语音/音频处理学术速递[6.21]

今日论文合集：cs.SD语音34篇，eess.AS音频处理45篇。

cs.SD语音

【1】 Sound reconstruction from human brain activity via a generative model with brain-like auditory features标题：通过具有类脑听觉特征的生成模型从人脑活动中重建声音链接：https://arxiv.org/abs/2306.11629

作者：Jong-Yun Park,Mitsuaki Tsukamoto,Misato Tanaka,Yukiyasu Kamitani机构：�, Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Kyoto, Japan, Department of Neuroinformatics, ATR Computational Neuroscience Laboratories, Kyoto, Japan

【2】 Align, Adapt and Inject: Sound-guided Unified Image Generation标题：调整、调整和注入：声音制导的统一图像生成链接：https://arxiv.org/abs/2306.11504

作者：Yue Yang,Kaipeng Zhang,Yuying Ge,Wenqi Shao,Zeyue Xue,Yu Qiao,Ping Luo机构：Shanghai Jiao Tong University, Shanghai AI Laboratory, The University of Hong Kong备注：Tech Report

【3】 Pipeline for recording datasets and running neural networks on the Bela embedded hardware platform标题：在Bela嵌入式硬件平台上记录数据集和运行神经网络的流水线链接：https://arxiv.org/abs/2306.11389

作者：Teresa Pelinski,Rodrigo Diaz,Adán L. Benito Temprano,Andrew McPherson机构：∗, Centre for Digital Music, Queen Mary University of, Dyson School of Design, Engineering, Imperial College London, UK

【4】 Multi-pass Training and Cross-information Fusion for Low-resource End-to-end Accented Speech Recognition标题：低资源端到端重音语音识别的多通道训练和交叉信息融合链接：https://arxiv.org/abs/2306.11309

作者：Xuefei Wang,Yanhua Long,Yijie Li,Haoran Wei机构：Key Innovation Group of Digital Humanities Resource and Research, Shanghai Normal University, Shanghai, China, Unisound AI Technology Co., Ltd., Beijing, China, Department of ECE, University of Texas at Dallas, Richardson, TX , USA

【5】 Phase Repair for Time-Domain Convolutional Neural Networks in Music Super-Resolution标题：MUSIC超分辨率时域卷积神经网络的相位修复链接：https://arxiv.org/abs/2306.11282

作者：Yenan Zhang,Guilly Kolkman,Hiroshi Watanabe机构：∗ Graduate School of Fundamental Science and Engineering, Waseda University, Tokyo, Japan, University of Amsterdam, Amsterdam, Netherlands, ‡ Graduate School of Fundamental Science and Engineering, Waseda University, Tokyo, Japan

【6】 Frequency & Channel Attention for computationally efficient sound event detection标题：用于计算高效的声音事件检测的频率和通道注意链接：https://arxiv.org/abs/2306.11277

作者：Hyeonuk Nam,Seong-Hu Kim,Deokki Min,Yong-Hwa Park机构：Korea Advanced Institute of Science and Technology, South Korea备注：Submitted to DCASE 2023 workshop

【7】 Vocal Timbre Effects with Differentiable Digital Signal Processing标题：可差分数字信号处理中的音色效果链接：https://arxiv.org/abs/2306.10886

作者：David Südholt,Cumhur Erkut机构：Centre for Digital Music, Queen Mary University of London, London, UK, Multisensory Experience Lab, Aalborg University Copenhagen, Copenhagen, Denmark备注：Accepted for publication in Proc DAFx 2023, Copenhagen, Denmark. Sound Examples: this https URL Code: this https URL

【8】 Female mosquito detection by means of AI techniques inside release containers in the context of a Sterile Insect Technique program标题：在不育昆虫技术项目的背景下，在释放容器内通过人工智能技术检测雌性蚊子链接：https://arxiv.org/abs/2306.10843

