语音/音频处理学术速递[5.31]

今日论文合集：cs.SD语音23篇，eess.AS音频处理31篇。

cs.SD语音

【1】 Unsupervised Melody-to-Lyric Generation标题：无监督的旋律到歌词生成链接：https://arxiv.org/abs/2305.19228

作者：Yufei Tian,Anjali Narayan-Chen,Shereen Oraby,Alessandra Cervone,Gunnar Sigurdsson,Chenyang Tao,Wenbo Zhao,Tagyoung Chung,Jing Huang,Nanyun Peng机构： University of California, Los Angeles, Amazon Alexa AI备注：Accepted to ACL 23. arXiv admin note: substantial text overlap with arXiv:2305.07760

【2】 Adaptation of Tongue Ultrasound-Based Silent Speech Interfaces Using Spatial Transformer Networks标题：基于空间变换网络的舌超声无声语音接口自适应链接：https://arxiv.org/abs/2305.19130

作者：László Tóth,Amin Honarmandi Shandiz,Gábor Gosztolya,Csapó Tamás Gábor机构：Institute of Informatics, University of Szeged, Hungary, ELRN-SZTE Research Group on Artificial Intelligence, Szeged, Hungary, Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary备注：5 pages, 3 figures, 3 tables

【3】 Pseudo-Siamese Network based Timbre-reserved Black-box Adversarial Attack in Speaker Identification标题：说话人辨认中基于伪暹罗网络的保留音色黑盒对抗攻击链接：https://arxiv.org/abs/2305.19020

作者：Qing Wang,Jixun Yao,Ziqian Wang,Pengcheng Guo,Lei Xie机构：Northwestern Polytechnical University (NPU), Xi’an, China备注：5 pages

【4】 Language-independent speaker anonymization using orthogonal Householder neural network标题：基于正交Household神经网络的非语言无关说话人匿名链接：https://arxiv.org/abs/2305.18823

作者：Xiaoxiao Miao,Xin Wang,Erica Cooper,Junichi Yamagishi,Natalia Tomashenko

【5】 Understanding temporally weakly supervised training: A case study for keyword spotting标题：理解时间弱监督训练：关键词识别的案例研究链接：https://arxiv.org/abs/2305.18794

作者：Heinrich Dinkel,Weiji Zhuang,Zhiyong Yan,Yongqing Wang,Junbo Zhang,Yujun Wang机构：Xiaomi Corperation, Beijing, China

【6】 E-PANNs: Sound Recognition Using Efficient Pre-trained Audio Neural Networks标题：E-PANN：基于高效预训练音频神经网络的声音识别链接：https://arxiv.org/abs/2305.18665

作者：Arshdeep Singh,Haohe Liu,Mark D. Plumbley机构：Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK备注：Accepted in Internoise 2023 conference

【7】 Building Accurate Low Latency ASR for Streaming Voice Search标题：为流媒体语音搜索构建准确的低延迟ASR链接：https://arxiv.org/abs/2305.18596

作者：Abhinav Goyal,Nikesh Garera机构：Flipkart备注：Accepted at ACL 2023 Industry Track

【8】 Make-An-Audio 2: Temporal-Enhanced Text-to-Audio Generation标题：Make-an-Audio 2：时间增强的文本到音频生成链接：https://arxiv.org/abs/2305.18474

作者：Jiawei Huang,Yi Ren,Rongjie Huang,Dongchao Yang,Zhenhui Ye,Chen Zhang,Jinglin Liu,Xiang Yin,Zejun Ma,Zhou Zhao机构：Zhejiang University, ByteDance, Peking University

【9】 Semantic Segmentation with Bidirectional Language Models Improves Long-form ASR标题：基于双向语言模型的语义切分改进长形ASR链接：https://arxiv.org/abs/2305.18419

作者：W. Ronny Huang,Hao Zhang,Shankar Kumar,Shuo-yiin Chang,Tara N. Sainath机构：Google Research, USA备注：Interspeech 2023. First 3 authors contributed equally

【10】 Speech Intelligibility Assessment of Dysarthric Speech by using Goodness of Pronunciation with Uncertainty Quantification标题：用发音优度不确定度量化评价韵律障碍语音的清晰度链接：https://arxiv.org/abs/2305.18392

作者：Eun Jung Yeo,Kwanghee Choi,Sunhee Kim,Minhwa Chung机构：Seoul National University, Republic of Korea, Carnegie Mellon University, United States of America备注：Accepted to Interspeech 2023

