语音/音频处理学术速递[9.12]

今日论文合集：cs.SD语音24篇，eess.AS音频处理24篇。

cs.SD语音

【1】 Kernel Interpolation of Incident Sound Field in Region Including Scattering Objects标题：含散射体区域入射声场的核内插链接：https://arxiv.org/abs/2309.05634

作者：Shoichi Koyama,Masaki Nakada,Juliano G. C. Ribeiro,Hiroshi Saruwatari机构：National Institute of Informatics,-,-, Hitotsubashi, Chiyoda-ku, Tokyo ,-, Japan, The University of Tokyo,-,-, Hongo, Bunkyo-ku, Tokyo ,-, Japan备注：Accepted to IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2023

【2】 Undecidability Results and Their Relevance in Modern Music Making标题：现代音乐创作中的不可判断性结果及其相关性链接：https://arxiv.org/abs/2309.05595

作者：Halley Young

【3】 LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech标题：LeBenchmark 2.0：一个标准化、可复制和增强的法语语音自我监督表示框架链接：https://arxiv.org/abs/2309.05472

作者：Titouan Parcollet,Ha Nguyen,Solene Evain,Marcely Zanon Boito,Adrien Pupier,Salima Mdhaffar,Hang Le,Sina Alisamir,Natalia Tomashenko,Marco Dinarelli,Shucong Zhang,Alexandre Allauzen,Maximin Coavoux,Yannick Esteve,Mickael Rouvier,Jerome Goulian,Benjamin Lecouteux,Francois Portet,Solange Rossato,Fabien Ringeval,Didier Schwab,Laurent Besacier机构：Samsung AI Center Cambridge,, Station Road, Cambridge, CB,JH, United Kingdom, Department of Computer Science and Technology, University of Cambridge, JJ Thomson Av., Cambridge, CB,FD, United Kingdom备注：Under submission at Computer Science and Language. Preprint allowed

【4】 SlideSpeech: A Large-Scale Slide-Enriched Audio-Visual Corpus标题：SlideSpeech：一个大规模的幻灯片视听语料库链接：https://arxiv.org/abs/2309.05396

作者：Haoxu Wang,Fan Yu,Xian Shi,Yuezhang Wang,Shiliang Zhang机构：School of Computer Science, Wuhan University, Wuhan, China, Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China, Speech Lab of DAMO Academy, Alibaba Group, China

【5】 EDAC: Efficient Deployment of Audio Classification Models For COVID-19 Detection标题：EDAC：高效部署用于新冠肺炎检测的音频分类模型链接：https://arxiv.org/abs/2309.05357

作者：Andrej Jovanović,Mario Mihaly,Lennon Donaldson机构：University of Edinburgh, United Kingdom

【6】 Addressing Feature Imbalance in Sound Source Separation标题：解决声源分离中的特征不平衡问题链接：https://arxiv.org/abs/2309.05287

作者：Jaechang Kim,Jeongyeon Hwang,Soheun Yi,Jaewoong Cho,Jungseul Ok机构：POSTECH,KRAFTON

【7】 Multimodal Fish Feeding Intensity Assessment in Aquaculture标题：水产养殖中的多式联运鱼投喂强度评估链接：https://arxiv.org/abs/2309.05058

作者：Meng Cui,Xubo Liu,Haohe Liu,Zhuangzhuang Du,Tao Chen,Guoping Lian,Daoliang Li,Wenwu Wang机构：University of Surrey

【8】 Efficient Emotional Adaptation for Audio-Driven Talking-Head Generation标题：用于音频驱动对话头生成的高效情感适应链接：https://arxiv.org/abs/2309.04946

作者：Yuan Gan,Zongxin Yang,Xihang Yue,Lingyun Sun,Yi Yang机构：ReLER, CCAI, Zhejiang University, China, College of Computer Science and Technology, Zhejiang University, China备注：Accepted to ICCV 2023. Project page: this https URL

【9】 Exploring Music Genre Classification: Algorithm Analysis and Deployment Architecture标题：探索音乐流派分类：算法分析与部署架构链接：https://arxiv.org/abs/2309.04861

作者：Ayan Biswas,Supriya Dhabal,Palaniandavar Venkateswaran机构：Dept. of Electronics and Tele-communication Engineering, Jadavpur University, Kolkata – , INDIA, Electronics & Communication Engineering Department, Netaji Subhash Engineering College, Kolkata - , INDIA

