语音/音频处理学术速递[6.16]

今日论文合集：cs.SD语音31篇，eess.AS音频处理36篇。

cs.SD语音

【1】 Few-shot bioacoustic event detection at the DCASE 2023 challenge标题：DCASE 2023挑战赛的少发生物声事件探测链接：https://arxiv.org/abs/2306.09223

作者：Ines Nolasco,Burooj Ghani,Shubhr Singh,Ester Vidaña-Vila,Helen Whitehead,Emily Grout,Michael Emmerson,Frants Jensen,Ivan Kiskin,Joe Morford,Ariana Strandburg-Peshkin,Lisa Gill,Hanna Pamuła,Vincent Lostanlen,Dan Stowell机构： Queen Mary University of London, Syracuse University, USA9 Institute for People-Centred AI, University of Surrey备注：submitted to DCASE 2023 workshop

【2】 STARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events标题：STARSS23：一个具有声音事件时空标注的真实场景空间记录视听数据集链接：https://arxiv.org/abs/2306.09126

作者：Kazuki Shimada,Archontis Politis,Parthasaarathy Sudarsanam,Daniel Krause,Kengo Uchida,Sharath Adavanne,Aapo Hakala,Yuichiro Koyama,Naoya Takahashi,Shusuke Takahashi,Tuomas Virtanen,Yuki Mitsufuji机构：Tampere University, Sony Research, Sony Group Corporation备注：25 pages, 8 figures

【3】 Audio Tagging on an Embedded Hardware Platform标题：嵌入式硬件平台上的音频标记链接：https://arxiv.org/abs/2306.09106

作者：Gabriel Bibbo,Arshdeep Singh,Mark D. Plumbley机构：Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK备注：Submitted to DCASE 2023 Workshop

【4】 CoverHunter: Cover Song Identification with Refined Attention and Alignments标题：CoverHunter：用精致的注意力和排列来掩饰歌曲识别链接：https://arxiv.org/abs/2306.09025

作者：Feng Liu,Deyi Tuo,Yinan Xu,Xintong Han机构：Intelligent Media Technology Department, Huya Inc, GuangZhou, China备注：6 pages, 3 figures

【5】 Team AcieLee: Technical Report for EPIC-SOUNDS Audio-Based Interaction Recognition Challenge 2023标题：AcieLee团队：基于史诗声音的交互识别挑战赛2023的技术报告链接：https://arxiv.org/abs/2306.08998

作者：Yuqi Li,Yizhi Luo,Xiaoshuai Hao,Chuanguang Yang,Zhulin An,Dantong Song,Wei Yi机构：College of Computer and Information Science College of Software, Southwest University, Chongqing, China, Samsung Research China-Beijing(SRC-B), Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China

【6】 Multi-Loss Convolutional Network with Time-Frequency Attention for Speech Enhancement标题：具有时频关注的多损耗卷积网络语音增强链接：https://arxiv.org/abs/2306.08956

作者：Liang Wan,Hongqing Liu,Yi Zhou,Jie Ji机构：School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China, vivo Mobile Commun co Ltd

【7】 Pushing the Limits of Unsupervised Unit Discovery for SSL Speech Representation标题：突破无监督单元发现的极限用于SSL语音表示链接：https://arxiv.org/abs/2306.08920

作者：Ziyang Ma,Zhisheng Zheng,Guanrou Yang,Yu Wang,Chao Zhang,Xie Chen机构：Shanghai Jiao Tong University, Shanghai, China, Shanghai AI Laboratory, Shanghai, China, Tsinghua University, Beijing, China备注：Accepted to Interspeech 2023

【8】 Exploring Isolated Musical Notes as Pre-training Data for Predominant Instrument Recognition in Polyphonic Music标题：探索孤立的音符作为复调音乐中主要乐器识别的预训练数据链接：https://arxiv.org/abs/2306.08850

作者：Lifan Zhong,Erica Cooper,Junichi Yamagishi,Nobuaki Minematsu机构：∗ Graduate School of Engineering, The University of Tokyo, Japan, † National Institute of Informatics, Japan备注：Submitted to APSIPA 2023