作者：Javier Naranjo-Alcazar,Jordi Grau-Haro,David Almenar,Pedro Zuccarello机构：Instituto Tecnol´ogico de Inform´atica (ITI), Valencia, Spain, Empresa de Transformaci´on Agraria S.A., S.M.E., M.P. (TRAGSA), Paterna (Valencia), Spain备注：Under review at DCASE 2023 Workshop

【9】 Comparison of L2 Korean pronunciation error patterns from five L1 backgrounds by using automatic phonetic transcription标题：利用自动音标技术比较五种母语背景下的二语发音错误模式链接：https://arxiv.org/abs/2306.10821

作者：Eun Jung Yeo,Hyungshin Ryu,Jooyoung Lee,Sunhee Kim,Minhwa Chung机构：Seoul National University备注：5 pages, 2 figures, accepted to ICPhS 2023

【10】 Multitrack Music Transcription with a Time-Frequency Perceiver标题：具有时频感知器的多声道音乐转录链接：https://arxiv.org/abs/2306.10785

作者：Wei-Tsung Lu,Ju-Chiang Wang,Yun-Ning Hung机构：SAMI, ByteDance, Mountain View, CA, USA备注：ICASSP 2023

【11】 Learning an Interpretable End-to-End Network for Real-Time Acoustic Beamforming标题：用于实时声学波束形成的可解释端到端网络的学习链接：https://arxiv.org/abs/2306.10772

作者：Hao Liang,Guanxing Zhou,Xiaotong Tu,Andreas Jakobsson,Xinghao Ding,Yue Huang备注：12 pages, 9 figures

【12】 Algorithms of Sampling-Frequency-Independent Layers for Non-integer Strides标题：非整数步长的采样频率无关层算法链接：https://arxiv.org/abs/2306.10718

作者：Kanami Imamura,Tomohiko Nakamura,Norihiro Takamune,Kohei Yatabe,Hiroshi Saruwatari机构：†Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan, ‡Department of Electrical Engineering and Computer Science, Tokyo University of Agriculture and Technology, Tokyo, Japan备注：5 pages, 3 figures, accepted for European Signal Processing Conference 2023 (EUSIPCO 2023)

【13】 Visually-Guided Sound Source Separation with Audio-Visual Predictive Coding标题：基于视听预测编码的视觉引导声源分离链接：https://arxiv.org/abs/2306.10684

作者：Zengjie Song,Zhaoxiang Zhang机构：National Laboratory of Pattern Recognition, Institute ofAutomation备注：Accepted to IEEE Transactions on Neural Networks and Learning Systems (T-NNLS)

【14】 STHG: Spatial-Temporal Heterogeneous Graph Learning for Advanced Audio-Visual Diarization标题：STHG：用于高级视听二值化的时空异构图学习链接：https://arxiv.org/abs/2306.10608

作者：Kyle Min机构：Intel Labs备注：Validation report for the Ego4D challenge at CVPR 2023

【15】 MARBLE: Music Audio Representation Benchmark for Universal Evaluation标题：大理石：音乐音频表现的普遍评价基准链接：https://arxiv.org/abs/2306.10548

作者：Ruibin Yuan,Yinghao Ma,Yizhi Li,Ge Zhang,Xingran Chen,Hanzhi Yin,Le Zhuo,Yiqi Liu,Jiawen Huang,Zeyue Tian,Binyue Deng,Ningzhi Wang,Wenhu Chen,Gus Xia,Wei Xue,Si Liu,Shi Wang,Ruibo Liu,Yike Guo,Jie Fu机构：Chenghua Lin,† Emmanouil Benetos, Anton Ragni, Norbert Gyenge, Roger Dannenberg, Multimodal Art Projection Research Community, Beijing Academy of Artificial Intelligence, Carnegie Mellon University, Queen Mary University of London, University of Sheffield

【16】 MOSPC: MOS Prediction Based on Pairwise Comparison标题：MOSPC：基于两两比较的MOS预测链接：https://arxiv.org/abs/2306.10493

作者：Kexin Wang,Yunlong Zhao,Qianqian Dong,Tom Ko,Mingxuan Wang机构：ByteDance, China

【17】 Text-Driven Foley Sound Generation With Latent Diffusion Model标题：基于潜在扩散模型的文本驱动Foley声音生成链接：https://arxiv.org/abs/2306.10359

