今日论文合集：cs.SD语音44篇，eess.AS音频处理44篇。
cs.SD语音
【1】 An Investigation of Distribution Alignment in Multi-Genre Speaker Recognition标题：多语种说话人识别中的分布对齐研究作者：Zhenyu Zhou,Junhui Chen,Namin Wang,Lantian Li,Dong Wang备注：submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.14158v1
【2】 Multi-Domain Adaptation by Self-Supervised Learning for Speaker Verification标题：基于自监督学习的多领域自适应说话人确认作者：Wan Lin,Lantian Li,Dong Wang备注：submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.14149v1
【3】 On the Relation between Internal Language Model and Sequence Discriminative Training for Neural Transducers标题：论神经传感器内部语言模型与顺序辨别训练的关系作者：Zijian Yang,Wei Zhou,Ralf Schlüter,Hermann Ney备注：submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.14130v1【4】 VoiceLens: Controllable Speaker Generation and Editing with Flow标题：VoiceLens：可控制的扬声器生成和流编辑作者：Yao Shi,Ming Li链接：http://arxiv.org/pdf/2309.14094v1【5】 Audio classification with Dilated Convolution with Learnable Spacings标题：具有可学习间隔的扩展卷积的音频分类作者：Ismail Khalfaoui-Hassani,Timothée Masquelier,Thomas Pellegrini链接：http://arxiv.org/pdf/2309.13972v1【6】 Speed Co-Augmentation for Unsupervised Audio-Visual Pre-training标题：无监督视听预训练中的速度协同增强作者：Jiangliu Wang,Jianbo Jiao,Yibing Song,Stephen James,Zhan Tong,Chongjian Ge,Pieter Abbeel,Yun-hui Liu备注：Published at the CVPR 2023 Sight and Sound workshop链接：http://arxiv.org/pdf/2309.13942v1【7】 Real-Time Emergency Vehicle Detection using Mel Spectrograms and Regular Expressions标题：基于Mel谱图和正则表达式的紧急车辆实时检测作者：Alberto Pacheco-Gonzalez,Raymundo Torres,Raul Chacon,Isidro Robledo备注：in Spanish language链接：http://arxiv.org/pdf/2309.13920v1【8】 HiGNN-TTS: Hierarchical Prosody Modeling with Graph Neural Networks for Expressive Long-form TTS标题：HiGNN-TTS：基于图神经网络的表现型长篇TTS层次化韵律建模作者：Dake Guo,Xinfa Zhu,Liumeng Xue,Tao Li,Yuanjun Lv,Yuepeng Jiang,Lei Xie备注：Accepted by ASRU2023链接：http://arxiv.org/pdf/2309.13907v1【9】 Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data标题：使用开源工具包和公开可用的数据重现耳语式训练作者：Yifan Peng,Jinchuan Tian,Brian Yan,Dan Berrebbi,Xuankai Chang,Xinjian Li,Jiatong Shi,Siddhant Arora,William Chen,Roshan Sharma,Wangyou Zhang,Yui Sudo,Muhammad Shakeel,Jee-weon Jung,Soumi Maiti,Shinji Watanabe备注：Accepted at ASRU 2023链接：http://arxiv.org/pdf/2309.13876v1
【10】 Fast-HuBERT: An Efficient Training Framework for Self-Supervised Speech Representation Learning标题：FAST-Hubert：一种高效的自监督语音表征学习训练框架作者：Guanrou Yang,Ziyang Ma,Zhisheng Zheng,Yakun Song,Zhikang Niu,Xie Chen链接：http://arxiv.org/pdf/2309.13860v1【11】 The second multi-channel multi-party meeting transcription challenge (M2MeT) 2.0): A benchmark for speaker-attributed ASR标题：第二次多渠道多方会议转录挑战(M2MeT)2.0)：说话人ASR的基准作者：Yuhao Liang,Mohan Shi,Fan Yu,Yangze Li,Shiliang Zhang,Zhihao Du,Qian Chen,Lei Xie,Yanmin Qian,Jian Wu,Zhuo Chen,Kong Aik Lee,Zhijie Yan,Hui Bu备注：8 pages, Accepted by ASRU2023链接：http://arxiv.org/pdf/2309.13573v1【12】 Related Rhythms: Recommendation System To Discover Music You May Like标题：相关节拍：发现你喜欢的音乐的推荐系统作者：Rahul