【11】 An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization标题：一种基于近邻初始化的高效扩散模型隶属度推理攻击链接：https://arxiv.org/abs/2305.18355

作者：Fei Kong,Jinhao Duan,RuiPeng Ma,Hengtao Shen,Xiaofeng Zhu,Xiaoshuang Shi,Kaidi Xu机构：University of Electronic Science and Technology of China, Drexel University

【12】 Make-A-Voice: Unified Voice Synthesis With Discrete Representation标题：发声：离散表示的统一语音合成链接：https://arxiv.org/abs/2305.19269

作者：Rongjie Huang,Chunlei Zhang,Yongqi Wang,Dongchao Yang,Luping Liu,Zhenhui Ye,Ziyue Jiang,Chao Weng,Zhou Zhao,Dong Yu机构：Zhejiang University, Tencent AI Lab, Peking University

【13】 A Stutter Seldom Comes Alone -- Cross-Corpus Stuttering Detection as a Multi-label Problem标题：口吃很少单独出现--作为多标签问题的跨语料库口吃检测链接：https://arxiv.org/abs/2305.19255

作者：Sebastian P. Bayerl,Dominik Wagner,Ilja Baumann,Florian Hönig,Tobias Bocklet,Elmar Nöth,Korbinian Riedhammer机构： Technische Hochschule N¨urnberg Georg Simon Ohm, Germany, KST Institut GmbH,Intel Labs, Friedrich-Alexander-Universit¨at Erlangen-N¨urnberg, Germany备注：Accepted for presentation at Interspeech 2023. arXiv admin note: substantial text overlap with arXiv:2210.15982

【14】 Leveraging Semantic Information for Efficient Self-Supervised Emotion Recognition with Audio-Textual Distilled Models标题：利用语义信息利用音频文本提取模型进行高效自监督情感识别链接：https://arxiv.org/abs/2305.19184

作者：Danilo de Oliveira,Navin Raj Prabhu,Timo Gerkmann机构：Signal Processing (SP), Universit¨at Hamburg, Germany备注：Accepted at Interspeech 2023

【15】 Predicting Preferred Dialogue-to-Background Loudness Difference in Dialogue-Separated Audio标题：预测对话分离音频中的首选对话与背景响度差异链接：https://arxiv.org/abs/2305.19100

作者：Luca Resti,Martin Strauss,Matteo Torcoli,Emanuël Habets,Bernd Edler机构：∗Fraunhofer Institute for Integrated Circuits (IIS), Erlangen, Germany, †International Audio Laboratories Erlangen, Germany, th International Conference on Quality of Multimedia Experience (QoMEX)备注：4 pages, 2 figures, Paper accepted at the 15th International Conference on Quality of Multimedia Experience (QoMEX)

【16】 Prospective Validation of Motor-Based Intervention with Automated Mispronunciation Detection of Rhotics in Residual Speech Sound Disorders标题：运动干预与Rhotics发音错误自动检测在残留语音障碍中的前瞻性验证链接：https://arxiv.org/abs/2305.19090

作者：Nina R Benway,Jonathan L Preston机构：Communication Sciences and Disorders, Syracuse University, New York, USA, Haskins Laboratories, New Haven, Connecticut, USA备注：To appear in Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2023

【17】 Towards single integrated spoofing-aware speaker verification embeddings标题：面向单一集成欺骗感知说话人验证嵌入链接：https://arxiv.org/abs/2305.19051

作者：Sung Hwan Mun,Hye-jin Shim,Hemlata Tak,Xin Wang,Xuechen Liu,Md Sahidullah,Myeonghun Jeong,Min Hyun Han,Massimiliano Todisco,Kong Aik Lee,Junichi Yamagishi,Nicholas Evans,Tomi Kinnunen,Nam Soo Kim,Jee-weon Jung机构：Seoul National University, South Korea,University of Eastern Finland, Finland, EURECOM, France,National Institute of Informatics, Japan,Inria, France,TCG CREST, India, Institute for Infocomm Research, ASTAR, Singapore,Carnegie Mellon University, USA备注：Accepted by INTERSPEECH 2023. Code and models are available in this https URL

【18】 Voice Conversion With Just Nearest Neighbors标题：仅与最近邻居进行语音转换链接：https://arxiv.org/abs/2305.18975

作者：Matthew Baas,Benjamin van Niekerk,Herman Kamper机构：MediaLab, Department of Electrical & Electronic Engineering, Stellenbosch University, South Africa备注：5 page, 1 table, 2 figures. Accepted at Interspeech 2023