【10】 Leveraging Large Language Models for Exploiting ASR Uncertainty标题：利用大型语言模型利用ASR不确定性链接：https://arxiv.org/abs/2309.04842

作者：Pranay Dighe,Yi Su,Shangshang Zheng,Yunshu Liu,Vineet Garg,Xiaochuan Niu,Ahmed Tewfik机构：Apple

【11】 AudRandAug: Random Image Augmentations for Audio Classification标题：AudRandAug：用于音频分类的随机图像增强链接：https://arxiv.org/abs/2309.04762

作者：Teerath Kumar,Muhammad Turab,Alessandra Mileo,Malika Bendechache,Takfarinas Saber机构：CRT-AI Centre, School of Computing, Dublin City University, Dublin, Ireland, Norwegian University of Science and Technology (NTNU), Gjovik, Norway, INSIGHT Research Centre, School of Computing, Dublin Ireland, Lero Research Centre, School of Computer Science备注：Paper has accepted at 25th Irish Machine Vision and Image Processing Conference

【12】 Mask-CTC-based Encoder Pre-training for Streaming End-to-End Speech Recognition标题：基于MASK-CTC的流端到端语音识别编码器预训练链接：https://arxiv.org/abs/2309.04654

作者：Huaibo Zhao,Yosuke Higuchi,Yusuke Kida,Tetsuji Ogawa,Tetsunori Kobayashi机构：⋆Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan, †LINE Corporation, Tokyo, Japan备注：Accepted to EUSIPCO 2023

【13】 Exploring Domain-Specific Enhancements for a Neural Foley Synthesizer标题：探索神经Foley合成器的特定领域增强链接：https://arxiv.org/abs/2309.04641

作者：Ashwin Pillay,Sage Betko,Ari Liloia,Hao Chen,Ankit Shah机构：Carnegie Mellon University, Pittsburgh, PA

【14】 The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion标题：声音的力量(TPOS)：具有稳定扩散的音频反应视频生成链接：https://arxiv.org/abs/2309.04509

作者：Yujin Jeong,Wonjeong Ryoo,Seunghyun Lee,Dabin Seo,Wonmin Byeon,Sangpil Kim,Jinkyu Kim机构：Department of Computer Science and Engineering, Korea University, Seoul , Korea, Department of Artificial Intelligence, Korea University, Seoul , Korea, NVIDIA Research, Santa Clara , USA, Prompt, “A photo of beautiful beach, with blue sky”, Frame备注：ICCV2023

【15】 COVID-19 Detection System: A Comparative Analysis of System Performance Based on Acoustic Features of Cough Audio Signals标题：新冠肺炎检测系统：基于咳嗽音频信号声学特征的系统性能比较分析链接：https://arxiv.org/abs/2309.04505

作者：Asmaa Shati,Ghulam Mubashar Hassan,Amitava Datta机构：Department of Computer Science and Software Engineering, University of Western Australia, Corresponding author备注：8 pages, 3 figures

【16】 Diffusion-Based Co-Speech Gesture Generation Using Joint Text and Audio Representation标题：基于扩散的文本和音频联合表示的协同语音手势生成链接：https://arxiv.org/abs/2309.05455

作者：Anna Deichler,Shivam Mehta,Simon Alexanderson,Jonas Beskow机构：KTH Royal Institute of Technology, Stockholm, Sweden

【17】 Multi-Modal Automatic Prosody Annotation with Contrastive Pretraining of SSWP标题：基于SSWP对比预训练的多模式自动韵律标注链接：https://arxiv.org/abs/2309.05423

作者：Jinzuomu Zhong,Yang Li,Hui Huang,Jie Liu,Zhiba Su,Jing Guo,Benlai Tang,Fengjie Zhu机构：School of Philosophy, Psychology & Language Sciences, University of Edinburgh, UK, Department of AI Technology, Transsion, China备注：Submitted to ICASSP 2024

【18】 Towards generalisable and calibrated synthetic speech detection with self-supervised representations标题：基于自监督表示的可泛化校正合成语音检测链接：https://arxiv.org/abs/2309.05384

作者：Dan Oneata,Adriana Stan,Octavian Pascu,Elisabeta Oneata,Horia Cucu机构：University “Politehnica” Bucharest, Romania, Technical University of Cluj-Napoca, Romania, Bitdefender, Romania备注：Submitted to ICASSP 2024