Singh,Pranav Kanuparthi链接：http://arxiv.org/pdf/2309.13544v1【13】 Coco-Nut: Corpus of Japanese Utterance and Voice Characteristics Description for Prompt-based Control标题：Coco-Nut：面向提示控制的日语语音特征描述语料库作者：Aya Watanabe,Shinnosuke Takamichi,Yuki Saito,Wataru Nakata,Detai Xin,Hiroshi Saruwatari备注：Submitted to ASRU2023链接：http://arxiv.org/pdf/2309.13509v1【14】 Hierarchical attention interpretation: an interpretable speech-level transformer for bi-modal depression detection标题：分层注意解释：一种用于双模式抑郁检测的可解释语音级转换器作者：Qingkun Deng,Saturnino Luz,Sofia de la Fuente Garcia备注：5 pages, 3 figures, submitted to IEEE International Conference on Acoustics, Speech, and Signal Processing链接：http://arxiv.org/pdf/2309.13476v1【15】 Asca: less audio data is more insightful标题：ASCA：音频数据越少越有洞察力作者：Xiang Li,Junhao Chen,Chao Li,Hongwu Lv备注：6 pages,3 figures链接：http://arxiv.org/pdf/2309.13373v1【16】 My Science Tutor (MyST) -- A Large Corpus of Children's Conversational Speech标题：我的科学导师(MYST)--儿童会话演讲的大型语料库作者：Sameer S. Pradhan,Ronald A. Cole,Wayne H. Ward链接：http://arxiv.org/pdf/2309.13347v1
【17】 Two vs. Four-Channel Sound Event Localization and Detection标题：双声道与四声道声事件定位与检测作者：Julia Wilkins,Magdalena Fuentes,Luca Bondi,Shabnam Ghaffarzadegan,Ali Abavisani,Juan Pablo Bello链接：http://arxiv.org/pdf/2309.13343v1【18】 Beyond Fairness: Age-Harmless Parkinson's Detection via Voice标题：超越公平：通过声音检测年龄无害的帕金森病作者：Yicheng Wang,Xiaotian Han,Leisheng Yu,Na Zou链接：http://arxiv.org/pdf/2309.13292v1【19】 WikiMT++ Dataset Card标题：WikiMT++数据集卡作者：Monan Zhou,Shangda Wu,Yuan Wang,Wei Li链接：http://arxiv.org/pdf/2309.13259v1【20】 Importance of negative sampling in weak label learning标题：负抽样在弱标签学习中的重要性作者：Ankit Shah,Fuyu Tang,Zelin Ye,Rita Singh,Bhiksha Raj链接：http://arxiv.org/pdf/2309.13227v1【21】 Invisible Watermarking for Audio Generation Diffusion Models标题：一种用于音频生成扩散模型的不可见水印作者：Xirong Cao,Xiang Li,Divyesh Jadav,Yanzhao Wu,Zhehui Chen,Chen Zeng,Wenqi Wei备注：This is an invited paper for IEEE TPS, part of the IEEE CICCogMITPS 2023 conference链接：http://arxiv.org/pdf/2309.13166v1【22】 Towards Lexical Analysis of Dog Vocalizations via Online Videos标题：基于网络视频的犬类发声词汇分析作者：Yufei Wang,Chunhao Zhang,Jieyi Huang,Mengyue Wu,Kenny Zhu链接：http://arxiv.org/pdf/2309.13086v1【23】 Does My Dog ''Speak'' Like Me? The Acoustic Correlation between Pet Dogs and Their Human Owners标题：我的狗狗会像我一样“说话”吗？宠物狗与其主人之间的声学相关性作者：Jieyi Huang,Chunhao Zhang,Yufei Wang,Mengyue Wu,Kenny Zhu链接：http://arxiv.org/pdf/2309.13085v1【24】 Towards General-Purpose Text-Instruction-Guided Voice Conversion标题：通用型文本-指令制导语音转换作者：Chun-Yi Kuan,Chen An Li,Tsu-Yuan Hsu,Tse-Yang Lin,Ho-Lam Chung,Kai-Wei Chang,Shuo-yiin Chang,Hung-yi Lee备注：Accepted to ASRU 2023链接：http://arxiv.org/pdf/2309.14324v1