【19】 Investigating model performance in language identification: beyond simple error statistics标题：研究语言识别中的模型性能：超越简单的错误统计链接：https://arxiv.org/abs/2305.18925

作者：Suzy J. Styles,Victoria Y. H. Chua,Fei Ting Woon,Hexin Liu,Leibny Paola Garcia Perera,Sanjeev Khudanpur,Andy W. H. Khong,Justin Dauwels机构：Psychology, School of Social Sciences, Nanyang Technological University, Singapore, School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, CLSP and HLT-COE, Johns Hopkins University, USA备注：Accepted to Interspeech 2023, 5 pages, 5 figures

【20】 LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus标题：LibriTTS-R：一个恢复的多说话人文语转换语料库链接：https://arxiv.org/abs/2305.18802

作者：Yuma Koizumi,Heiga Zen,Shigeki Karita,Yifan Ding,Kohei Yatabe,Nobuyuki Morioka,Michiel Bacchiani,Yu Zhang,Wei Han,Ankur Bapna机构： Google, Japan, Tokyo University of Agriculture & Technology, Japan, Google, USA备注：Accepted to Interspeech 2023

【21】 Dual Transformer Decoder based Features Fusion Network for Automated Audio Captioning标题：基于双Transformer译码的自动音频字幕特征融合网络链接：https://arxiv.org/abs/2305.18753

作者：Jianyuan Sun,Xubo Liu,Xinhao Mei,Volkan Kılıç,Mark D. Plumbley,Wenwu Wang机构：Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK, Department of Electrical and Electronics Engineering, Izmir Katip Celebi University, Turkey备注：INTERSPEECH 2023. arXiv admin note: substantial text overlap with arXiv:2210.05037

【22】 Multi-Band Acoustic Monitoring of Aerial Signatures标题：航空签名的多频段声学监测链接：https://arxiv.org/abs/2305.18551

作者：Andrew Mead,Sarah Little,Paul Sail,Michelle Tu,Wesley Andrés Watters,Abigail White,Richard Cloete机构：Galileo Project, Harvard-Smithsonian Center for Astrophysics, Garden Street, Cambridge, MA , USA, †Scienti¯c Coalition for UAP Studies, Fort Myers, FL , USA, ‡Whitin Observatory, Wellesley College, Central Street, Wellesley, MA , USA, §Harvard University备注：None

【23】 DeCoR: Defy Knowledge Forgetting by Predicting Earlier Audio Codes标题：装饰：通过预测更早的音频码来挑战知识遗忘链接：https://arxiv.org/abs/2305.18441

作者：Xilin Jiang,Yinghao Aaron Li,Nima Mesgarani机构：Department of Electrical Engineering, Columbia University, USA备注：INTERSPEECH 2023

eess.AS音频处理

【1】 Make-A-Voice: Unified Voice Synthesis With Discrete Representation标题：发声：离散表示的统一语音合成链接：https://arxiv.org/abs/2305.19269

作者：Rongjie Huang,Chunlei Zhang,Yongqi Wang,Dongchao Yang,Luping Liu,Zhenhui Ye,Ziyue Jiang,Chao Weng,Zhou Zhao,Dong Yu机构：Zhejiang University, Tencent AI Lab, Peking University

【2】 A Stutter Seldom Comes Alone -- Cross-Corpus Stuttering Detection as a Multi-label Problem标题：口吃很少单独出现--作为多标签问题的跨语料库口吃检测链接：https://arxiv.org/abs/2305.19255

【3】 Leveraging Semantic Information for Efficient Self-Supervised Emotion Recognition with Audio-Textual Distilled Models标题：利用语义信息利用音频文本提取模型进行高效自监督情感识别链接：https://arxiv.org/abs/2305.19184

作者：Danilo de Oliveira,Navin Raj Prabhu,Timo Gerkmann机构：Signal Processing (SP), Universit¨at Hamburg, Germany备注：Accepted at Interspeech 2023

【4】 Predicting Preferred Dialogue-to-Background Loudness Difference in Dialogue-Separated Audio标题：预测对话分离音频中的首选对话与背景响度差异链接：https://arxiv.org/abs/2305.19100

【5】 Prospective Validation of Motor-Based Intervention with Automated Mispronunciation Detection of Rhotics in Residual Speech Sound Disorders标题：运动干预与Rhotics发音错误自动检测在残留语音障碍中的前瞻性验证链接：https://arxiv.org/abs/2305.19090