作者：Yi Yuan,Haohe Liu,Xubo Liu,Xiyuan Kang,Peipei Wu,Mark D. Plumbley,Wenwu Wang机构：Centre for Vision Speech and Signal Processing, University of Surrey, United Kingdom备注：Submit to DCASE-workshop 2023. arXiv admin note: text overlap with arXiv:2305.15905

【18】 Neural Fast Full-Rank Spatial Covariance Analysis for Blind Source Separation标题：用于盲源分离的神经网络快速满秩空间协方差分析链接：https://arxiv.org/abs/2306.10240

作者：Yoshiaki Bando,Yoshiki Masuyama,Aditya Arie Nugraha,Kazuyoshi Yoshii机构：∗National Institute of Advanced Industrial Science and Technology, Japan, †Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan, ‡Department of Computer Science, Tokyo Metropolitan University, Japan备注：5 pages, 2 figures, accepted to EUSIPCO 2023

【19】 Musico-acoustic Depictions of Laminar and Turbulent Flows in Ligeti Piano Etude No. 9 and a Novel Method of Analysis标题：Ligeti第九钢琴练习曲层流和湍流的声学描述及新的分析方法链接：https://arxiv.org/abs/2306.10093

作者：Noah Chuipka

【20】 Acoustic Identification of Ae. aegypti Mosquitoes using Smartphone Apps and Residual Convolutional Neural Networks标题：Ae.的声学鉴定用智能手机应用和残差卷积神经网络控制埃及伊蚊链接：https://arxiv.org/abs/2306.10091

作者：Kayuã Oleques Paim,Ricardo Rohweder,Mariana Recamonde-Mendoza,Rodrigo Brandão Mansilha1,Weverton Cordeiro机构：Instituto de Informática, Universidade Federal do Rio Grande do Sul (UFRGS), Programa de Pós-Graduação em Engenharia de Software (PPGES), Universidade Federal do Pampa - Campus Alegrete (UNIPAMPA), Programa de Pós-Graduação em Genética e Biologia Molecular

【21】 Implicit neural representation with physics-informed neural networks for the reconstruction of the early part of room impulse responses标题：用物理信息神经网络隐式神经表示重建房间脉冲响应的早期部分链接：https://arxiv.org/abs/2306.11509

作者：Mirco Pezzoli,Fabio Antonacci,Augusto Sarti机构：Dipartimento di Elettronica, Informatica e Bioingegneria, Politecnico di Milano, Italy备注：Accepted for publication at Forum Acusticum 2023

【22】 eCat: An End-to-End Model for Multi-Speaker TTS & Many-to-Many Fine-Grained Prosody Transfer标题：ECAT：一种端到端的多说话人TTS模型&多对多细粒度韵律传输链接：https://arxiv.org/abs/2306.11327

作者：Ammar Abbas,Sri Karlapati,Bastian Schnell,Penny Karanasou,Marcel Granero Moya,Amith Nagaraj,Ayman Boustati,Nicole Peinelt,Alexis Moinet,Thomas Drugman机构：Alexa AI, Amazon备注：Accepted to be published in the Proceedings of InterSpeech 2023

【23】 Rehearsal-Free Online Continual Learning for Automatic Speech Recognition标题：用于自动语音识别的免排练在线连续学习链接：https://arxiv.org/abs/2306.10860

作者：Steven Vander Eeckt,Hugo Van hamme机构：KU Leuven, Department Electrical Engineering ESAT-PSI, Leuven, Belgium备注：Accepted at INTERSPEECH 2023. 5 pages

【24】 MIR-GAN: Refining Frame-Level Modality-Invariant Representations with Adversarial Network for Audio-Visual Speech Recognition标题：MIR-GAN：改进基于对抗性网络的帧级通道不变表示用于视听语音识别链接：https://arxiv.org/abs/2306.10567

