientifique, INRS-EMT, University of Qu´ebec, Montr´eal, Canada备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08099v1【13】 hear-your-action: human action recognition by ultrasound active sensing标题：听到你的行动：通过超声主动感知识别人类行动作者：Risako Tanigawa,Yasunori Ishii机构：Panasonic Holdings Corporation, Yagumonaka-machi, Moriguchi City, Osaka, Japan链接：http://arxiv.org/pdf/2309.08087v1【14】 SSL-Net: A Synergistic Spectral and Learning-based Network for Efficient Bird Sound Classification标题：SSL-Net：一种基于协同频谱和学习的高效鸟声分类网络作者：Yiyuan Yang,Kaichen Zhou,Niki Trigoni,Andrew Markham机构：Department of Computer Science, University of Oxford, United Kingdom链接：http://arxiv.org/pdf/2309.08072v1【15】 Retrieval-Augmented Text-to-Audio Generation标题：检索-增强的文本到音频生成作者：Yi Yuan,Haohe Liu,Xubo Liu,Qiushi Huang,Mark D. Plumbley,Wenwu Wang机构：School of Computer Science and Electronic Engineering, University of Surrey, UK备注：Submitted to ICASSP 2023链接：http://arxiv.org/pdf/2309.08051v1【16】 VoicePAT: An Efficient Open-source Evaluation Toolkit for Voice Privacy Research标题：VoicePAT：一种用于语音隐私研究的高效开源评估工具作者：Sarina Meyer,Xiaoxiao Miao,Ngoc Thang Vu备注：Submitted to OJSP-ICASSP 2024链接：http://arxiv.org/pdf/2309.08049v1【17】 Comparative Assessment of Markov Models and Recurrent Neural Networks for Jazz Music Generation标题：马尔可夫模型和递归神经网络在爵士乐生成中的比较评估作者：Conrad Hsu,Ross Greer机构：Carlmont High School, Belmont, CA, Electrical & Computer Engineering, University of California San Diego, La Jolla, CA, Student Authors, SUMMARY链接：http://arxiv.org/pdf/2309.08027v1【18】 Folding Attention: Memory and Power Optimization for On-Device Transformer-based Streaming Speech Recognition标题：折叠注意力：基于设备Transformer的流传输语音识别的存储和功耗优化作者：Yang Li,Liangzhen Lai,Yuan Shangguan,Forrest N. Iandola,Ernie Chang,Yangyang Shi,Vikas Chandra机构：Meta AI链接：http://arxiv.org/pdf/2309.07988v1【19】 SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systems标题：SLMIA-SR：针对说话人识别系统的说话人级别成员推理攻击作者：Guangke Chen,Yedi Zhang,Fu Song机构：ShanghaiTech University, Automotive Software Innovation Center, Institute of Software, Chinese Academy of Sciences & University of Chinese Academy of Sciences备注：Accepted by the 31st Network and Distributed System Security (NDSS) Symposium, 2024链接：http://arxiv.org/pdf/2309.07983v1【20】 Prompting Segmentation with Sound is Generalizable Audio-Visual Source Localizer标题：用声音提示分割是可推广的视听信源定位器作者：Yaoting Wang,Weisong Liu,Guangyao Li,Jian Ding,Di Hu,Xi Li机构：Gaoling School of Artificial Intelligence, Renmin University of China, School of Computer Science, Northwest Polytechnical University, LIESMARS, Wuhan Univrsity, College of Computer Science and Technology, Zhejiang University备注：12 pages, 7 figures, submitted to AAAI 2024链接：http://arxiv.org/pdf/2309.07929v1【21】 Open-vocabulary Keyword-spotting with Adaptive Instance Normalization标题：基于自适应实例归一化的开放词汇表关键词发现作者：Aviv Navon,Aviv Shamsian,Neta Glazer,Gill Hetz,Joseph Keshet机构：aiOla Research备注：Under Review链接：http://arxiv.org/pdf/2309.08561v1【22】 Towards Word-Level End-to-End Neural Speaker Diarization with Auxiliary Network标题：基于辅助网络的词级端到端神经说话人对象化作者：Yiling Huang,Weiran Wang,Guanlong Zhao,Hank Liao,Wei Xia,Quan Wang机构：Google LLC, USA链接：http://arxiv.org/pdf/2309.08489v1【23】 Mixture Encoder Supporting Continuous Speech Separation for Meeting Recognition标题：用于会议识别的支持连续语音分离的混合编码器作者：Peter Vieting,Simon Berger,Thilo von Neumann,Christoph Boeddeker,Ralf Schlüter,Reinhold Haeb-Umbach机构：Machine Learning and Human Language Technology, Computer Science Department, RWTH Aachen University, Germany, AppTek GmbH, Germany, Paderborn University, Germany备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08454v1【24】 Chunked Attention-based Encoder-Decoder Model for Streaming Speech Recognition标题：基于块注意力的流传输语音识别编解码器模型作者：Mohammad Zeineldeen,Albert Zeyer,Ralf Schlüter,Hermann Ney机构：Machine Learning and Human Language Technology, Computer Science Department, RWTH Aachen University, Germany, AppTek