【6】 Towards single integrated spoofing-aware speaker verification embeddings标题：面向单一集成欺骗感知说话人验证嵌入链接：https://arxiv.org/abs/2305.19051

【7】 MiniSUPERB: Lightweight Benchmark for Self-supervised Speech Models标题：MiniSUPERB：用于自监督语音模型的轻量级基准链接：https://arxiv.org/abs/2305.19011

作者：Yu-Hsiang Wang,Huang-Yu Chen,Kai-Wei Chang,Winston Hsu,Hung-yi Lee机构：Graduate Institute of Electrical Engineering, National Taiwan University, Taiwan, Graduate Institute of Computer Science and Information Engineering, National Taiwan University

【8】 Voice Conversion With Just Nearest Neighbors标题：仅与最近邻居进行语音转换链接：https://arxiv.org/abs/2305.18975

【9】 Investigating model performance in language identification: beyond simple error statistics标题：研究语言识别中的模型性能：超越简单的错误统计链接：https://arxiv.org/abs/2305.18925

【10】 MERLIon CCS Challenge: A English-Mandarin code-switching child-directed speech corpus for language identification and diarization标题：Merlion CCS Challenges：一个面向语言识别和二值化的英汉语码转换儿童语音语料库链接：https://arxiv.org/abs/2305.18881

作者：Victoria Y. H. Chua,Hexin Liu,Leibny Paola Garcia Perera,Fei Ting Woon,Jinyi Wong,Xiangyu Zhang,Sanjeev Khudanpur,Andy W. H. Khong,Justin Dauwels,Suzy J. Styles机构：Psychology, School of Social Sciences, Nanyang Technological University, Singapore, School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, CLSP and HLT-COE, Johns Hopkins University, USA备注：Accepted by Interspeech 2023, 5 pages, 2 figures, 3 tables

【11】 LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus标题：LibriTTS-R：一个恢复的多说话人文语转换语料库链接：https://arxiv.org/abs/2305.18802

【12】 Dual Transformer Decoder based Features Fusion Network for Automated Audio Captioning标题：基于双Transformer译码的自动音频字幕特征融合网络链接：https://arxiv.org/abs/2305.18753

【13】 Adapting Multi-Lingual ASR Models for Handling Multiple Talkers标题：采用多语言ASR模型处理多个说话者链接：https://arxiv.org/abs/2305.18747

作者：Chenda Li,Yao Qian,Zhuo Chen,Naoyuki Kanda,Dongmei Wang,Takuya Yoshioka,Yanmin Qian,Michael Zeng机构：Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China, Microsoft, Redmond, WA, USA备注：Accepted by Interspeech 2023

【14】 An empirical study on speech restoration guided by self supervised speech representation标题：自监督语音表征指导语音恢复的实验研究链接：https://arxiv.org/abs/2305.18739

作者：Jaeuk Byun,Youna Ji,Soo Whan Chung,Soyeon Choe,Min Seok Choi机构：NAVER Cloud Corporation, Seongnam, South Korea备注：To be presented at ICASSP 2023

【15】 Transforming the Embeddings: A Lightweight Technique for Speech Emotion Recognition Tasks标题：变换嵌入：一种用于语音情感识别任务的轻量级技术链接：https://arxiv.org/abs/2305.18640

作者：Orchid Chetia Phukan,Arun Balaji Buduru,Rajesh Sharma机构：IIIT-Delhi, India, University of Tartu, Estonia备注：Accepted to Interspeech 2023

【16】 DeCoR: Defy Knowledge Forgetting by Predicting Earlier Audio Codes标题：装饰：通过预测更早的音频码来挑战知识遗忘链接：https://arxiv.org/abs/2305.18441

作者：Xilin Jiang,Yinghao Aaron Li,Nima Mesgarani机构：Department of Electrical Engineering, Columbia University, USA备注：INTERSPEECH 2023

【17】 Optimization design of a micro-perforated panel absorber with 8.6 octave bands标题：8.6倍频程微穿孔板吸振器的优化设计链接：https://arxiv.org/abs/2305.18298

作者：Xiaoming Wang,Chen Liang,Yulin Mei机构：School of Mechanical Engineering, Dalian University of Technology, School of Automotive Engineering

【18】 Unsupervised Melody-to-Lyric Generation标题：无监督的旋律到歌词生成链接：https://arxiv.org/abs/2305.19228

【19】 Adaptation of Tongue Ultrasound-Based Silent Speech Interfaces Using Spatial Transformer Networks标题：基于空间变换网络的舌超声无声语音接口自适应链接：https://arxiv.org/abs/2305.19130

