今日论文合集：cs.SD语音4篇，eess.AS音频处理4篇。
cs.SD语音
【1】 Mel-Band RoFormer for Music Source Separation标题：用于音乐源分离的Mel-Band RoFormer作者：Ju-Chiang Wang,Wei-Tsung Lu,Minz Won机构：Speech, Audio, and Music Intelligence (SAMI), ByteDance备注：submitted as an ISMIR 2023 late-breaking and demo paper链接：http://arxiv.org/pdf/2310.01809v1
【2】 Audio-visual child-adult speaker classification in dyadic interactions标题：二元交互中的视听儿童-成人说话人分类作者：Anfeng Xu,Kevin Huang,Tiantian Feng,Helen Tager-Flusberg,Shrikanth Narayanan机构：⋆ University of Southern California, Los Angeles, CA, USA, † Boston University, Boston, MA, USA备注：In review for ICASSP 2024, 5 pages链接：http://arxiv.org/pdf/2310.01867v1
【3】 Preserving Phonemic Distinctions for Ordinal Regression: A Novel Loss Function for Automatic Pronunciation Assessment标题：有序回归保留音位差异：一种新的发音自动评估损失函数作者：Bi-Cheng Yan,Hsin-Wei Wang,Yi-Cheng Wang,Jiun-Ting Li,Chi-Han Lin,Berlin Chen机构：National Taiwan Normal University, Taipei, Taiwan, E.SUN Financial Holding Co., Ltd., Taipei, Taiwan备注：Submitted to ASRU 2023链接：http://arxiv.org/pdf/2310.01839v1【4】 One model to rule them all ? Towards End-to-End Joint Speaker Diarization and Speech Recognition标题：一个模特就能统治所有人？面向端到端联合说话人二值化和语音识别作者：Samuele Cornell,Jee-weon Jung,Shinji Watanabe,Stefano Squartini机构：Italy ,Carnegie Mellon University, USA链接：http://arxiv.org/pdf/2310.01688v1
eess.AS音频处理
【1】 Audio-visual child-adult speaker classification in dyadic interactions标题：二元交互中的视听儿童-成人说话人分类作者：Anfeng Xu,Kevin Huang,Tiantian Feng,Helen Tager-Flusberg,Shrikanth Narayanan机构：⋆ University of Southern California, Los Angeles, CA, USA, † Boston University, Boston, MA, USA备注：In review for ICASSP 2024, 5 pages链接：http://arxiv.org/pdf/2310.01867v1
【2】 Preserving Phonemic Distinctions for Ordinal Regression: A Novel Loss Function for Automatic Pronunciation Assessment标题：有序回归保留音位差异：一种新的发音自动评估损失函数作者：Bi-Cheng Yan,Hsin-Wei Wang,Yi-Cheng Wang,Jiun-Ting Li,Chi-Han Lin,Berlin Chen机构：National Taiwan Normal University, Taipei, Taiwan, E.SUN Financial Holding Co., Ltd., Taipei, Taiwan备注：Submitted to ASRU 2023链接：http://arxiv.org/pdf/2310.01839v1
【3】 One model to rule them all ? Towards End-to-End Joint Speaker Diarization and Speech Recognition标题：一个模特就能统治所有人？面向端到端联合说话人二值化和语音识别作者：Samuele Cornell,Jee-weon Jung,Shinji Watanabe,Stefano Squartini机构：Italy ,Carnegie Mellon University, USA链接：http://arxiv.org/pdf/2310.01688v1【4】 Mel-Band RoFormer for Music Source Separation标题：用于音乐源分离的Mel-Band RoFormer作者：Ju-Chiang Wang,Wei-Tsung Lu,Minz Won机构：Speech, Audio, and Music Intelligence (SAMI), ByteDance备注：submitted as an ISMIR 2023 late-breaking and demo paper链接：http://arxiv.org/pdf/2310.01809v1
机器翻译，仅供参考