GmbH, Germany备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08436v1【25】 DiaCorrect: Error Correction Back-end For Speaker Diarization标题：DiaEqut：扬声器二元化的纠错后端作者：Jiangyu Han,Federico Landini,Johan Rohdin,Mireia Diez,Lukas Burget,Yuhang Cao,Heng Lu,Jan Cernocky机构：Ximalaya Inc., Shanghai, China备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08377v1【26】 Audio-free Prompt Tuning for Language-Audio Models标题：语言-音频模型的免费音频提示调谐作者：Yiming Li,Xiangdong Wang,Hong Liu机构：Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China., University of Chinese Academy of Sciences, Beijing, China.备注：submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08357v1【27】 Semi-supervised Sound Event Detection with Local and Global Consistency Regularization标题：基于局部和全局一致性正则化的半监督声事件检测作者：Yiming Li,Xiangdong Wang,Hong Liu,Rui Tao,Long Yan,Kazushige Ouchi机构：Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China., University of Chinese Academy of Sciences, Beijing, China., Toshiba China R&D Center, Beijing, China.备注：submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08355v1【28】 The Multimodal Information Based Speech Processing (MISP) 2023 Challenge: Audio-Visual Target Speaker Extraction标题：基于多模式信息的语音处理(MISP2023)挑战：视听目标说话人提取作者：Shilong Wu,Chenxi Wang,Hang Chen,Yusheng Dai,Chenyue Zhang,Ruoyu Wang,Hongbo Lan,Jun Du,Chin-Hui Lee,Jingdong Chen,Shinji Watanabe,Sabato Marco Siniscalchi,Odette Scharenborg,Zhong-Qiu Wang,Jia Pan,Jianqing Gao机构：University of Science and Technology of China, China , Georgia Institute of Technology, USA, Northwestern Polytechnical University, China , Carnegie Mellon University, USA备注：5 pages, 4 figures链接：http://arxiv.org/pdf/2309.08348v1【29】 Diff-SV: A Unified Hierarchical Framework for Noise-Robust Speaker Verification Using Score-Based Diffusion Probabilistic Models标题：DIFF-SV：基于分数扩散概率模型的抗噪说话人确认统一分层框架作者：Ju-ho Kim,Jungwoo Heo,Hyun-seo Shin,Chan-yeong Lim,Ha-Jin Yu机构：School of Computer Science, University of Seoul备注：5 pages, 2 figures, submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08320v1【30】 A Real-Time Active Speaker Detection System Integrating an Audio-Visual Signal with a Spatial Querying Mechanism标题：一种结合视听信号和空间查询机制的实时主动说话人检测系统作者：Ilya Gurvich,Ido Leichter,Dharmendar Reddy Palle,Yossi Asher,Alon Vinnikov,Igor Abramovski,Vishak Gopal,Ross Cutler,Eyal Krupka机构：Microsoft Corporation链接：http://arxiv.org/pdf/2309.08295v1【31】 Speech-dependent Modeling of Own Voice Transfer Characteristics for In-ear Microphones in Hearables标题：人耳入耳式麦克风自身语音传递特性的语音相关建模作者：Mattes Ohlenbusch,Christian Rollwage,Simon Doclo机构：Fraunhofer Institute for Digital Media Technology IDMT, Oldenburg Branch for Hearing, Speech and Audio Technology HSA, Germany, University of Oldenburg, Department of Medical Physics and Acoustics, and Cluster of Excellence Hearing,all, Germany备注：Presented at Forum Acusticum 2023链接：http://arxiv.org/pdf/2309.08294v1【32】 Head-Related Transfer Function Interpolation with a Spherical CNN标题：基于球面细胞神经网络的头部相关传递函数内插作者：Xingyu Chen,Fei Ma,Yile Zhang,Amy Bastine,Prasanga N. Samarasinghe机构：Audio and Acoustic Signal Processing Group, Australian National University链接：http://arxiv.org/pdf/2309.08290v1【33】 One-Class Knowledge Distillation for Spoofing Speech Detection标题：用于欺骗语音检测的一类知识提取作者：Jingze Lu,Yuxiang Zhang,Wenchao Wang,Zengqiang Shang,Pengyuan Zhang机构：Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, University of Chinese Academy of Sciences, Beijing, China备注：submitted to icassp 2024链接：http://arxiv.org/pdf/2309.08285v1【34】 Improving Short Utterance Anti-Spoofing with AASIST2标题：基于AASIST2的短话抗欺骗性改进作者：Yuxiang Zhang,Jingze Lu,Zengqiang Shang,Wenchao Wang,Pengyuan Zhang机构：Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, University of Chinese Academy of Sciences, Beijing, China备注：5 pages, 2 figures链接：http://arxiv.org/pdf/2309.08279v1【35】 Improving Voice Conversion for Dissimilar Speakers Using Perceptual