【20】 Pseudo-Siamese Network based Timbre-reserved Black-box Adversarial Attack in Speaker Identification标题：说话人辨认中基于伪暹罗网络的保留音色黑盒对抗攻击链接：https://arxiv.org/abs/2305.19020

作者：Qing Wang,Jixun Yao,Ziqian Wang,Pengcheng Guo,Lei Xie机构：Northwestern Polytechnical University (NPU), Xi’an, China备注：5 pages

【21】 Language-independent speaker anonymization using orthogonal Householder neural network标题：基于正交Household神经网络的非语言无关说话人匿名链接：https://arxiv.org/abs/2305.18823

作者：Xiaoxiao Miao,Xin Wang,Erica Cooper,Junichi Yamagishi,Natalia Tomashenko

【22】 Understanding temporally weakly supervised training: A case study for keyword spotting标题：理解时间弱监督训练：关键词识别的案例研究链接：https://arxiv.org/abs/2305.18794

作者：Heinrich Dinkel,Weiji Zhuang,Zhiyong Yan,Yongqing Wang,Junbo Zhang,Yujun Wang机构：Xiaomi Corperation, Beijing, China

【23】 E-PANNs: Sound Recognition Using Efficient Pre-trained Audio Neural Networks标题：E-PANN：基于高效预训练音频神经网络的声音识别链接：https://arxiv.org/abs/2305.18665

作者：Arshdeep Singh,Haohe Liu,Mark D. Plumbley机构：Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK备注：Accepted in Internoise 2023 conference

【24】 Building Accurate Low Latency ASR for Streaming Voice Search标题：为流媒体语音搜索构建准确的低延迟ASR链接：https://arxiv.org/abs/2305.18596

作者：Abhinav Goyal,Nikesh Garera机构：Flipkart备注：Accepted at ACL 2023 Industry Track

【25】 Multi-Band Acoustic Monitoring of Aerial Signatures标题：航空签名的多频段声学监测链接：https://arxiv.org/abs/2305.18551

【26】 VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset标题：Vavast：一个视觉-音频-字幕-文本全通道基础模型和数据集链接：https://arxiv.org/abs/2305.18500

作者：Sihan Chen,Handong Li,Qunbo Wang,Zijia Zhao,Mingzhen Sun,Xinxin Zhu,Jing Liu机构：School of Artificial Intelligence, University of Chinese Academy of Sciences, Institute of Automation, Chinese Academy of Science备注：23 pages, 5 figures

【27】 Make-An-Audio 2: Temporal-Enhanced Text-to-Audio Generation标题：Make-an-Audio 2：时间增强的文本到音频生成链接：https://arxiv.org/abs/2305.18474

作者：Jiawei Huang,Yi Ren,Rongjie Huang,Dongchao Yang,Zhenhui Ye,Chen Zhang,Jinglin Liu,Xiang Yin,Zejun Ma,Zhou Zhao机构：Zhejiang University, ByteDance, Peking University

【28】 Semantic Segmentation with Bidirectional Language Models Improves Long-form ASR标题：基于双向语言模型的语义切分改进长形ASR链接：https://arxiv.org/abs/2305.18419

作者：W. Ronny Huang,Hao Zhang,Shankar Kumar,Shuo-yiin Chang,Tara N. Sainath机构：Google Research, USA备注：Interspeech 2023. First 3 authors contributed equally

【29】 Speech Intelligibility Assessment of Dysarthric Speech by using Goodness of Pronunciation with Uncertainty Quantification标题：用发音优度不确定度量化评价韵律障碍语音的清晰度链接：https://arxiv.org/abs/2305.18392

【30】 An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization标题：一种基于近邻初始化的高效扩散模型隶属度推理攻击链接：https://arxiv.org/abs/2305.18355

作者：Fei Kong,Jinhao Duan,RuiPeng Ma,Hengtao Shen,Xiaofeng Zhu,Xiaoshuang Shi,Kaidi Xu机构：University of Electronic Science and Technology of China, Drexel University

【31】 Mitigating Catastrophic Forgetting for Few-Shot Spoken Word Classification Through Meta-Learning标题：利用元学习缓解少发口语分类中的灾难性遗忘链接：https://arxiv.org/abs/2305.13080

作者：Ruan van der Merwe,Herman Kamper机构：ByteFuse, E&E Engineering, Stellenbosch University, South Africa备注：5 pages, 3 figures, Accepted to Interspeech 2023

机器翻译，仅供参考

语音/音频处理学术速递[5.31]

评论 0