今日论文合集：cs.SD语音13篇，eess.AS音频处理13篇。
cs.SD语音

【1】 AV-CPL: Continuous Pseudo-Labeling for Audio-Visual Speech Recognition标题：连续伪标记法在视听语音识别中的应用作者：Andrew Rouditchenko,Ronan Collobert,Tatiana Likhomanenko机构：MIT, Apple备注：Under review链接：http://arxiv.org/pdf/2309.17395v1

【2】 Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Supervision, and LLM Mix-up Augmentation标题：利用细粒度音频特征、文本嵌入监督和LLM混合增强改进音频字幕模型作者：Shih-Lun Wu,Xuankai Chang,Gordon Wichern,Jee-weon Jung,François Germain,Jonathan Le Roux,Shinji Watanabe机构：Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA, Mitsubishi Electric Research Labs (MERL), Cambridge, MA, USA备注：Preprint, under review at ICASSP 2024. Winner of the DCASE 2023 Challenge Task 6A: Automated Audio Captioning (AAC)链接：http://arxiv.org/pdf/2309.17352v1
【3】 RTFS-Net: Recurrent time-frequency modelling for efficient audio-visual speech separation标题：RTFS-Net：高效视听语音分离的递归时频建模作者：Samuel Pegg,Kai Li,Xiaolin Hu机构：. Department of Computer Science and Technology, Institute for AI, BNRist, Tsinghua University, Beijing , China, . Tsinghua Laboratory of Brain and Intelligence (THBI), IDGMcGovern Institute for Brain Research, Tsinghua University, Beijing , China备注：17 pages, 4 figures链接：http://arxiv.org/pdf/2309.17189v1【4】 Style Transfer for Non-differentiable Audio Effects标题：不可区分音效的风格转换作者：Kieran Grant机构：University of Glasgow链接：http://arxiv.org/pdf/2309.17125v1【5】 ReFlow-TTS: A Rectified Flow Model for High-fidelity Text-to-Speech标题：Reflow-TTS：一种适用于高保真文语转换的纠错流模型作者：Wenhao Guan,Qi Su,Haodong Zhou,Shiyu Miao,Xingjia Xie,Lin Li,Qingyang Hong机构：School of Informatics, Xiamen University, China, School of Electronic Science and Engineering, Xiamen University, China备注：Submitted to ICASSP2024链接：http://arxiv.org/pdf/2309.17056v1【6】 SSHR: Leveraging Self-supervised Hierarchical Representations for Multilingual Automatic Speech Recognition标题：SSHR：利用自监督层次表示进行多语言自动语音识别作者：Hongfei Xue,Qijie Shao,Kaixun Huang,Peikun Chen,Lei Xie,Jie Liu机构：Northwestern Polytechnical University, Xian, China, Huawei Cloud备注：5 pages, 2 figures链接：http://arxiv.org/pdf/2309.16937v1【7】 Toward Universal Speech Enhancement for Diverse Input Conditions标题：面向不同输入条件的通用语音增强作者：Wangyou Zhang,Kohei Saijo,Zhong-Qiu Wang,Shinji Watanabe,Yanmin Qian机构：Shanghai Jiao Tong University, China, Waseda University, Japan, Carnegie Mellon University, USA备注：6 pages, 3 figures, 5 tables, accepted by ASRU 2023链接：http://arxiv.org/pdf/2309.17384v1【8】 LRPD: Large Replay Parallel Dataset标题：LRPD：大型重播并行数据集作者：Ivan Yakovlev,Mikhail Melnikov,Nikita Bukhal,Rostislav Makarov,Alexander Alenin,Nikita Torgashov,Anton Okhotnikov机构：(c) Paper ID: , (f) Conference Location: Singapore, Sands Expo & Convention Centre, (g) DOI: ,.,ICASSP,.,., (h) Publisher: IEEE, (i) Cite as:, Yakovlev, I., Melnikov, M., Bukhal, N., Makarov, R., Alenin, A., TorgashovJournal-ref：ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 6612-6616链接：http://arxiv.org/pdf/2309.17298v1【9】 Wiki-En-ASR-Adapt: Large-scale synthetic dataset for English ASR Customization标题：Wiki-en-ASR-Adapt：面向英语ASR定制的大规模合成数据集作者：Alexandra Antonova机构：Moscow Institute of Physics and Technology备注：Accepted to IEEE ASRU 2023链接：http://arxiv.org/pdf/2309.17267v1【10】 Low-Resource Self-Supervised Learning with SSL-Enhanced TTS标题：基于SSL增强型TTS的低资源自监督学习作者：Po-chun Hsu,Ali Elkahky,Wei-Ning Hsu,Yossi Adi,Tu Anh Nguyen,Jade Copet,Emmanuel Dupoux,Hung-yi Lee,Abdelrahman Mohamed机构：Graduate Institute of Communication Engineering, National Taiwan University, Apple, Meta AI, The Hebrew University of Jerusalem, Rembrand Inc.