【9】 Unsupervised speech intelligibility assessment with utterance level alignment distance between teacher and learner Wav2Vec-2.0 representations标题：基于Wav2Vec-2.0表征的非监督语音清晰度评价链接：https://arxiv.org/abs/2306.08845

作者：Nayan Anand,Meenakshi Sirigiraju,Chiranjeevi Yarra机构：Speech Lab, Language Technologies Research Center (LTRC), IIIT, Hyderabad, India

【10】 When to Use Efficient Self Attention? Profiling Text, Speech and Image Transformer Variants标题：什么时候使用有效的自我注意？分析文本、语音和图像转换器变体链接：https://arxiv.org/abs/2306.08667

作者：Anuj Diwan,Eunsol Choi,David Harwath机构：Department of Computer Science, The University of Texas at Austin备注：10 pages, 6 pages. Accepted to ACL 2023

【11】 Anticipatory Music Transformer标题：期待中的音乐Transformer链接：https://arxiv.org/abs/2306.08620

作者：John Thickstun,David Hall,Chris Donahue,Percy Liang机构：Stanford University, Google DeepMind备注：33 pages, 6 figures

【12】 Improving Code-Switching and Named Entity Recognition in ASR with Speech Editing based Data Augmentation标题：基于语音编辑的数据增强改进ASR中的代码切换和命名实体识别链接：https://arxiv.org/abs/2306.08588

作者：Zheng Liang,Zheshu Song,Ziyang Ma,Chenpeng Du,Kai Yu,Xie Chen机构：MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China备注：Accepted by Interspeech 2023

【13】 Tagged End-to-End Simultaneous Speech Translation Training using Simultaneous Interpretation Data标题：使用同声传译数据的标记端到端同声翻译训练链接：https://arxiv.org/abs/2306.08582

作者：Yuka Ko,Ryo Fukuda,Yuta Nishikawa,Yasumasa Kano,Katsuhito Sudoh,Satoshi Nakamura机构：Nara Institute of Science and Technology备注：Accepted to IWSLT2023 scientific paper

【14】 Learning Cross-lingual Mappings for Data Augmentation to Improve Low-Resource Speech Recognition标题：学习用于数据增强的跨语言映射以改进低资源语音识别链接：https://arxiv.org/abs/2306.08577

作者：Muhammad Umar Farooq,Thomas Hain机构：Speech and Hearing Research Group, University of Sheffield, UK.备注：Accepted for Interspeech 2023

【15】 ITALIC: An Italian Intent Classification Dataset标题：斜体：意大利意向分类数据集链接：https://arxiv.org/abs/2306.08502

作者：Alkis Koudounas,Moreno La Quatra,Lorenzo Vaiani,Luca Colomba,Giuseppe Attanasio,Eliana Pastor,Luca Cagliero,Elena Baralis机构：♢Politecnico di Torino, Turin, Italy, ♣Kore University of Enna, Enna, Italy, ♡Bocconi University, Milan, Italy备注：Accepted at INTERSPEECH 2023. Data and code at this https URL

【16】 Combining piano performance dimensions for score difficulty classification标题：结合钢琴演奏维度进行乐谱难度分类链接：https://arxiv.org/abs/2306.08480

作者：Pedro Ramoneda,Dasaem Jeong,Vsevolod Eremenko,Nazif Can Tamer,Marius Miron,Xavier Serra机构：Universitat Pompeu Fabra, Barcelona, Spain, Sogang University, Seoul, Republic of Korea备注：36 pages

【17】 Gesper: A Restoration-Enhancement Framework for General Speech Reconstruction标题：Gesper：一种通用语音重建的恢复增强框架链接：https://arxiv.org/abs/2306.08454

作者：Wenzhe Liu,Yupeng Shi,Jun Chen,Wei Rao,Shulin He,Andong Li,Yannan Wang,Zhiyong Wu机构：Tencent Ethereal Audio Lab, Tencent, Shenzhen, China, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China备注：Accepted by InterSpeech 2023