作者：Yuchen Hu,Chen Chen,Ruizhe Li,Heqing Zou,Eng Siong Chng机构：Nanyang Technological University, Singapore, University of Aberdeen, UK备注：14 pages, 5 figures, Accepted by ACL 2023

【25】 Hearing Lips in Noise: Universal Viseme-Phoneme Mapping and Transfer for Robust Audio-Visual Speech Recognition标题：噪声中的听觉嘴唇：用于健壮视听语音识别的通用视素-音素映射和转换链接：https://arxiv.org/abs/2306.10563

作者：Yuchen Hu,Ruizhe Li,Chen Chen,Chengwei Qin,Qiushi Zhu,Eng Siong Chng机构：Nanyang Technological University, Singapore, University of Aberdeen, UK, University of Science and Technology of China, China备注：19 pages, 9 figures, Accepted by ACL 2023

【26】 SURT 2.0: Advances in Transducer-based Multi-talker Speech Recognition标题：SURT 2.0：基于传感器的多人语音识别研究进展链接：https://arxiv.org/abs/2306.10559

作者：Desh Raj,Daniel Povey,Sanjeev Khudanpur备注：13 pages, 6 figures. Project webpage: this https URL

【27】 LM-VC: Zero-shot Voice Conversion via Speech Generation based on Language Models标题：LM-VC：基于语言模型的语音生成零发声转换链接：https://arxiv.org/abs/2306.10521

作者：Zhichao Wang,Yuanzhe Chen,Lei Xie,Qiao Tian,Yuping Wang机构：School of Com-puter Science, Northwestern Polytechnical University

【28】 Channel Spatial Based Few-Shot Bird Sounds Event Detection标题：基于通道空间的少发鸟鸣事件检测链接：https://arxiv.org/abs/2306.10499

作者：Lingwen Liu,Yuxuan Feng,Haitao Fu,Yajie Yang,Xin Pan,Chenlei Jin机构：∗ Jilin Agricultural University, Changchun, China备注：2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference

【29】 Autophonic Loudness of Singers in Simulated Room Acoustic Environments标题：模拟室内声学环境中歌手的自声响度链接：https://arxiv.org/abs/2306.10271

作者：Manuj Yadav,Densil Cabrera机构：The University of Sydney

【30】 Two simultaneous talkers distract more than one in simulated multi-talker environments, regardless of overall sound levels typical of open-plan offices标题：在模拟的多人讲话环境中，两个同时讲话的人会分散多个人的注意力，而不考虑开放式办公室的典型总体音量链接：https://arxiv.org/abs/2306.10269

作者：Manuj Yadav,Densil Cabrera机构：Sydney School of Architecture, Design and Planning, The University of Sydney, Sydney, NSW , Australia, a r t i c l e, i n f o, Article history:

【31】 Reliability and repeatability of ISO 3382-3 metrics based on repeated acoustic measurements in open-plan offices标题：基于开放式办公室重复声学测量的ISO 3382-3度量标准的可靠性和重复性链接：https://arxiv.org/abs/2306.10268

作者：Manuj Yadav,Densil Cabrera,James Love,Jungsoo Kim,Jonothan Holmes,Hugo Caldwell,Richard de Dear机构：Sydney School of Architecture, Design and Planning, The University of Sydney, Sydney, NSW , Australia, a r t i c l e, i n f o, Article history:, a b s t r a c t

【32】 Low-Resource Text-to-Speech Using Specific Data and Noise Augmentation标题：使用特定数据和噪声增强的低资源文本到语音转换链接：https://arxiv.org/abs/2306.10152

作者：Kishor Kayyar Lakshminarayana,Christian Dittmar,Nicola Pia,Emanuël Habets机构：∗Fraunhofer Institute for Integrated Circuits (IIS), Erlangen, Germany, †International Audio Laboratories Erlangen, Germany备注：Accepted for publication at EUSIPCO-2023, Helsinki

【33】 Improving Audio Caption Fluency with Automatic Error Correction标题：利用自动纠错功能提高音频字幕流畅度链接：https://arxiv.org/abs/2306.10090