【25】 Speaker anonymization using neural audio codec language models标题：基于神经音频编解码器语言模型的说话人匿名作者：Michele Panariello,Francesco Nespoli,Massimiliano Todisco,Nicholas Evans备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.14129v1【26】 Haha-Pod: An Attempt for Laughter-based Non-Verbal Speaker Verification标题：HAHA-Pod：一种基于笑声的非言语说话人确认方法作者：Yuke Lin,Xiaoyi Qin,Ning Jiang,Guoqing Zhao,Ming Li备注：accepted by ASRU 2023链接：http://arxiv.org/pdf/2309.14109v1【27】 Wav2vec-based Detection and Severity Level Classification of Dysarthria from Speech标题：基于Wav2vec的语音构音障碍检测及严重程度分类作者：Farhad Javanmardi,Saska Tirronen,Manila Kodali,Sudarsana Reddy Kadiri,Paavo AlkuJournal-ref：in Proc. ICASSP, Rhodes Island, Greece, June 4-10, 2023链接：http://arxiv.org/pdf/2309.14107v1【28】 BiSinger: Bilingual Singing Voice Synthesis标题：BiSinger：双语歌声合成作者：Huali Zhou,Yueqian Lin,Yao Shi,Peng Sun,Ming Li备注：Accepted by ASRU2023链接：http://arxiv.org/pdf/2309.14089v1【29】 Analysis and Detection of Pathological Voice using Glottal Source Features标题：基于声门声源特征的病理性嗓音分析与检测作者：Sudarsana Reddy Kadiri,Paavo AlkuJournal-ref：IEEE Journal of Selected Topics in Signal Processing, Vol. 14, No. 2, pp. 367-379, February 2020链接：http://arxiv.org/pdf/2309.14080v1【30】 Unsupervised Accent Adaptation Through Masked Language Model Correction Of Discrete Self-Supervised Speech Units标题：基于掩蔽语言模型的无监督口音自适应离散自监督语音单元的校正作者：Jakob Poncelet,Hugo Van hamme备注：Submitted to ICASSP2024链接：http://arxiv.org/pdf/2309.13994v1【31】 Connecting Speech Encoder and Large Language Model for ASR标题：ASR中语音编码器与大语言模型的连接作者：Wenyi Yu,Changli Tang,Guangzhi Sun,Xianzhao Chen,Tian Tan,Wei Li,Lu Lu,Zejun Ma,Chao Zhang链接：http://arxiv.org/pdf/2309.13963v1【32】 Evaluating Classification Systems Against Soft Labels with Fuzzy Precision and Recall标题：基于模糊精确度和召回率的软标签分类系统评价作者：Manu Harju,Annamaria Mesaros备注：published in DCASE 2023链接：http://arxiv.org/pdf/2309.13938v1
【33】 Frame-wise streaming end-to-end speaker diarization with non-autoregressive self-attention-based attractors标题：基于非自回归自注意吸引子的逐帧流传输端到端说话人二值化作者：Di Liang,Nian Shao,Xiaofei Li链接：http://arxiv.org/pdf/2309.13916v1【34】 AutoPrep: An Automatic Preprocessing Framework for In-the-Wild Speech Data标题：AutoPrep：一种野外语音数据自动预处理框架作者：Jianwei Yu,Hangting Chen,Yanyao Bian,Xiang Li,Yi Luo,Jinchuan Tian,Mengyang Liu,Jiayi Jiang,Shuai Wang链接：http://arxiv.org/pdf/2309.13905v1【35】 Diffusion Conditional Expectation Model for Efficient and Robust Target Speech Extraction标题：高效稳健性目标语音提取的扩散条件期望模型作者：Leying Zhang,Yao Qian,Linfeng Yu,Heming Wang,Xinkai Wang,Hemin Yang,Long Zhou,Shujie Liu,Yanmin Qian,Michael Zeng备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.13874v1【36】 A Two-Step Approach for Narrowband Source Localization in Reverberant Rooms标题：混响室内窄带声源定位的两步法作者：Wei-Ting Lai,Lachlan Birnie,Thushara Abhayapala,Amy Bastine,Shaoheng Xu,Prasanga Samarasinghe链接：http://arxiv.org/pdf/2309.13819v1【37】 VoiceLDM: Text-to-Speech with Environmental Context标题：VoiceLDM：具有环境背景的文本到语音转换作者：Yeonghyeon Lee,Inmo Yeon,Juhan Nam,Joon Son Chung备注：Demos and code are available at this https URL链接：http://arxiv.org/pdf/2309.13664v1【38】 Cross-modal Alignment with Optimal Transport for CTC-based ASR标题：基于CTC的ASR的跨模式匹配和最优传输作者：Xugang Lu,Peng Shen,Yu Tsao,Hisashi Kawai备注：Accepted