Losses标题：利用知觉损失改善不同说话人的语音转换作者：Suhita Ghosh1,Yamini Sinha,Ingo Siegert,Sebastian Stober机构：Artificial Intelligence Lab, Otto-von-Guericke-University Magdeburg, Germany, Mobile Dialog Systems, Otto-von-Guericke-University Magdeburg, Germany备注：Accepted in The German Annual Conference on Acoustics 2023 (DAGA)链接：http://arxiv.org/pdf/2309.08263v1【36】 Cross-lingual Knowledge Distillation via Flow-based Voice Conversion for Robust Polyglot Text-To-Speech标题：基于流的多语种语音转换跨语言知识提取作者：Dariusz Piotrowski,Renard Korzeniowski,Alessio Falai,Sebastian Cygert,Kamil Pokora,Georgi Tinchev,Ziyao Zhang,Kayoko Yanagisawa机构：Alexa AI, Amazon, Gdańsk University of Technology, Gdańsk, Poland备注：Accepted at ICONIP 2023链接：http://arxiv.org/pdf/2309.08255v1【37】 RVAE-EM: Generative speech dereverberation based on recurrent variational auto-encoder and convolutive transfer function标题：RVAE-EM：基于递归变分自动编码器和卷积传递函数的生成性语音去混响作者：Pengyu Wang,Xiaofei Li机构：Zhejiang University, Hangzhou, China, Westlake University & Westlake Institute for Advanced Study, Hangzhou, China备注：Submitted to ICASSP2024链接：http://arxiv.org/pdf/2309.08157v1【38】 Fine-tune the pretrained ATST model for sound event detection标题：微调用于声音事件检测的预先训练的ATST模型作者：Nian Shao,Xian Li,Xiaofei Li机构：Zhejiang University, Hangzhou, China, Westlake University & Westlake Institute for Advanced Study, Hangzhou, China备注：5 pages, 3 figures, this paper is submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08153v1【39】 Audio Difference Learning for Audio Captioning标题：用于音频字幕的音频差异学习作者：Tatsuya Komatsu,Yusuke Fujita,Kazuya Takeda,Tomoki Toda机构：LINE Corporation, Japan,Nagoya University, Japan备注：submitted to ICASSP2024链接：http://arxiv.org/pdf/2309.08141v1【40】 PromptTTS++: Controlling Speaker Identity in Prompt-Based Text-to-Speech Using Natural Language Descriptions标题：PromptTTS++：使用自然语言描述在基于提示的文语转换中控制说话人身份作者：Reo Shimizu,Ryuichi Yamamoto,Masaya Kawamura,Yuma Shirahata,Hironori Doi,Tatsuya Komatsu,Kentaro Tachibana机构：Tohoku University, Japan,LINE Corp., Japan.备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08140v1【41】 t-SOT FNT: Streaming Multi-talker ASR with Text-only Domain Adaptation Capability标题：T-SOT FNT：具有纯文本域适配能力的流媒体多人通话ASR作者：Jian Wu,Naoyuki Kanda,Takuya Yoshioka,Rui Zhao,Zhuo Chen,Jinyu Li机构：Microsoft, One Microsoft Way, Redmond, WA, USA备注：5 pages, 2 figures, submitted to ICASSP2024链接：http://arxiv.org/pdf/2309.08131v1【42】 Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context标题：LibriHeavy：一个50,000小时的ASR语料库，带有标点符号大小写和上下文作者：Wei Kang,Xiaoyu Yang,Zengwei Yao,Fangjun Kuang,Yifan Yang,Liyong Guo,Long Lin,Daniel Povey机构：Xiaomi Corp., Beijing, China备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08105v1【43】 DDSP-SFX: Acoustically-guided sound effects generation with differentiable digital signal processing标题：DDSP-SFX：利用可差分数字信号处理的声导音效生成作者：Yunyi Liu,Craig Jin,David Gunawan机构：University of Sydney,Dolby Laboratory链接：http://arxiv.org/pdf/2309.08060v1
【44】 AV2Wav: Diffusion-Based Re-synthesis from Continuous Self-supervised Features for Audio-Visual Speech Enhancement标题：AV2Wav：基于扩散的连续自监督特征重合成视听语音增强作者：Ju-Chieh Chou,Chung-Ming Chien,Karen Livescu机构：Toyota Technological Institute at Chicago备注：Submitted to ICASSP链接：http://arxiv.org/pdf/2309.08030v1【45】 USM-SCD: Multilingual Speaker Change Detection Based on Large Pretrained Foundation Models标题：USM-SCD：基于大型预训练基础模型的多语言说话人变化检测作者：Guanlong Zhao,Yongqiang Wang,Jason Pelecanos,Yu Zhang,Hank Liao,Yiling Huang,Han Lu,Quan Wang机构：Google LLC, USA备注：5 pages, 2 figures链接：http://arxiv.org/pdf/2309.08023v1【46】 DiariST: Streaming Speech Translation with Speaker Diarization标题：日记本作者：使用说话人二元化的流媒体语音翻译作者：Mu Yang,Naoyuki Kanda,Xiaofei Wang,Junkun Chen,Peidong Wang,Jian Xue,Jinyu Li,Takuya Yoshioka机构：Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX, USA, Microsoft, One Microsoft Way, Redmond, WA, USA备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08007v1【47】 Efficient Face