【19】 Enhancing Speaker Diarization with Large Language Models: A Contextual Beam Search Approach标题：利用大语言模型增强说话人二元化：语境波束搜索法链接：https://arxiv.org/abs/2309.05248

作者：Tae Jin Park,Kunal Dhawan,Nithin Koluguri,Jagadeesh Balam机构：NVIDIA, Santa Clara, USA备注：4 pages 1 reference page, ICASSP format

【20】 Gray Jedi MVDR Post-filtering标题：灰色绝地MVDR后滤波链接：https://arxiv.org/abs/2309.05057

作者：François Grondin,Caleb Rascón机构：Caleb Rasc´on 2 1Universit´e de Sherbrooke, 2Universidad Nacional Aut´onoma de M´exico备注：\c{opyright} 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

【21】 VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching标题：VoiceFlow：采用整流匹配的高效文本到语音转换链接：https://arxiv.org/abs/2309.05027

作者：Yiwei Guo,Chenpeng Du,Ziyang Ma,Xie Chen,Kai Yu机构：MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China备注：4 figure, 5 pages, submitted to ICASSP 2024

【22】 Generalized Minimum Error with Fiducial Points Criterion for Robust Learning标题：基于基准点准则的广义最小误差稳健学习链接：https://arxiv.org/abs/2309.04670

作者：Haiquan Zhao,Yuan Gao,Yingying Zhu机构：备注：12 pages, 9 figures

【23】 Leveraging Pretrained Image-text Models for Improving Audio-Visual Learning标题：利用预先训练的图文模型改进视听学习链接：https://arxiv.org/abs/2309.04628

作者：Saurabhchand Bhati,Jesús Villalba,Laureano Moro-Velazquez,Thomas Thebaud,Najim Dehak机构：†Center for Language and Speech Processing, Johns Hopkins University, USA, ‡Human Language Technology Center of Excellence, Johns Hopkins University, USA

【24】 End-to-End Speech Recognition and Disfluency Removal with Acoustic Language Model Pretraining标题：使用声学语言模型预训练的端到端语音识别和不流利消除链接：https://arxiv.org/abs/2309.04516

作者：Saksham Bassi,Giulio Duregon,Siddhartha Jalagam,David Roth机构：sb, gjd, scj, dsr

eess.AS音频处理

【1】 Diffusion-Based Co-Speech Gesture Generation Using Joint Text and Audio Representation标题：基于扩散的文本和音频联合表示的协同语音手势生成链接：https://arxiv.org/abs/2309.05455

作者：Anna Deichler,Shivam Mehta,Simon Alexanderson,Jonas Beskow机构：KTH Royal Institute of Technology, Stockholm, Sweden

【2】 Multi-Modal Automatic Prosody Annotation with Contrastive Pretraining of SSWP标题：基于SSWP对比预训练的多模式自动韵律标注链接：https://arxiv.org/abs/2309.05423

【3】 Towards generalisable and calibrated synthetic speech detection with self-supervised representations标题：基于自监督表示的可泛化校正合成语音检测链接：https://arxiv.org/abs/2309.05384

【4】 Enhancing Speaker Diarization with Large Language Models: A Contextual Beam Search Approach标题：利用大语言模型增强说话人二元化：语境波束搜索法链接：https://arxiv.org/abs/2309.05248

作者：Tae Jin Park,Kunal Dhawan,Nithin Koluguri,Jagadeesh Balam机构：NVIDIA, Santa Clara, USA备注：4 pages 1 reference page, ICASSP format

【5】 Gray Jedi MVDR Post-filtering标题：灰色绝地MVDR后滤波链接：https://arxiv.org/abs/2309.05057

【6】 VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching标题：VoiceFlow：采用整流匹配的高效文本到语音转换链接：https://arxiv.org/abs/2309.05027

【7】 Generalized Minimum Error with Fiducial Points Criterion for Robust Learning标题：基于基准点准则的广义最小误差稳健学习链接：https://arxiv.org/abs/2309.04670

作者：Haiquan Zhao,Yuan Gao,Yingying Zhu机构：备注：12 pages, 9 figures

【8】 Leveraging Pretrained Image-text Models for Improving Audio-Visual Learning标题：利用预先训练的图文模型改进视听学习链接：https://arxiv.org/abs/2309.04628