作者：Hanxue Zhang,Zeyu Xie,Xuenan Xu,Mengyue Wu,Kai Yu机构：MoE Key Lab of Artificial Intelligence, X-LANCE Lab, Department of Computer Science and Engineering, AI Institute, Shanghai Jiao Tong University, Shanghai, China备注：Accepted by NCMMSC 2022

【34】 Taming Diffusion Models for Music-driven Conducting Motion Generation标题：音乐驱动的指挥动作生成的驯化扩散模型链接：https://arxiv.org/abs/2306.10065

作者：Zhuoran Zhao,Jinbin Bai,Delong Chen,Debang Wang,Yubo Pan机构：Dept. of Computer Science, School of Computing, National University of Singapore, Xiaobing.AI备注：Accepted by AAAI 2023 Summer Symposium

eess.AS音频处理

【1】 Expressive Machine Dubbing Through Phrase-level Cross-lingual Prosody Transfer标题：基于短语级跨语言韵律转移的表现力机器配音链接：https://arxiv.org/abs/2306.11662

作者：Jakub Swiatkowski,Duo Wang,Mikolaj Babianski,Giuseppe Coccia,Patrick Lumban Tobing,Ravichander Vipperla,Viacheslav Klimkov,Vincent Pollet机构：Amazon Science备注：Submitted to INTERSPEECH

【2】 Cross-lingual Prosody Transfer for Expressive Machine Dubbing标题：表现力机器配音中的跨语言韵律迁移链接：https://arxiv.org/abs/2306.11658

作者：Jakub Swiatkowski,Duo Wang,Mikolaj Babianski,Patrick Lumban Tobing,Ravichander Vipperla,Vincent Pollet机构：Amazon Science备注：Submitted to INTERSPEECH

【3】 Implicit neural representation with physics-informed neural networks for the reconstruction of the early part of room impulse responses标题：用物理信息神经网络隐式神经表示重建房间脉冲响应的早期部分链接：https://arxiv.org/abs/2306.11509

【4】 Auditory Neural Response Inspired Sound Event Detection Based on Spectro-temporal Receptive Field标题：基于谱-时感受场的听神经反应诱发声事件检测链接：https://arxiv.org/abs/2306.11427

作者：Deokki Min,Hyeonuk Nam,Yong-Hwa Park机构：Korea Advanced Institute of Science and Technology, South Korea备注：Submitted to DCASE 2023 Workshop

【5】 A Computation-efficient Online Secondary Path Modeling Technique for Modified FXLMS Algorithm标题：一种计算高效的改进FXLMS算法在线次级通道建模技术链接：https://arxiv.org/abs/2306.11408

作者：Junwei Ji,Dongyuan Shi,Woon-Seng Gan,Xiaoyi Shen,Zhengding Luo机构：School of Electrical and Electronic Engineering, Nanyang Technological University, Nanyang Avenue, Singapore

【6】 Visually grounded few-shot word learning in low-resource settings标题：低资源环境下基于视觉的Few-Shot单词学习链接：https://arxiv.org/abs/2306.11371

作者：Leanne Nortje,Dan Oneata,Herman Kamper备注：Submitted to TALSP. arXiv admin note: substantial text overlap with arXiv:2305.15937

【7】 eCat: An End-to-End Model for Multi-Speaker TTS & Many-to-Many Fine-Grained Prosody Transfer标题：ECAT：一种端到端的多说话人TTS模型&多对多细粒度韵律传输链接：https://arxiv.org/abs/2306.11327

【8】 Rehearsal-Free Online Continual Learning for Automatic Speech Recognition标题：用于自动语音识别的免排练在线连续学习链接：https://arxiv.org/abs/2306.10860

作者：Steven Vander Eeckt,Hugo Van hamme机构：KU Leuven, Department Electrical Engineering ESAT-PSI, Leuven, Belgium备注：Accepted at INTERSPEECH 2023. 5 pages