【18】 SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?标题：SpeechGLUE：自我监督的语音模型能多好地捕捉语言知识？链接：https://arxiv.org/abs/2306.08374

作者：Takanori Ashihara,Takafumi Moriya,Kohei Matsuura,Tomohiro Tanaka,Yusuke Ijima,Taichi Asami,Marc Delcroix,Yukinori Honma机构：NTT Corporation, Japan备注：Accepted at INTERSPEECH 2023

【19】 Research on an improved Conformer end-to-end Speech Recognition Model with R-Drop Structure标题：一种改进的R-Drop结构整形端到端语音识别模型研究链接：https://arxiv.org/abs/2306.08329

作者：Weidong Ji,Shijie Zan,Guohui Zhou,Xu Wang机构： College of Computer Information Engineering, Harbin Normal University, Harbin, China备注：15 pages, 9 figures

【20】 A Novel Scheme to classify Read and Spontaneous Speech标题：一种新的朗读和自发语音分类方案链接：https://arxiv.org/abs/2306.08012

作者：Sunil Kumar Kopparapu机构：TCS Research, India备注：14 pages, 8 figures

【21】 Domain Information Control at Inference Time for Acoustic Scene Classification标题：声场分类推理时的域信息控制链接：https://arxiv.org/abs/2306.08010

作者：Shahed Masoudian,Khaled Koutini,Markus Schedl,Gerhard Widmer,Navid Rekabsaz机构：Johannes Kepler University Linz, Institute of Computational Perception, Linz Institute of Technology (LIT), AI Lab, Austria

【22】 Time-Domain Wideband ISM for Spherical Microphone Arrays标题：球面传声器阵列的时域宽带ISM链接：https://arxiv.org/abs/2306.09135

作者：Jiarui Wang,Prasanga Samarasinghe,Thushara Abhayapala,Jihui Aimee Zhang机构：∗The Australian National University, †University of Southampton备注：Submitted to the IEEE 25th International Workshop on Multimedia Signal Processing (IEEE MMSP 2023)

【23】 Multichannel Active Noise Control with Exterior Radiation Suppression Based on Riemannian Optimization标题：基于黎曼优化的外辐射抑制多通道有源噪声控制链接：https://arxiv.org/abs/2306.08855

作者：Takaaki Kojima,Kazuyuki Arikawa,Shoichi Koyama,Hiroshi Saruwatari机构：The University of Tokyo, Tokyo, Japan, Graduate School of Information Science and Technology, Digital Content and Media Sciences Research Division, National Institute of Informatics备注：Accepted to European Signal Processing Conference (EUSIPCO) 2023

【24】 Towards training Bilingual and Code-Switched Speech Recognition models from Monolingual data sources标题：从单语数据源训练双语和码切换语音识别模型链接：https://arxiv.org/abs/2306.08753

作者：Kunal Dhawan,Dima Rekesh,Boris Ginsburg机构：NVIDIA, USA

【25】 Variance-Preserving-Based Interpolation Diffusion Models for Speech Enhancement标题：基于保方差的语音增强内插扩散模型链接：https://arxiv.org/abs/2306.08527

作者：Zilu Guo,Jun Du,Chin-Hui Lee,Yu Gao,Wenbin Zhang机构：University of Science and Technology of China, Hefei , China, Georgia Institute of Technology, Atlanta, GA. ,-, USA, AI Innovation Center, Midea Group (Shanghai) Co.,Ltd., Shanghai , China

【26】 Permutation Invariant Recurrent Neural Networks for Sound Source Tracking Applications标题：置换不变递归神经网络在声源跟踪中的应用链接：https://arxiv.org/abs/2306.08510

作者：David Diaz-Guerra,Archontis Politis,Antonio Miguel,Jose R. Beltran,Tuomas Virtanen机构： Audio Research Group, Tampere University, Finland, Department of Electronic Engineering and Communications, University of Zaragoza, Spain备注：Accepted for publication at Forum Acusticum 2023