备注：Preprint链接：http://arxiv.org/pdf/2309.17020v1【11】 Synthetic Speech Detection Based on Temporal Consistency and Distribution of Speaker Features标题：基于说话人特征时间一致性和分布的合成语音检测作者：Yuxiang Zhang,Zhuo Li,Jingze Lu,Wenchao Wang,Pengyuan Zhang机构：Wenchao Wang and Pengyuan ZhangThe authors are with Key Laboratory of Speech Acoustics and ContentUnderstanding, Institute of Acoustics, China and also with University of Chinese Academy of Sciences备注：5 pages, 3 figures, 4 tables链接：http://arxiv.org/pdf/2309.16954v1【12】 Enhancing Code-switching Speech Recognition with Interactive Language Biases标题：利用交互语言偏向增强码型转换语音识别作者：Hexin Liu,Leibny Paola Garcia,Xiangyu Zhang,Andy W. H. Khong,Sanjeev Khudanpur机构：School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, CLSP and HLT-COE, Johns Hopkins University, USA, University of New South Wales, Australia备注：Submitted to IEEE ICASSP 2024链接：http://arxiv.org/pdf/2309.16953v1【13】 Towards High Resolution Weather Monitoring with Sound Data标题：利用声学数据进行高分辨率天气监测作者：Enis Berk Çoban,Megan Perra,Michael I. Mandel机构：Michael I Mandel, The Graduate Center, CUNY, New York, NY, USA, Environmental Biology, SUNY-ESF, Syracuse, NY, USA备注：5 pages, submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.16867v1
eess.AS音频处理

【1】 Toward Universal Speech Enhancement for Diverse Input Conditions标题：面向不同输入条件的通用语音增强作者：Wangyou Zhang,Kohei Saijo,Zhong-Qiu Wang,Shinji Watanabe,Yanmin Qian机构：Shanghai Jiao Tong University, China, Waseda University, Japan, Carnegie Mellon University, USA备注：6 pages, 3 figures, 5 tables, accepted by ASRU 2023链接：http://arxiv.org/pdf/2309.17384v1

【2】 LRPD: Large Replay Parallel Dataset标题：LRPD：大型重播并行数据集作者：Ivan Yakovlev,Mikhail Melnikov,Nikita Bukhal,Rostislav Makarov,Alexander Alenin,Nikita Torgashov,Anton Okhotnikov机构：(c) Paper ID: , (f) Conference Location: Singapore, Sands Expo & Convention Centre, (g) DOI: ,.,ICASSP,.,., (h) Publisher: IEEE, (i) Cite as:, Yakovlev, I., Melnikov, M., Bukhal, N., Makarov, R., Alenin, A., TorgashovJournal-ref：ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 6612-6616链接：http://arxiv.org/pdf/2309.17298v1
【3】 Wiki-En-ASR-Adapt: Large-scale synthetic dataset for English ASR Customization标题：Wiki-en-ASR-Adapt：面向英语ASR定制的大规模合成数据集作者：Alexandra Antonova机构：Moscow Institute of Physics and Technology备注：Accepted to IEEE ASRU 2023链接：http://arxiv.org/pdf/2309.17267v1【4】 Low-Resource Self-Supervised Learning with SSL-Enhanced TTS标题：基于SSL增强型TTS的低资源自监督学习作者：Po-chun Hsu,Ali Elkahky,Wei-Ning Hsu,Yossi Adi,Tu Anh Nguyen,Jade Copet,Emmanuel Dupoux,Hung-yi Lee,Abdelrahman Mohamed机构：Graduate Institute of Communication Engineering, National Taiwan University, Apple, Meta AI, The Hebrew University of Jerusalem, Rembrand Inc.