【9】 DuTa-VC: A Duration-aware Typical-to-atypical Voice Conversion Approach with Diffusion Probabilistic Model标题：DUTA-VC：一种基于扩散概率模型的时长感知的典型到非典型语音转换方法链接：https://arxiv.org/abs/2306.10588

作者：Helin Wang,Thomas Thebaud,Jesus Villalba,Myra Sydnor,Becky Lammers,Najim Dehak,Laureano Moro-Velazquez机构：Center for Language and Speech Processing, Johns Hopkins University, USA, Human Language Technology Center of Excellence, Johns Hopkins University, USA, Department of Physical Medicine and Rehabilitation, Johns Hopkins University School of Medicine, USA

【10】 MIR-GAN: Refining Frame-Level Modality-Invariant Representations with Adversarial Network for Audio-Visual Speech Recognition标题：MIR-GAN：改进基于对抗性网络的帧级通道不变表示用于视听语音识别链接：https://arxiv.org/abs/2306.10567

作者：Yuchen Hu,Chen Chen,Ruizhe Li,Heqing Zou,Eng Siong Chng机构：Nanyang Technological University, Singapore, University of Aberdeen, UK备注：14 pages, 5 figures, Accepted by ACL 2023

【11】 Hearing Lips in Noise: Universal Viseme-Phoneme Mapping and Transfer for Robust Audio-Visual Speech Recognition标题：噪声中的听觉嘴唇：用于健壮视听语音识别的通用视素-音素映射和转换链接：https://arxiv.org/abs/2306.10563

【12】 SURT 2.0: Advances in Transducer-based Multi-talker Speech Recognition标题：SURT 2.0：基于传感器的多人语音识别研究进展链接：https://arxiv.org/abs/2306.10559

作者：Desh Raj,Daniel Povey,Sanjeev Khudanpur备注：13 pages, 6 figures. Project webpage: this https URL

【13】 LM-VC: Zero-shot Voice Conversion via Speech Generation based on Language Models标题：LM-VC：基于语言模型的语音生成零发声转换链接：https://arxiv.org/abs/2306.10521

作者：Zhichao Wang,Yuanzhe Chen,Lei Xie,Qiao Tian,Yuping Wang机构：School of Com-puter Science, Northwestern Polytechnical University

【14】 Channel Spatial Based Few-Shot Bird Sounds Event Detection标题：基于通道空间的少发鸟鸣事件检测链接：https://arxiv.org/abs/2306.10499

【15】 Autophonic Loudness of Singers in Simulated Room Acoustic Environments标题：模拟室内声学环境中歌手的自声响度链接：https://arxiv.org/abs/2306.10271

作者：Manuj Yadav,Densil Cabrera机构：The University of Sydney

【16】 Two simultaneous talkers distract more than one in simulated multi-talker environments, regardless of overall sound levels typical of open-plan offices标题：在模拟的多人讲话环境中，两个同时讲话的人会分散多个人的注意力，而不考虑开放式办公室的典型总体音量链接：https://arxiv.org/abs/2306.10269

作者：Manuj Yadav,Densil Cabrera机构：Sydney School of Architecture, Design and Planning, The University of Sydney, Sydney, NSW , Australia, a r t i c l e, i n f o, Article history:

【17】 Reliability and repeatability of ISO 3382-3 metrics based on repeated acoustic measurements in open-plan offices标题：基于开放式办公室重复声学测量的ISO 3382-3度量标准的可靠性和重复性链接：https://arxiv.org/abs/2306.10268

【18】 Low-Resource Text-to-Speech Using Specific Data and Noise Augmentation标题：使用特定数据和噪声增强的低资源文本到语音转换链接：https://arxiv.org/abs/2306.10152

【19】 CML-TTS A Multilingual Dataset for Speech Synthesis in Low-Resource Languages标题：用于低资源语言语音合成的多语种数据集CML-TTS链接：https://arxiv.org/abs/2306.10097

作者：Frederico S. Oliveira,Edresson Casanova,Arnaldo Cândido Júnior,Anderson S. Soares,Arlindo R. Galvão Filho机构：Soares, and Arlindo R. Galv˜ao Filho, UFG, Goi´as - GO - Brazil备注：12 pages, 5 figures, Accepted at the 25th International Conference on Text, Speech and Dialogue (TSD 2022)