Detection with Audio-Based Region Proposals标题：基于音频区域建议的高效人脸检测作者：William Aris,François Grondin机构：1William Aris and Franc¸ois Grondin are with the Department of Elec-trical Engineering and Computer Engineering, Interdisciplinary Institutefor Technological Innovation ( 3IT), de l’Universit´e链接：http://arxiv.org/pdf/2309.08005v1【48】 Voxtlm: unified decoder-only models for consolidating speech recognitionsynthesis and speechtext continuation tasks标题：Voxtlm：统一的仅解码器模型，用于合并语音识别合成和语音文本继续任务作者：Soumi Maiti,Yifan Peng,Shukjae Choi,Jee-weon Jung,Xuankai Chang,Shinji Watanabe机构：Carnegie Mellon University, USA, dot Inc., Republic of Korea链接：http://arxiv.org/pdf/2309.07937v1【49】 Kid-Whisper: Towards Bridging the Performance Gap in Automatic Speech Recognition for Children VS. Adults标题：儿童-耳语：为儿童自动语音识别弥合性能差距VS。成虫作者：Ahmed Adel Attia,Jing Liu,Wei Ai,Dorottya Demszky,Carol Espy-Wilson机构：University of Maryland College Park, MD, USA, Stanford University, CA, USA链接：http://arxiv.org/pdf/2309.07927v1【50】 Hierarchical Audio-Visual Information Fusion with Multi-label Joint Decoding for MER 2023标题：面向MER 2023的多标签联合译码分层视听信息融合作者：Haotian Wang,Yuxuan Xi,Hang Chen,Jun Du,Yan Song,Qing Wang,Hengshun Zhou,Chenxi Wang,Jiefeng Ma,Pengfei Hu,Ya Jiang,Shi Cheng,Jie Zhang,Yuzhe Weng机构：University of Science and Technology, of China, Hefei, Anhui, China, Northwestern Polytechnical, Xi’an, Shaanxi, ChinaJournal-ref：The 31st ACM International Conference on Multimedia (MM'23), 2023链接：http://arxiv.org/pdf/2309.07925v1

eess.AS音频处理
【1】 Open-vocabulary Keyword-spotting with Adaptive Instance Normalization标题：基于自适应实例归一化的开放词汇表关键词发现作者：Aviv Navon,Aviv Shamsian,Neta Glazer,Gill Hetz,Joseph Keshet机构：aiOla Research备注：Under Review链接：http://arxiv.org/pdf/2309.08561v1
【2】 Towards Word-Level End-to-End Neural Speaker Diarization with Auxiliary Network标题：基于辅助网络的词级端到端神经说话人对象化作者：Yiling Huang,Weiran Wang,Guanlong Zhao,Hank Liao,Wei Xia,Quan Wang机构：Google LLC, USA链接：http://arxiv.org/pdf/2309.08489v1【3】 Mixture Encoder Supporting Continuous Speech Separation for Meeting Recognition标题：用于会议识别的支持连续语音分离的混合编码器作者：Peter Vieting,Simon Berger,Thilo von Neumann,Christoph Boeddeker,Ralf Schlüter,Reinhold Haeb-Umbach机构：Machine Learning and Human Language Technology, Computer Science Department, RWTH Aachen University, Germany, AppTek GmbH, Germany, Paderborn University, Germany备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08454v1【4】 Chunked Attention-based Encoder-Decoder Model for Streaming Speech Recognition标题：基于块注意力的流传输语音识别编解码器模型作者：Mohammad Zeineldeen,Albert Zeyer,Ralf Schlüter,Hermann Ney机构：Machine Learning and Human Language Technology, Computer Science Department, RWTH Aachen University, Germany, AppTek GmbH, Germany备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08436v1
【5】 DiaCorrect: Error Correction Back-end For Speaker Diarization标题：DiaEqut：扬声器二元化的纠错后端作者：Jiangyu Han,Federico Landini,Johan Rohdin,Mireia Diez,Lukas Burget,Yuhang Cao,Heng Lu,Jan Cernocky机构：Ximalaya Inc., Shanghai, China备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08377v1【6】 Audio-free Prompt Tuning for Language-Audio Models标题：语言-音频模型的免费音频提示调谐作者：Yiming Li,Xiangdong Wang,Hong Liu机构： Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China., University of Chinese Academy of Sciences, Beijing, China.备注：submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08357v1【7】 Semi-supervised Sound Event Detection with Local and Global Consistency Regularization标题：基于局部和全局一致性正则化的半监督声事件检测作者：Yiming Li,Xiangdong Wang,Hong Liu,Rui Tao,Long Yan,Kazushige Ouchi机构： Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China., University of Chinese Academy of Sciences, Beijing, China., Toshiba China R&D Center, Beijing, China.