to IEEE ASRU 2023链接：http://arxiv.org/pdf/2309.13650v1【39】 Efficient Black-Box Speaker Verification Model Adaptation with Reprogramming and Backend Learning标题：基于重编程和后端学习的高效黑盒说话人确认模型自适应作者：Jingyu Li,Tan Lee链接：http://arxiv.org/pdf/2309.13605v1【40】 Speech enhancement with frequency domain auto-regressive modeling标题：基于频域自回归建模的语音增强作者：Anurenjan Purushothaman,Debottam Dutta,Rohit Kumar,Sriram GanapathyJournal-ref：IEEEACM Transactions on Audio, Speech and Language Processing 2023链接：http://arxiv.org/pdf/2309.13537v1【41】 Attention Is All You Need For Blind Room Volume Estimation标题：你只需要注意就可以估计盲室体积作者：Chunxi Wang,Maoshen Jia,Meiran Li,Changchun Bao,Wenyu Jin备注：5 pages, 4 figures, submitted ICASSP 2024链接：http://arxiv.org/pdf/2309.13504v1【42】 Contrastive Speaker Embedding With Sequential Disentanglement标题：序列解纠缠的对比话者嵌入作者：Youzhi Tu,Man-Wai Mak,Jen-Tzung Chien备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.13253v1【43】 Importance of Smoothness Induced by Optimizers in FL4ASR: Towards Understanding Federated Learning for End-to-End ASR标题：FL4ASR中优化器诱导的平滑性的重要性：理解端到端ASR的联合学习作者：Sheikh Shams Azam,Tatiana Likhomanenko,Martin Pelikan,Jan "Honza" Silovsky备注：In Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) 2023链接：http://arxiv.org/pdf/2309.13102v1【44】 A time-causal and time-recursive analogue of the Gabor transform标题：Gabor变换的时间因果和时间递归模拟作者：Tony Lindeberg备注：10 pages, 5 figures链接：http://arxiv.org/pdf/2308.14512v3
eess.AS音频处理
【1】 Towards General-Purpose Text-Instruction-Guided Voice Conversion标题：通用型文本-指令制导语音转换作者：Chun-Yi Kuan,Chen An Li,Tsu-Yuan Hsu,Tse-Yang Lin,Ho-Lam Chung,Kai-Wei Chang,Shuo-yiin Chang,Hung-yi Lee备注：Accepted to ASRU 2023链接：http://arxiv.org/pdf/2309.14324v1
【2】 Speaker anonymization using neural audio codec language models标题：基于神经音频编解码器语言模型的说话人匿名作者：Michele Panariello,Francesco Nespoli,Massimiliano Todisco,Nicholas Evans备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.14129v1
【3】 Haha-Pod: An Attempt for Laughter-based Non-Verbal Speaker Verification标题：HAHA-Pod：一种基于笑声的非言语说话人确认方法作者：Yuke Lin,Xiaoyi Qin,Ning Jiang,Guoqing Zhao,Ming Li备注：accepted by ASRU 2023链接：http://arxiv.org/pdf/2309.14109v1【4】 Wav2vec-based Detection and Severity Level Classification of Dysarthria from Speech标题：基于Wav2vec的语音构音障碍检测及严重程度分类作者：Farhad Javanmardi,Saska Tirronen,Manila Kodali,Sudarsana Reddy Kadiri,Paavo AlkuJournal-ref：in Proc. ICASSP, Rhodes Island, Greece, June 4-10, 2023链接：http://arxiv.org/pdf/2309.14107v1【5】 BiSinger: Bilingual Singing Voice Synthesis标题：BiSinger：双语歌声合成作者：Huali Zhou,Yueqian Lin,Yao Shi,Peng Sun,Ming Li备注：Accepted by ASRU2023链接：http://arxiv.org/pdf/2309.14089v1【6】 Analysis and Detection of Pathological Voice using Glottal Source Features标题：基于声门声源特征的病理性嗓音分析与检测作者：Sudarsana Reddy Kadiri,Paavo AlkuJournal-ref：IEEE Journal of Selected Topics in Signal Processing, Vol. 14, No. 2, pp. 367-379, February 2020链接：http://arxiv.org/pdf/2309.14080v1【7】 Unsupervised Accent Adaptation Through Masked