【20】 Improving Audio Caption Fluency with Automatic Error Correction标题：利用自动纠错功能提高音频字幕流畅度链接：https://arxiv.org/abs/2306.10090

【21】 Taming Diffusion Models for Music-driven Conducting Motion Generation标题：音乐驱动的指挥动作生成的驯化扩散模型链接：https://arxiv.org/abs/2306.10065

【22】 Recent Advances in Direct Speech-to-text Translation标题：直接语音到文本翻译的最新进展链接：https://arxiv.org/abs/2306.11646

作者：Chen Xu,Rong Ye,Qianqian Dong,Chengqi Zhao,Tom Ko,Mingxuan Wang,Tong Xiao,Jingbo Zhu机构：School of Computer Science and Engineering, Northeastern University, Shenyang, China, ByteDance AI Lab, NiuTrans Research, Shenyang, China备注：An expanded version of the paper accepted by IJCAI2023 survey track

【23】 Sound reconstruction from human brain activity via a generative model with brain-like auditory features标题：通过具有类脑听觉特征的生成模型从人脑活动中重建声音链接：https://arxiv.org/abs/2306.11629

【24】 Align, Adapt and Inject: Sound-guided Unified Image Generation标题：调整、调整和注入：声音制导的统一图像生成链接：https://arxiv.org/abs/2306.11504

作者：Yue Yang,Kaipeng Zhang,Yuying Ge,Wenqi Shao,Zeyue Xue,Yu Qiao,Ping Luo机构：Shanghai Jiao Tong University, Shanghai AI Laboratory, The University of Hong Kong备注：Tech Report

【25】 Timestamped Embedding-Matching Acoustic-to-Word CTC ASR标题：时间戳嵌入匹配声字CTC ASR链接：https://arxiv.org/abs/2306.11473

作者：Woojay Jeon

【26】 Pipeline for recording datasets and running neural networks on the Bela embedded hardware platform标题：在Bela嵌入式硬件平台上记录数据集和运行神经网络的流水线链接：https://arxiv.org/abs/2306.11389

【27】 Multi-pass Training and Cross-information Fusion for Low-resource End-to-end Accented Speech Recognition标题：低资源端到端重音语音识别的多通道训练和交叉信息融合链接：https://arxiv.org/abs/2306.11309

【28】 Phase Repair for Time-Domain Convolutional Neural Networks in Music Super-Resolution标题：MUSIC超分辨率时域卷积神经网络的相位修复链接：https://arxiv.org/abs/2306.11282

【29】 Frequency & Channel Attention for computationally efficient sound event detection标题：用于计算高效的声音事件检测的频率和通道注意链接：https://arxiv.org/abs/2306.11277

作者：Hyeonuk Nam,Seong-Hu Kim,Deokki Min,Yong-Hwa Park机构：Korea Advanced Institute of Science and Technology, South Korea备注：Submitted to DCASE 2023 workshop

【30】 Vocal Timbre Effects with Differentiable Digital Signal Processing标题：可差分数字信号处理中的音色效果链接：https://arxiv.org/abs/2306.10886

【31】 Female mosquito detection by means of AI techniques inside release containers in the context of a Sterile Insect Technique program标题：在不育昆虫技术项目的背景下，在释放容器内通过人工智能技术检测雌性蚊子链接：https://arxiv.org/abs/2306.10843

【32】 Comparison of L2 Korean pronunciation error patterns from five L1 backgrounds by using automatic phonetic transcription标题：利用自动音标技术比较五种母语背景下的二语发音错误模式链接：https://arxiv.org/abs/2306.10821

作者：Eun Jung Yeo,Hyungshin Ryu,Jooyoung Lee,Sunhee Kim,Minhwa Chung机构：Seoul National University备注：5 pages, 2 figures, accepted to ICPhS 2023