备注：submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08355v1【8】 The Multimodal Information Based Speech Processing (MISP) 2023 Challenge: Audio-Visual Target Speaker Extraction标题：基于多模式信息的语音处理(MISP2023)挑战：视听目标说话人提取作者：Shilong Wu,Chenxi Wang,Hang Chen,Yusheng Dai,Chenyue Zhang,Ruoyu Wang,Hongbo Lan,Jun Du,Chin-Hui Lee,Jingdong Chen,Shinji Watanabe,Sabato Marco Siniscalchi,Odette Scharenborg,Zhong-Qiu Wang,Jia Pan,Jianqing Gao机构： University of Science and Technology of China, China , Georgia Institute of Technology, USA, Northwestern Polytechnical University, China , Carnegie Mellon University, USA备注：5 pages, 4 figures链接：http://arxiv.org/pdf/2309.08348v1【9】 Diff-SV: A Unified Hierarchical Framework for Noise-Robust Speaker Verification Using Score-Based Diffusion Probabilistic Models标题：DIFF-SV：基于分数扩散概率模型的抗噪说话人确认统一分层框架作者：Ju-ho Kim,Jungwoo Heo,Hyun-seo Shin,Chan-yeong Lim,Ha-Jin Yu机构：School of Computer Science, University of Seoul备注：5 pages, 2 figures, submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08320v1
【10】 A Real-Time Active Speaker Detection System Integrating an Audio-Visual Signal with a Spatial Querying Mechanism标题：一种结合视听信号和空间查询机制的实时主动说话人检测系统作者：Ilya Gurvich,Ido Leichter,Dharmendar Reddy Palle,Yossi Asher,Alon Vinnikov,Igor Abramovski,Vishak Gopal,Ross Cutler,Eyal Krupka机构：Microsoft Corporation链接：http://arxiv.org/pdf/2309.08295v1【11】 Speech-dependent Modeling of Own Voice Transfer Characteristics for In-ear Microphones in Hearables标题：人耳入耳式麦克风自身语音传递特性的语音相关建模作者：Mattes Ohlenbusch,Christian Rollwage,Simon Doclo机构： Fraunhofer Institute for Digital Media Technology IDMT, Oldenburg Branch for Hearing, Speech and Audio Technology HSA, Germany, University of Oldenburg, Department of Medical Physics and Acoustics, and Cluster of Excellence Hearing,all, Germany备注：Presented at Forum Acusticum 2023链接：http://arxiv.org/pdf/2309.08294v1【12】 Head-Related Transfer Function Interpolation with a Spherical CNN标题：基于球面细胞神经网络的头部相关传递函数内插作者：Xingyu Chen,Fei Ma,Yile Zhang,Amy Bastine,Prasanga N. Samarasinghe机构：Audio and Acoustic Signal Processing Group, Australian National University链接：http://arxiv.org/pdf/2309.08290v1【13】 One-Class Knowledge Distillation for Spoofing Speech Detection标题：用于欺骗语音检测的一类知识提取作者：Jingze Lu,Yuxiang Zhang,Wenchao Wang,Zengqiang Shang,Pengyuan Zhang机构：Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, University of Chinese Academy of Sciences, Beijing, China备注：submitted to icassp 2024链接：http://arxiv.org/pdf/2309.08285v1【14】 Improving Short Utterance Anti-Spoofing with AASIST2标题：基于AASIST2的短话抗欺骗性改进作者：Yuxiang Zhang,Jingze Lu,Zengqiang Shang,Wenchao Wang,Pengyuan Zhang机构：Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, University of Chinese Academy of Sciences, Beijing, China备注：5 pages, 2 figures链接：http://arxiv.org/pdf/2309.08279v1【15】 Improving Voice Conversion for Dissimilar Speakers Using Perceptual Losses标题：利用知觉损失改善不同说话人的语音转换作者：Suhita Ghosh1,Yamini Sinha,Ingo Siegert,Sebastian Stober机构： Artificial Intelligence Lab, Otto-von-Guericke-University Magdeburg, Germany, Mobile Dialog Systems, Otto-von-Guericke-University Magdeburg, Germany备注：Accepted in The German Annual Conference on Acoustics 2023 (DAGA)链接：http://arxiv.org/pdf/2309.08263v1【16】 Cross-lingual Knowledge Distillation via Flow-based Voice Conversion for Robust Polyglot Text-To-Speech标题：基于流的多语种语音转换跨语言知识提取作者：Dariusz Piotrowski,Renard Korzeniowski,Alessio Falai,Sebastian Cygert,Kamil Pokora,Georgi Tinchev,Ziyao Zhang,Kayoko Yanagisawa机构： Alexa AI, Amazon, Gdańsk University of Technology, Gdańsk, Poland备注：Accepted at ICONIP 2023链接：http://arxiv.org/pdf/2309.08255v1【17】 RVAE-EM: Generative speech dereverberation based on recurrent variational auto-encoder and convolutive transfer function标题：RVAE-EM：基于递归变分自动编码器和卷积传递函数的生成性语音去混响作者：Pengyu Wang,Xiaofei Li机构：Zhejiang University, Hangzhou, China, Westlake University & Westlake Institute for Advanced Study, Hangzhou, China备注：Submitted to ICASSP2024链接：http://arxiv.org/pdf/2309.08157v1【18】 Fine-tune the pretrained ATST model for sound event detection标题：微调用于声音事件检测的预先训练的ATST模型作者：Nian Shao,Xian