【9】 End-to-End Speech Recognition and Disfluency Removal with Acoustic Language Model Pretraining标题：使用声学语言模型预训练的端到端语音识别和不流利消除链接：https://arxiv.org/abs/2309.04516

作者：Saksham Bassi,Giulio Duregon,Siddhartha Jalagam,David Roth机构：sb, gjd, scj, dsr

【10】 Kernel Interpolation of Incident Sound Field in Region Including Scattering Objects标题：含散射体区域入射声场的核内插链接：https://arxiv.org/abs/2309.05634

【11】 Undecidability Results and Their Relevance in Modern Music Making标题：现代音乐创作中的不可判断性结果及其相关性链接：https://arxiv.org/abs/2309.05595

作者：Halley Young

【12】 LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech标题：LeBenchmark 2.0：一个标准化、可复制和增强的法语语音自我监督表示框架链接：https://arxiv.org/abs/2309.05472

【13】 SlideSpeech: A Large-Scale Slide-Enriched Audio-Visual Corpus标题：SlideSpeech：一个大规模的幻灯片视听语料库链接：https://arxiv.org/abs/2309.05396

【14】 EDAC: Efficient Deployment of Audio Classification Models For COVID-19 Detection标题：EDAC：高效部署用于新冠肺炎检测的音频分类模型链接：https://arxiv.org/abs/2309.05357

作者：Andrej Jovanović,Mario Mihaly,Lennon Donaldson机构：University of Edinburgh, United Kingdom

【15】 Addressing Feature Imbalance in Sound Source Separation标题：解决声源分离中的特征不平衡问题链接：https://arxiv.org/abs/2309.05287

作者：Jaechang Kim,Jeongyeon Hwang,Soheun Yi,Jaewoong Cho,Jungseul Ok机构：POSTECH,KRAFTON

【16】 Multimodal Fish Feeding Intensity Assessment in Aquaculture标题：水产养殖中的多式联运鱼投喂强度评估链接：https://arxiv.org/abs/2309.05058

作者：Meng Cui,Xubo Liu,Haohe Liu,Zhuangzhuang Du,Tao Chen,Guoping Lian,Daoliang Li,Wenwu Wang机构：University of Surrey

【17】 Efficient Emotional Adaptation for Audio-Driven Talking-Head Generation标题：用于音频驱动对话头生成的高效情感适应链接：https://arxiv.org/abs/2309.04946

【18】 Exploring Music Genre Classification: Algorithm Analysis and Deployment Architecture标题：探索音乐流派分类：算法分析与部署架构链接：https://arxiv.org/abs/2309.04861

【19】 Leveraging Large Language Models for Exploiting ASR Uncertainty标题：利用大型语言模型利用ASR不确定性链接：https://arxiv.org/abs/2309.04842

作者：Pranay Dighe,Yi Su,Shangshang Zheng,Yunshu Liu,Vineet Garg,Xiaochuan Niu,Ahmed Tewfik机构：Apple

【20】 AudRandAug: Random Image Augmentations for Audio Classification标题：AudRandAug：用于音频分类的随机图像增强链接：https://arxiv.org/abs/2309.04762

【21】 Mask-CTC-based Encoder Pre-training for Streaming End-to-End Speech Recognition标题：基于MASK-CTC的流端到端语音识别编码器预训练链接：https://arxiv.org/abs/2309.04654

【22】 Exploring Domain-Specific Enhancements for a Neural Foley Synthesizer标题：探索神经Foley合成器的特定领域增强链接：https://arxiv.org/abs/2309.04641

作者：Ashwin Pillay,Sage Betko,Ari Liloia,Hao Chen,Ankit Shah机构：Carnegie Mellon University, Pittsburgh, PA

【23】 The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion标题：声音的力量(TPOS)：具有稳定扩散的音频反应视频生成链接：https://arxiv.org/abs/2309.04509

【24】 COVID-19 Detection System: A Comparative Analysis of System Performance Based on Acoustic Features of Cough Audio Signals标题：新冠肺炎检测系统：基于咳嗽音频信号声学特征的系统性能比较分析链接：https://arxiv.org/abs/2309.04505

机器翻译，仅供参考

语音/音频处理学术速递[9.12]

评论 0