语音/音频处理学术速递[6.30]

今日论文合集：cs.SD语音10篇，eess.AS音频处理11篇。

cs.SD语音

【1】 LyricWhiz: Robust Multilingual Zero-shot Lyrics Transcription by Whispering to ChatGPT标题：LyricWhiz：通过Whispering to ChatGPT进行健壮的多语言零命中率歌词转录链接：https://arxiv.org/abs/2306.17103

作者：Le Zhuo,Ruibin Yuan,Jiahao Pan,Yinghao Ma,Yizhi LI,Ge Zhang,Si Liu,Roger Dannenberg,Jie Fu,Chenghua Lin,Emmanouil Benetos,Wenhu Chen,Wei Xue,Yike Guo机构：Beihang University, Beijing Academy of Artificial Intelligence, Carnegie Mellon University, Hong Kong University of Science and Technology, Queen Mary University of London, University of Sheffield, University of Waterloo备注：9 pages, 2 figures, 5 tables, accepted by ISMIR 2023

【2】 On the relevance of acoustic measurements for creating realistic virtual acoustic environments标题：论声学测量与创建逼真虚拟声学环境的相关性链接：https://arxiv.org/abs/2306.16967

作者：Siegfried Gündert,Stephan D. Ewert,Steven van de Par备注：This work has been submitted to the I3DA 2023 International Conference (IEEE Xplore Digital Library) for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible

【3】 Speech-based Age and Gender Prediction with Transformers标题：基于语音的Transformer年龄和性别预测链接：https://arxiv.org/abs/2306.16962

作者：Felix Burkhardt,Johannes Wagner,Hagen Wierstorf,Florian Eyben,Björn Schuller机构：audEERING GmbH, Germany, Chair EIHW, University of Augsburg, Germany, GLAM, Imperial College London, UK备注：5 pages, submitted to 15th ITG Conference on Speech Communication

【4】 Predicting Music Hierarchies with a Graph-Based Neural Decoder标题：基于图的神经解码器预测音乐层级链接：https://arxiv.org/abs/2306.16955

作者：Francesco Foscarin,Daniel Harasim,Gerhard Widmer机构：Institute of Computational Perception, Johannes Kepler University Linz, Austria, Independent Researcher备注：To be published in the Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)

【5】 Leveraging Cross-Utterance Context For ASR Decoding标题：利用交叉话语语境进行ASR解码链接：https://arxiv.org/abs/2306.16903

作者：Robert Flynn,Anton Ragni机构：Department of Computer Science, University of Sheffield, Portobello, Sheffield S,DP, UK

【6】 Transfer Learning with Semi-Supervised Dataset Annotation for Birdcall Classification标题：基于半监督数据集标注的迁移学习用于鸟鸣分类链接：https://arxiv.org/abs/2306.16760

作者：Anthony Miyaguchi,Nathan Zhong,Murilo Gustineli,Chris Hayduk机构：Georgia Institute of Technology, North Ave NW, Atlanta, GA备注：BirdCLEF working note submission to Multimedia Retrieval in Nature (LifeCLEF) for CLEF 2023

【7】 Automatic Speech Recognition of Non-Native Child Speech for Language Learning Applications标题：用于语言学习的非母语儿童语音的自动语音识别链接：https://arxiv.org/abs/2306.16710

作者：Simone Wills,Yu Bai,Cristian Tejedor-Garcia,Catia Cucchiarini,Helmer Strik机构：Radboud University Nijmegen, The Netherlands, NovoLearning, The Netherlands, Cristian Tejedor-García �备注：None

【8】 Evaluation of Virtual Acoustic Environments with Different Acoustic Level of Detail标题：不同细节声级的虚拟声环境评价链接：https://arxiv.org/abs/2306.17012

作者：Stefan Fichna,Steven van de Par,Stephan D. Ewert备注：This work has been submitted to the I3DA 2023 International Conference on Immersive and 3D Audio for possible publication