备注：Preprint链接：http://arxiv.org/pdf/2309.17020v1【5】 Synthetic Speech Detection Based on Temporal Consistency and Distribution of Speaker Features标题：基于说话人特征时间一致性和分布的合成语音检测作者：Yuxiang Zhang,Zhuo Li,Jingze Lu,Wenchao Wang,Pengyuan Zhang机构：Wenchao Wang and Pengyuan ZhangThe authors are with Key Laboratory of Speech Acoustics and ContentUnderstanding, Institute of Acoustics, China and also with University of Chinese Academy of Sciences备注：5 pages, 3 figures, 4 tables链接：http://arxiv.org/pdf/2309.16954v1【6】 Enhancing Code-switching Speech Recognition with Interactive Language Biases标题：利用交互语言偏向增强码型转换语音识别作者：Hexin Liu,Leibny Paola Garcia,Xiangyu Zhang,Andy W. H. Khong,Sanjeev Khudanpur机构：School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, CLSP and HLT-COE, Johns Hopkins University, USA, University of New South Wales, Australia备注：Submitted to IEEE ICASSP 2024链接：http://arxiv.org/pdf/2309.16953v1【7】 Towards High Resolution Weather Monitoring with Sound Data标题：利用声学数据进行高分辨率天气监测作者：Enis Berk Çoban,Megan Perra,Michael I. Mandel机构：Michael I Mandel, The Graduate Center, CUNY, New York, NY, USA, Environmental Biology, SUNY-ESF, Syracuse, NY, USA备注：5 pages, submitted to ICASSP 2024链接：http://arxiv.org/pdf/2309.16867v1
【8】 AV-CPL: Continuous Pseudo-Labeling for Audio-Visual Speech Recognition标题：连续伪标记法在视听语音识别中的应用作者：Andrew Rouditchenko,Ronan Collobert,Tatiana Likhomanenko机构：MIT, Apple备注：Under review链接：http://arxiv.org/pdf/2309.17395v1【9】 Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Supervision, and LLM Mix-up Augmentation标题：利用细粒度音频特征、文本嵌入监督和LLM混合增强改进音频字幕模型作者：Shih-Lun Wu,Xuankai Chang,Gordon Wichern,Jee-weon Jung,François Germain,Jonathan Le Roux,Shinji Watanabe机构：Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA, Mitsubishi Electric Research Labs (MERL), Cambridge, MA, USA备注：Preprint, under review at ICASSP 2024. Winner of the DCASE 2023 Challenge Task 6A: Automated Audio Captioning (AAC)链接：http://arxiv.org/pdf/2309.17352v1【10】 RTFS-Net: Recurrent time-frequency modelling for efficient audio-visual speech separation标题：RTFS-Net：高效视听语音分离的递归时频建模作者：Samuel Pegg,Kai Li,Xiaolin Hu机构：. Department of Computer Science and Technology, Institute for AI, BNRist, Tsinghua University, Beijing , China, . Tsinghua Laboratory of Brain and Intelligence (THBI), IDGMcGovern Institute for Brain Research, Tsinghua University, Beijing , China备注：17 pages, 4 figures链接：http://arxiv.org/pdf/2309.17189v1【11】 Style Transfer for Non-differentiable Audio Effects标题：不可区分音效的风格转换作者：Kieran Grant机构：University of Glasgow链接：http://arxiv.org/pdf/2309.17125v1【12】 ReFlow-TTS: A Rectified Flow Model for High-fidelity Text-to-Speech标题：Reflow-TTS：一种适用于高保真文语转换的纠错流模型作者：Wenhao Guan,Qi Su,Haodong Zhou,Shiyu Miao,Xingjia Xie,Lin Li,Qingyang Hong机构：School of Informatics, Xiamen University, China, School of Electronic Science and Engineering, Xiamen University, China备注：Submitted to ICASSP2024链接：http://arxiv.org/pdf/2309.17056v1【13】 SSHR: Leveraging Self-supervised Hierarchical Representations for Multilingual Automatic Speech Recognition标题：SSHR：利用自监督层次表示进行多语言自动语音识别作者：Hongfei Xue,Qijie Shao,Kaixun Huang,Peikun Chen,Lei Xie,Jie Liu机构：Northwestern Polytechnical University, Xian, China, Huawei Cloud备注：5 pages, 2 figures链接：http://arxiv.org/pdf/2309.16937v1
机器翻译，仅供参考