【33】 Multitrack Music Transcription with a Time-Frequency Perceiver标题：具有时频感知器的多声道音乐转录链接：https://arxiv.org/abs/2306.10785

作者：Wei-Tsung Lu,Ju-Chiang Wang,Yun-Ning Hung机构：SAMI, ByteDance, Mountain View, CA, USA备注：ICASSP 2023

【34】 Learning an Interpretable End-to-End Network for Real-Time Acoustic Beamforming标题：用于实时声学波束形成的可解释端到端网络的学习链接：https://arxiv.org/abs/2306.10772

作者：Hao Liang,Guanxing Zhou,Xiaotong Tu,Andreas Jakobsson,Xinghao Ding,Yue Huang备注：12 pages, 9 figures

【35】 Algorithms of Sampling-Frequency-Independent Layers for Non-integer Strides标题：非整数步长的采样频率无关层算法链接：https://arxiv.org/abs/2306.10718

【36】 Visually-Guided Sound Source Separation with Audio-Visual Predictive Coding标题：基于视听预测编码的视觉引导声源分离链接：https://arxiv.org/abs/2306.10684

作者：Zengjie Song,Zhaoxiang Zhang机构：National Laboratory of Pattern Recognition, Institute ofAutomation备注：Accepted to IEEE Transactions on Neural Networks and Learning Systems (T-NNLS)

【37】 STHG: Spatial-Temporal Heterogeneous Graph Learning for Advanced Audio-Visual Diarization标题：STHG：用于高级视听二值化的时空异构图学习链接：https://arxiv.org/abs/2306.10608

作者：Kyle Min机构：Intel Labs备注：Validation report for the Ego4D challenge at CVPR 2023

【38】 MARBLE: Music Audio Representation Benchmark for Universal Evaluation标题：大理石：音乐音频表现的普遍评价基准链接：https://arxiv.org/abs/2306.10548

【39】 MOSPC: MOS Prediction Based on Pairwise Comparison标题：MOSPC：基于两两比较的MOS预测链接：https://arxiv.org/abs/2306.10493

作者：Kexin Wang,Yunlong Zhao,Qianqian Dong,Tom Ko,Mingxuan Wang机构：ByteDance, China

【40】 Text-Driven Foley Sound Generation With Latent Diffusion Model标题：基于潜在扩散模型的文本驱动Foley声音生成链接：https://arxiv.org/abs/2306.10359

【41】 Neural Fast Full-Rank Spatial Covariance Analysis for Blind Source Separation标题：用于盲源分离的神经网络快速满秩空间协方差分析链接：https://arxiv.org/abs/2306.10240

【42】 Musico-acoustic Depictions of Laminar and Turbulent Flows in Ligeti Piano Etude No. 9 and a Novel Method of Analysis标题：Ligeti第九钢琴练习曲层流和湍流的声学描述及新的分析方法链接：https://arxiv.org/abs/2306.10093

作者：Noah Chuipka

【43】 Acoustic Identification of Ae. aegypti Mosquitoes using Smartphone Apps and Residual Convolutional Neural Networks标题：Ae.的声学鉴定用智能手机应用和残差卷积神经网络控制埃及伊蚊链接：https://arxiv.org/abs/2306.10091

【44】 EM-Network: Oracle Guided Self-distillation for Sequence Learning标题：EM-Network：Oracle引导的序列学习自升法链接：https://arxiv.org/abs/2306.10058

作者：Ji Won Yoon,Sunghwan Ahn,Hyeonseung Lee,Minchan Kim,Seok Min Kim,Nam Soo Kim机构：1Department of ECE and INMC, Seoul National University备注：ICML 2023

【45】 Investigating Reproducibility at Interspeech Conferences: A Longitudinal and Comparative Perspective标题：跨语种会议可再现性研究：纵向和比较视角链接：https://arxiv.org/abs/2306.10033

作者：Mohammad Arvan,A. Seza Doğruöz,Natalie Parde机构：University of Illinois Chicago, USA, Ghent University, Belgium

机器翻译，仅供参考

语音/音频处理学术速递[6.21]

评论 0