Li,Xiaofei Li机构： Zhejiang University, Hangzhou, China, Westlake University & Westlake Institute for Advanced Study, Hangzhou, China备注：5 pages, 3 figures, this paper is submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08153v1【19】 Audio Difference Learning for Audio Captioning标题：用于音频字幕的音频差异学习作者：Tatsuya Komatsu,Yusuke Fujita,Kazuya Takeda,Tomoki Toda机构：LINE Corporation, Japan,Nagoya University, Japan备注：submitted to ICASSP2024链接：http://arxiv.org/pdf/2309.08141v1【20】 PromptTTS++: Controlling Speaker Identity in Prompt-Based Text-to-Speech Using Natural Language Descriptions标题：PromptTTS++：使用自然语言描述在基于提示的文语转换中控制说话人身份作者：Reo Shimizu,Ryuichi Yamamoto,Masaya Kawamura,Yuma Shirahata,Hironori Doi,Tatsuya Komatsu,Kentaro Tachibana机构：Tohoku University, Japan,LINE Corp., Japan.备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08140v1
【21】 t-SOT FNT: Streaming Multi-talker ASR with Text-only Domain Adaptation Capability标题：T-SOT FNT：具有纯文本域适配能力的流媒体多人通话ASR作者：Jian Wu,Naoyuki Kanda,Takuya Yoshioka,Rui Zhao,Zhuo Chen,Jinyu Li机构：Microsoft, One Microsoft Way, Redmond, WA, USA备注：5 pages, 2 figures, submitted to ICASSP2024链接：http://arxiv.org/pdf/2309.08131v1【22】 Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context标题：LibriHeavy：一个50,000小时的ASR语料库，带有标点符号大小写和上下文作者：Wei Kang,Xiaoyu Yang,Zengwei Yao,Fangjun Kuang,Yifan Yang,Liyong Guo,Long Lin,Daniel Povey机构：Xiaomi Corp., Beijing, China备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08105v1
【23】 DDSP-SFX: Acoustically-guided sound effects generation with differentiable digital signal processing标题：DDSP-SFX：利用可差分数字信号处理的声导音效生成作者：Yunyi Liu,Craig Jin,David Gunawan机构：University of Sydney,Dolby Laboratory链接：http://arxiv.org/pdf/2309.08060v1【24】 AV2Wav: Diffusion-Based Re-synthesis from Continuous Self-supervised Features for Audio-Visual Speech Enhancement标题：AV2Wav：基于扩散的连续自监督特征重合成视听语音增强作者：Ju-Chieh Chou,Chung-Ming Chien,Karen Livescu机构：Toyota Technological Institute at Chicago备注：Submitted to ICASSP链接：http://arxiv.org/pdf/2309.08030v1【25】 USM-SCD: Multilingual Speaker Change Detection Based on Large Pretrained Foundation Models标题：USM-SCD：基于大型预训练基础模型的多语言说话人变化检测作者：Guanlong Zhao,Yongqiang Wang,Jason Pelecanos,Yu Zhang,Hank Liao,Yiling Huang,Han Lu,Quan Wang机构：Google LLC, USA备注：5 pages, 2 figures链接：http://arxiv.org/pdf/2309.08023v1【26】 DiariST: Streaming Speech Translation with Speaker Diarization标题：日记本作者：使用说话人二元化的流媒体语音翻译作者：Mu Yang,Naoyuki Kanda,Xiaofei Wang,Junkun Chen,Peidong Wang,Jian Xue,Jinyu Li,Takuya Yoshioka机构： Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX, USA, Microsoft, One Microsoft Way, Redmond, WA, USA备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08007v1【27】 Efficient Face Detection with Audio-Based Region Proposals标题：基于音频区域建议的高效人脸检测作者：William Aris,François Grondin机构： 1William Aris and Franc¸ois Grondin are with the Department of Elec-trical Engineering and Computer Engineering, Interdisciplinary Institutefor Technological Innovation ( 3IT), de l’Universit´e链接：http://arxiv.org/pdf/2309.08005v1【28】 Voxtlm: unified decoder-only models for consolidating speech recognitionsynthesis and speechtext continuation tasks标题：Voxtlm：统一的仅解码器模型，用于合并语音识别合成和语音文本继续任务作者：Soumi Maiti,Yifan Peng,Shukjae Choi,Jee-weon Jung,Xuankai Chang,Shinji Watanabe机构：Carnegie Mellon University, USA, dot Inc., Republic of Korea链接：http://arxiv.org/pdf/2309.07937v1