Language Model Correction Of Discrete Self-Supervised Speech Units标题：基于掩蔽语言模型的无监督口音自适应离散自监督语音单元的校正作者：Jakob Poncelet,Hugo Van hamme备注：Submitted to ICASSP2024链接：http://arxiv.org/pdf/2309.13994v1【8】 Connecting Speech Encoder and Large Language Model for ASR标题：ASR中语音编码器与大语言模型的连接作者：Wenyi Yu,Changli Tang,Guangzhi Sun,Xianzhao Chen,Tian Tan,Wei Li,Lu Lu,Zejun Ma,Chao Zhang链接：http://arxiv.org/pdf/2309.13963v1【9】 Evaluating Classification Systems Against Soft Labels with Fuzzy Precision and Recall标题：基于模糊精确度和召回率的软标签分类系统评价作者：Manu Harju,Annamaria Mesaros备注：published in DCASE 2023链接：http://arxiv.org/pdf/2309.13938v1【10】 Frame-wise streaming end-to-end speaker diarization with non-autoregressive self-attention-based attractors标题：基于非自回归自注意吸引子的逐帧流传输端到端说话人二值化作者：Di Liang,Nian Shao,Xiaofei Li链接：http://arxiv.org/pdf/2309.13916v1
【11】 AutoPrep: An Automatic Preprocessing Framework for In-the-Wild Speech Data标题：AutoPrep：一种野外语音数据自动预处理框架作者：Jianwei Yu,Hangting Chen,Yanyao Bian,Xiang Li,Yi Luo,Jinchuan Tian,Mengyang Liu,Jiayi Jiang,Shuai Wang链接：http://arxiv.org/pdf/2309.13905v1【12】 Diffusion Conditional Expectation Model for Efficient and Robust Target Speech Extraction标题：高效稳健性目标语音提取的扩散条件期望模型作者：Leying Zhang,Yao Qian,Linfeng Yu,Heming Wang,Xinkai Wang,Hemin Yang,Long Zhou,Shujie Liu,Yanmin Qian,Michael Zeng备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.13874v1【13】 A Two-Step Approach for Narrowband Source Localization in Reverberant Rooms标题：混响室内窄带声源定位的两步法作者：Wei-Ting Lai,Lachlan Birnie,Thushara Abhayapala,Amy Bastine,Shaoheng Xu,Prasanga Samarasinghe链接：http://arxiv.org/pdf/2309.13819v1【14】 VoiceLDM: Text-to-Speech with Environmental Context标题：VoiceLDM：具有环境背景的文本到语音转换作者：Yeonghyeon Lee,Inmo Yeon,Juhan Nam,Joon Son Chung备注：Demos and code are available at this https URL链接：http://arxiv.org/pdf/2309.13664v1【15】 Cross-modal Alignment with Optimal Transport for CTC-based ASR标题：基于CTC的ASR的跨模式匹配和最优传输作者：Xugang Lu,Peng Shen,Yu Tsao,Hisashi Kawai备注：Accepted to IEEE ASRU 2023链接：http://arxiv.org/pdf/2309.13650v1【16】 Efficient Black-Box Speaker Verification Model Adaptation with Reprogramming and Backend Learning标题：基于重编程和后端学习的高效黑盒说话人确认模型自适应作者：Jingyu Li,Tan Lee链接：http://arxiv.org/pdf/2309.13605v1【17】 Speech enhancement with frequency domain auto-regressive modeling标题：基于频域自回归建模的语音增强作者：Anurenjan Purushothaman,Debottam Dutta,Rohit Kumar,Sriram GanapathyJournal-ref：IEEEACM Transactions on Audio, Speech and Language Processing 2023链接：http://arxiv.org/pdf/2309.13537v1【18】 Attention Is All You Need For Blind Room Volume Estimation标题：你只需要注意就可以估计盲室体积作者：Chunxi Wang,Maoshen Jia,Meiran Li,Changchun Bao,Wenyu Jin备注：5 pages, 4 figures, submitted ICASSP 2024链接：http://arxiv.org/pdf/2309.13504v1【19】 Contrastive Speaker Embedding With Sequential Disentanglement标题：序列解纠缠的对比话者嵌入作者：Youzhi Tu,Man-Wai Mak,Jen-Tzung Chien备注：Submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.13253v1【20】 Importance of Smoothness Induced by Optimizers in FL4ASR: Towards Understanding Federated Learning for End-to-End ASR标题：FL4ASR中优化器诱导的平滑性的重要性：理解端到端ASR的联合学习作者：Sheikh Shams Azam,Tatiana Likhomanenko,Martin Pelikan,Jan "Honza" Silovsky备注：In Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) 2023链接：http://arxiv.org/pdf/2309.13102v1【21】 An Investigation of Distribution Alignment in Multi-Genre Speaker Recognition标题：多语种说话人识别中的分布对齐研究作者：Zhenyu Zhou,Junhui Chen,Namin Wang,Lantian Li,Dong Wang备注：submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.14158v1【22】 Multi-Domain Adaptation by Self-Supervised Learning for Speaker Verification标题：基于自监督学习的多领域自适应说话人确认作者：Wan Lin,Lantian Li,Dong Wang备注：submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.14149v1【23】 On the Relation between Internal Language Model and Sequence Discriminative Training for Neural Transducers标题：论神经传感器内部语言模型与顺序辨别训练的关系作者：Zijian Yang,Wei Zhou,Ralf Schlüter,Hermann Ney备注：submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.14130v1【24】 VoiceLens: Controllable Speaker Generation and Editing with Flow标题：VoiceLens：可控制的扬声器生成和流编辑作者：Yao Shi,Ming Li链接：http://arxiv.org/pdf/2309.14094v1【25】 Audio classification with Dilated Convolution with Learnable Spacings标题：具有可学习间隔的扩展卷积的音频分类作者：Ismail Khalfaoui-Hassani,Timothée Masquelier,Thomas Pellegrini链接：http://arxiv.org/pdf/2309.13972v1【26】 Speed Co-Augmentation for Unsupervised Audio-Visual Pre-training标题：无监督视听预训练中的速度协同增强作者：Jiangliu Wang,Jianbo Jiao,Yibing Song,Stephen James,Zhan Tong,Chongjian Ge,Pieter Abbeel,Yun-hui Liu备注：Published at the CVPR 2023 Sight and Sound workshop链接：http://arxiv.org/pdf/2309.13942v1【27】 Real-Time Emergency Vehicle Detection using Mel Spectrograms and Regular Expressions标题：基于Mel谱图和正则表达式的紧急车辆实时检测作者：Alberto Pacheco-Gonzalez,Raymundo Torres,Raul Chacon,Isidro Robledo备注：in Spanish language链接：http://arxiv.org/pdf/2309.13920v1【28】 HiGNN-TTS: Hierarchical Prosody Modeling with Graph Neural Networks for Expressive Long-form TTS标题：HiGNN-TTS：基于图神经网络的表现型长篇TTS层次化韵律建模作者：Dake Guo,Xinfa Zhu,Liumeng Xue,Tao Li,Yuanjun Lv,Yuepeng Jiang,Lei Xie备注：Accepted by ASRU2023链接：http://arxiv.org/pdf/2309.13907v1【29】 Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data标题：使用开源工具包和公开可用的数据重现耳语式训练作者：Yifan Peng,Jinchuan Tian,Brian Yan,Dan Berrebbi,Xuankai Chang,Xinjian Li,Jiatong Shi,Siddhant Arora,William Chen,Roshan Sharma,Wangyou Zhang,Yui Sudo,Muhammad Shakeel,Jee-weon Jung,Soumi Maiti,Shinji Watanabe备注：Accepted at ASRU 2023链接：http://arxiv.org/pdf/2309.13876v1【30】 Fast-HuBERT: An Efficient Training Framework for Self-Supervised Speech Representation Learning标题：FAST-Hubert：一种高效的自监督语音表征学习训练框架作者：Guanrou Yang,Ziyang Ma,Zhisheng Zheng,Yakun Song,Zhikang Niu,Xie Chen链接：http://arxiv.org/pdf/2309.13860v1【31】 The second multi-channel multi-party meeting transcription challenge (M2MeT) 2.0): A benchmark for speaker-attributed ASR标题：第二次多渠道多方会议转录挑战(M2MeT)2.0)：说话人ASR的基准作者：Yuhao Liang,Mohan Shi,Fan Yu,Yangze Li,Shiliang Zhang,Zhihao Du,Qian Chen,Lei Xie,Yanmin Qian,Jian Wu,Zhuo Chen,Kong Aik Lee,Zhijie Yan,Hui Bu备注：8 pages, Accepted by ASRU2023链接：http://arxiv.org/pdf/2309.13573v1【32】 Related Rhythms: Recommendation System To Discover Music You May Like标题：相关节拍：发现你喜欢的音乐的推荐系统作者：Rahul Singh,Pranav Kanuparthi链接：http://arxiv.org/pdf/2309.13544v1