【9】 High-Quality Automatic Voice Over with Accurate Alignment: Supervision through Self-Supervised Discrete Speech Units标题：精确对齐的高质量自动画外音：通过自我监控的离散语音单元进行监控链接：https://arxiv.org/abs/2306.17005

作者：Junchen Lu,Berrak Sisman,Mingyang Zhang,Haizhou Li机构：National University of Singapore, Singapore, The University of Texas at Dallas, USA, Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China备注：Accepted to INTERSPEECH 2023

【10】 Computationally-efficient and perceptually-motivated rendering of diffuse reflections in room acoustics simulation标题：室内声学模拟中漫射反射的计算效率和感知激励绘制链接：https://arxiv.org/abs/2306.16696

作者：Stephan D. Ewert,Nico Gößling,Oliver Buttler,Steven van de Par,Hongmei Hu机构：Medizinische Physik und Akustik and Cluster of Excellence Hearing,all, Universität Oldenburg, Oldenburg, Germany备注：This work has been submitted to Forum Acusticum 2023 for publication

eess.AS音频处理

【1】 Evaluation of Virtual Acoustic Environments with Different Acoustic Level of Detail标题：不同细节声级的虚拟声环境评价链接：https://arxiv.org/abs/2306.17012

作者：Stefan Fichna,Steven van de Par,Stephan D. Ewert备注：This work has been submitted to the I3DA 2023 International Conference on Immersive and 3D Audio for possible publication

【2】 High-Quality Automatic Voice Over with Accurate Alignment: Supervision through Self-Supervised Discrete Speech Units标题：精确对齐的高质量自动画外音：通过自我监控的离散语音单元进行监控链接：https://arxiv.org/abs/2306.17005

【3】 Deep Learning-based F0 Synthesis for Speaker Anonymization标题：基于深度学习的F0合成说话人匿名化链接：https://arxiv.org/abs/2306.16860

作者：Ünal Ege Gaznepoglu,Nils Peters机构：International Audio Laboratories, Friedrich-Alexander-Universit¨at, Am Wolfsmantel , Erlangen, Germany备注：5 pages, 4 figures, 6 tables, accepted to EUSIPCO 2023

【4】 Computationally-efficient and perceptually-motivated rendering of diffuse reflections in room acoustics simulation标题：室内声学模拟中漫射反射的计算效率和感知激励绘制链接：https://arxiv.org/abs/2306.16696

【5】 LyricWhiz: Robust Multilingual Zero-shot Lyrics Transcription by Whispering to ChatGPT标题：LyricWhiz：通过Whispering to ChatGPT进行健壮的多语言零命中率歌词转录链接：https://arxiv.org/abs/2306.17103

【6】 On the relevance of acoustic measurements for creating realistic virtual acoustic environments标题：论声学测量与创建逼真虚拟声学环境的相关性链接：https://arxiv.org/abs/2306.16967

【7】 Speech-based Age and Gender Prediction with Transformers标题：基于语音的Transformer年龄和性别预测链接：https://arxiv.org/abs/2306.16962

【8】 Predicting Music Hierarchies with a Graph-Based Neural Decoder标题：基于图的神经解码器预测音乐层级链接：https://arxiv.org/abs/2306.16955

【9】 Leveraging Cross-Utterance Context For ASR Decoding标题：利用交叉话语语境进行ASR解码链接：https://arxiv.org/abs/2306.16903

作者：Robert Flynn,Anton Ragni机构：Department of Computer Science, University of Sheffield, Portobello, Sheffield S,DP, UK

【10】 Transfer Learning with Semi-Supervised Dataset Annotation for Birdcall Classification标题：基于半监督数据集标注的迁移学习用于鸟鸣分类链接：https://arxiv.org/abs/2306.16760

【11】 Automatic Speech Recognition of Non-Native Child Speech for Language Learning Applications标题：用于语言学习的非母语儿童语音的自动语音识别链接：https://arxiv.org/abs/2306.16710

机器翻译，仅供参考

语音/音频处理学术速递[6.30]

评论 0