【29】 Kid-Whisper: Towards Bridging the Performance Gap in Automatic Speech Recognition for Children VS. Adults标题：儿童-耳语：为儿童自动语音识别弥合性能差距VS。成虫作者：Ahmed Adel Attia,Jing Liu,Wei Ai,Dorottya Demszky,Carol Espy-Wilson机构：University of Maryland College Park, MD, USA, Stanford University, CA, USA链接：http://arxiv.org/pdf/2309.07927v1【30】 Hierarchical Audio-Visual Information Fusion with Multi-label Joint Decoding for MER 2023标题：面向MER 2023的多标签联合译码分层视听信息融合作者：Haotian Wang,Yuxuan Xi,Hang Chen,Jun Du,Yan Song,Qing Wang,Hengshun Zhou,Chenxi Wang,Jiefeng Ma,Pengfei Hu,Ya Jiang,Shi Cheng,Jie Zhang,Yuzhe Weng机构：University of Science and Technology, of China, Hefei, Anhui, China, Northwestern Polytechnical, Xi’an, Shaanxi, ChinaJournal-ref：The 31st ACM International Conference on Multimedia (MM'23), 2023链接：http://arxiv.org/pdf/2309.07925v1【31】 Augmenting conformers with structured state space models for online speech recognition标题：利用结构化状态空间模型增强一致性以用于在线语音识别作者：Haozhe Shan,Albert Gu,Zhong Meng,Weiran Wang,Krzysztof Choromanski,Tara Sainath机构：Google LLC.链接：http://arxiv.org/pdf/2309.08551v1【32】 Visual Speech Recognition for Low-resource Languages with Automatic Labels From Whisper Model标题：基于耳语模型自动标注的低资源语言视觉语音识别作者：Jeong Hun Yeo,Minsu Kim,Shinji Watanabe,Yong Man Ro机构：Integrated Vision and Language Lab, KAIST, South Korea, Language Technologies Institute, Carnegie Mellon University, USA链接：http://arxiv.org/pdf/2309.08535v1
【33】 Towards Practical and Efficient Image-to-Speech Captioning with Vision-Language Pre-training and Multi-modal Tokens标题：基于视觉语言预训练和多模式标记的实用高效的图语转换字幕作者：Minsu Kim,Jeongsoo Choi,Soumi Maiti,Jeong Hun Yeo,Shinji Watanabe,Yong Man Ro机构：Integrated Vision and Language Lab, KAIST, South Korea, Language Technologies Institute, Carnegie Mellon University, USA链接：http://arxiv.org/pdf/2309.08531v1【34】 Audio-Visual Active Speaker Extraction for Sparsely Overlapped Multi-talker Speech标题：稀疏重叠多人语音的视听主动说话人提取作者：Junjie Li,Ruijie Tao,Zexu Pan,Meng Ge,Shuai Wang,Haizhou Li机构： Shenzhen Research Institute of Big Data, Shenzhen, China, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), China, Department of Electrical and Computer Engineering, National University of Singapore, Singapore备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08408v1【35】 Exploring Meta Information for Audio-based Zero-shot Bird Classification标题：基于音频的零拍鸟分类的元信息探索作者：Alexander Gebhard,Andreas Triantafyllopoulos,Teresa Bez,Lukas Christ,Alexander Kathan,Björn W. Schuller机构：Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany, GLAM – Group on Language, Audio, & Music, Imperial College London, UK备注：This work has been submitted to the IEEE for possible publication链接：http://arxiv.org/pdf/2309.08398v1【36】 HM-Conformer: A Conformer-based audio deepfake detection system with hierarchical pooling and multi-level classification token aggregation methods标题：HM-Conform：一种基于Conform的分级池化多级分类令牌聚合音频深度伪检测系统作者：Hyun-seo Shin,Jungwoo Heo,Ju-ho Kim,Chan-yeong Lim,Wonbin Kim,Ha-Jin Yu机构：School of Computer Science, University of Seoul备注：Submitted to 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2024)链接：http://arxiv.org/pdf/2309.08208v1【37】 TF-SepNet: An Efficient 1D Kernel Design in CNNs for Low-Complexity Acoustic Scene Classification标题：TF-SepNet：一种用于低复杂度声学场景分类的高效一维CNN核设计作者：Yiqiang Cai,Peihong Zhang,Shengchen Li机构：School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Ren’ai Road, Suzhou, China备注：Submitted to the 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024)链接：http://arxiv.org/pdf/2309.08200v1【38】 Controllable Residual Speaker Representation for Voice Conversion标题：用于语音转换的可控剩余说话人表示作者：Le Xu,Jiangyan Yi,Jianhua Tao,Tao Wang,Yong Ren,Rongxiu Zhong机构：School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China, State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Department of Automation, Tsinghua University, Beijing, China备注：submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08166v1