【33】 Coco-Nut: Corpus of Japanese Utterance and Voice Characteristics Description for Prompt-based Control标题：Coco-Nut：面向提示控制的日语语音特征描述语料库作者：Aya Watanabe,Shinnosuke Takamichi,Yuki Saito,Wataru Nakata,Detai Xin,Hiroshi Saruwatari备注：Submitted to ASRU2023链接：http://arxiv.org/pdf/2309.13509v1【34】 Hierarchical attention interpretation: an interpretable speech-level transformer for bi-modal depression detection标题：分层注意解释：一种用于双模式抑郁检测的可解释语音级转换器作者：Qingkun Deng,Saturnino Luz,Sofia de la Fuente Garcia备注：5 pages, 3 figures, submitted to IEEE International Conference on Acoustics, Speech, and Signal Processing链接：http://arxiv.org/pdf/2309.13476v1【35】 Asca: less audio data is more insightful标题：ASCA：音频数据越少越有洞察力作者：Xiang Li,Junhao Chen,Chao Li,Hongwu Lv备注：6 pages,3 figures链接：http://arxiv.org/pdf/2309.13373v1【36】 My Science Tutor (MyST) -- A Large Corpus of Children's Conversational Speech标题：我的科学导师(MYST)--儿童会话演讲的大型语料库作者：Sameer S. Pradhan,Ronald A. Cole,Wayne H. Ward链接：http://arxiv.org/pdf/2309.13347v1【37】 Two vs. Four-Channel Sound Event Localization and Detection标题：双声道与四声道声事件定位与检测作者：Julia Wilkins,Magdalena Fuentes,Luca Bondi,Shabnam Ghaffarzadegan,Ali Abavisani,Juan Pablo Bello链接：http://arxiv.org/pdf/2309.13343v1【38】 Beyond Fairness: Age-Harmless Parkinson's Detection via Voice标题：超越公平：通过声音检测年龄无害的帕金森病作者：Yicheng Wang,Xiaotian Han,Leisheng Yu,Na Zou链接：http://arxiv.org/pdf/2309.13292v1【39】 WikiMT++ Dataset Card标题：WikiMT++数据集卡作者：Monan Zhou,Shangda Wu,Yuan Wang,Wei Li链接：http://arxiv.org/pdf/2309.13259v1【40】 Importance of negative sampling in weak label learning标题：负抽样在弱标签学习中的重要性作者：Ankit Shah,Fuyu Tang,Zelin Ye,Rita Singh,Bhiksha Raj链接：http://arxiv.org/pdf/2309.13227v1【41】 Invisible Watermarking for Audio Generation Diffusion Models标题：一种用于音频生成扩散模型的不可见水印作者：Xirong Cao,Xiang Li,Divyesh Jadav,Yanzhao Wu,Zhehui Chen,Chen Zeng,Wenqi Wei备注：This is an invited paper for IEEE TPS, part of the IEEE CICCogMITPS 2023 conference链接：http://arxiv.org/pdf/2309.13166v1【42】 Towards Lexical Analysis of Dog Vocalizations via Online Videos标题：基于网络视频的犬类发声词汇分析作者：Yufei Wang,Chunhao Zhang,Jieyi Huang,Mengyue Wu,Kenny Zhu链接：http://arxiv.org/pdf/2309.13086v1【43】 Does My Dog ''Speak'' Like Me? The Acoustic Correlation between Pet Dogs and Their Human Owners标题：我的狗狗会像我一样“说话”吗？宠物狗与其主人之间的声学相关性作者：Jieyi Huang,Chunhao Zhang,Yufei Wang,Mengyue Wu,Kenny Zhu链接：http://arxiv.org/pdf/2309.13085v1【44】 Applied design thinking in urban air mobility: creating the airtaxi cabin design of the future from a user perspective标题：城市空气机动性中的应用设计思维：从用户的角度创造未来的空中出租车客舱设计作者：F. Reimer,J. Herzig,L. Winkler,J. Biedermann,F. Meller,B. Nagel备注：13 pages链接：http://arxiv.org/pdf/2309.05353v1
机器翻译，仅供参考