【39】 Unimodal Aggregation for CTC-based Speech Recognition标题：用于基于CTC的语音识别的单峰聚集作者：Ying Fang,Xiaofei Li机构： Zhejiang University, Hangzhou, China, Westlake University & Westlake Institute for Advanced Study, Hangzhou, China链接：http://arxiv.org/pdf/2309.08150v1【40】 Syn-Att: Synthetic Speech Attribution via Semi-Supervised Unknown Multi-Class Ensemble of CNNs标题：SYN-ATT：基于半监督未知CNN多类集成的合成语音属性作者：Md Awsafur Rahman,Bishmoy Paul,Najibul Haque Sarker,Zaber Ibn Abdul Hakim,Shaikh Anowarul Fattah,Mohammad Saquib机构： Dept. of EEE, BUET, Bangladesh, Dept. of CSE, BUET, Bangladesh, Dept. of EE, UT Dallas, Texas, USA备注：Winning Solution of IEEE SP Cup at ICASSP 2022链接：http://arxiv.org/pdf/2309.08146v1【41】 Two-Step Knowledge Distillation for Tiny Speech Enhancement标题：用于微小语音增强的两步知识提取作者：Rayan Daod Nathoo,Mikolaj Kegler,Marko Stamenovic机构：Bose Corporation, USA备注：Under review ICASSP 2024链接：http://arxiv.org/pdf/2309.08144v1【42】 Diversity-based core-set selection for text-to-speech with linguistic and acoustic features标题：基于多样性的具有语言和声学特征的文语转换核集选择作者：Kentaro Seki,Shinnosuke Takamichi,Takaaki Saeki,Hiroshi Saruwatari机构：The University of Tokyo, Japan.链接：http://arxiv.org/pdf/2309.08127v1【43】 Foundation Model Assisted Automatic Speech Emotion Recognition: Transcribing, Annotating, and Augmenting标题：基础模型辅助的自动语音情感识别：转录、标注和增强作者：Tiantian Feng,Shrikanth Narayanan机构：Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, USA备注：Under review链接：http://arxiv.org/pdf/2309.08108v1【44】 Characterizing the temporal dynamics of universal speech representations for generalizable deepfake detection标题：用于泛化深度伪检测的通用语音表示的时间动力学特征作者：Yi Zhu,Saurabh Powar,Tiago H. Falk机构：Institut national de la recherche scientifique, INRS-EMT, University of Qu´ebec, Montr´eal, Canada备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.08099v1
【45】 hear-your-action: human action recognition by ultrasound active sensing标题：听到你的行动：通过超声主动感知识别人类行动作者：Risako Tanigawa,Yasunori Ishii机构：Panasonic Holdings Corporation, Yagumonaka-machi, Moriguchi City, Osaka, Japan链接：http://arxiv.org/pdf/2309.08087v1
【46】 SSL-Net: A Synergistic Spectral and Learning-based Network for Efficient Bird Sound Classification标题：SSL-Net：一种基于协同频谱和学习的高效鸟声分类网络作者：Yiyuan Yang,Kaichen Zhou,Niki Trigoni,Andrew Markham机构：Department of Computer Science, University of Oxford, United Kingdom链接：http://arxiv.org/pdf/2309.08072v1【47】 Retrieval-Augmented Text-to-Audio Generation标题：检索-增强的文本到音频生成作者：Yi Yuan,Haohe Liu,Xubo Liu,Qiushi Huang,Mark D. Plumbley,Wenwu Wang机构：School of Computer Science and Electronic Engineering, University of Surrey, UK备注：Submitted to ICASSP 2023链接：http://arxiv.org/pdf/2309.08051v1【48】 VoicePAT: An Efficient Open-source Evaluation Toolkit for Voice Privacy Research标题：VoicePAT：一种用于语音隐私研究的高效开源评估工具作者：Sarina Meyer,Xiaoxiao Miao,Ngoc Thang Vu备注：Submitted to OJSP-ICASSP 2024链接：http://arxiv.org/pdf/2309.08049v1
【49】 Comparative Assessment of Markov Models and Recurrent Neural Networks for Jazz Music Generation标题：马尔可夫模型和递归神经网络在爵士乐生成中的比较评估作者：Conrad Hsu,Ross Greer机构： Carlmont High School, Belmont, CA, Electrical & Computer Engineering, University of California San Diego, La Jolla, CA, Student Authors, SUMMARY链接：http://arxiv.org/pdf/2309.08027v1【50】 Folding Attention: Memory and Power Optimization for On-Device Transformer-based Streaming Speech Recognition标题：折叠注意力：基于设备Transformer的流传输语音识别的存储和功耗优化作者：Yang Li,Liangzhen Lai,Yuan Shangguan,Forrest N. Iandola,Ernie Chang,Yangyang Shi,Vikas Chandra机构：Meta AI链接：http://arxiv.org/pdf/2309.07988v1【51】 SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systems标题：SLMIA-SR：针对说话人识别系统的说话人级别成员推理攻击作者：Guangke Chen,Yedi Zhang,Fu Song机构： ShanghaiTech University, Automotive Software Innovation Center, Institute of Software, Chinese Academy of Sciences & University of Chinese Academy of Sciences备注：Accepted by the 31st Network and Distributed System Security (NDSS) Symposium, 2024链接：http://arxiv.org/pdf/2309.07983v1【52】 Prompting Segmentation with Sound is Generalizable Audio-Visual Source Localizer标题：用声音提示分割是可推广的视听信源定位器作者：Yaoting Wang,Weisong Liu,Guangyao Li,Jian Ding,Di Hu,Xi Li机构： Gaoling School of Artificial Intelligence, Renmin University of China, School of Computer Science, Northwest Polytechnical University, LIESMARS, Wuhan Univrsity, College of Computer Science and Technology, Zhejiang University备注：12 pages, 7 figures, submitted to AAAI 2024链接：http://arxiv.org/pdf/2309.07929v1
机器翻译，仅供参考