【27】 BRUDEX Database: Binaural Room Impulse Responses with Uniformly Distributed External Microphones标题：BRUDEX数据库：均匀分布外部麦克风的双耳室内脉冲响应链接：https://arxiv.org/abs/2306.08484

作者：Daniel Fejgin,Wiebke Middelberg,Simon Doclo机构：University of Oldenburg, Department of Medical Physics and Acoustics and Cluster of Excellence Hearing,all, Oldenburg, Germany, Web: www.sigproc.uni-oldenburg.de备注：Submitted to ITG 2023

【28】 Feature Normalization for Fine-tuning Self-Supervised Models in Speech Enhancement标题：语音增强中精调自监督模型的特征归一化链接：https://arxiv.org/abs/2306.08406

作者：Hejung Yang,Hong-Goo Kang机构：Dept. of Electrical and Electronic Engineering, Yonsei University, South Korea备注：INTERSPEECH 2023 accepted

【29】 DCTX-Conformer: Dynamic context carry-over for low latency unified streaming and non-streaming Conformer标题：DCTX-Conform：低延迟统一流和非流Conformator的动态上下文结转链接：https://arxiv.org/abs/2306.08175

作者：Goeric Huybrechts,Srikanth Ronanki,Xilai Li,Hadis Nosrati,Sravan Bodapati,Katrin Kirchhoff机构：Kirchhoff, AWS AI Labs, USA, AWS AI Labs, Australia

【30】 Efficient Adapters for Giant Speech Models标题：适用于巨型语音模型的高效适配器链接：https://arxiv.org/abs/2306.08131

作者：Nanxin Chen,Izhak Shafran,Yu Zhang,Chung-Cheng Chiu,Hagen Soltau,James Qin,Yonghui Wu机构：Google DeepMind, USA

【31】 Evaluation of Spatial Distortion in Multichannel Audio标题：多声道音频的空间失真评估链接：https://arxiv.org/abs/2306.08053

作者：Karn N. Watcharasupat,Alexander Lerch机构： Georgia Institute ofTechnology备注：Submitted to IEEE Signal Processing Letters

eess.AS音频处理

【1】 Lexical Speaker Error Correction: Leveraging Language Models for Speaker Diarization Error Correction标题：词汇说话人纠错：利用语言模型进行说话人离散化纠错链接：https://arxiv.org/abs/2306.09313

作者：Rohit Paturi,Sundararajan Srinivasan,Xiang Li机构：AWS AI Labs备注：Accepted at INTERSPEECH 2023. arXiv admin note: text overlap with arXiv:1907.05337 by other authors

【2】 Time-Domain Wideband ISM for Spherical Microphone Arrays标题：球面传声器阵列的时域宽带ISM链接：https://arxiv.org/abs/2306.09135

【3】 Multichannel Active Noise Control with Exterior Radiation Suppression Based on Riemannian Optimization标题：基于黎曼优化的外辐射抑制多通道有源噪声控制链接：https://arxiv.org/abs/2306.08855

【4】 Towards training Bilingual and Code-Switched Speech Recognition models from Monolingual data sources标题：从单语数据源训练双语和码切换语音识别模型链接：https://arxiv.org/abs/2306.08753

作者：Kunal Dhawan,Dima Rekesh,Boris Ginsburg机构：NVIDIA, USA

【5】 Variance-Preserving-Based Interpolation Diffusion Models for Speech Enhancement标题：基于保方差的语音增强内插扩散模型链接：https://arxiv.org/abs/2306.08527

【6】 Low-Complexity Steered Response Power Mapping based on Low-Rank and Sparse Interpolation标题：基于低阶稀疏内插的低复杂度转向响应功率映射链接：https://arxiv.org/abs/2306.08514

作者：Thomas Dietzen,Enzo De Sena,Toon van Waterschoot机构： Enzo De Sena is withUniversity of Surrey, Institute of Sound Recording

【7】 Permutation Invariant Recurrent Neural Networks for Sound Source Tracking Applications标题：置换不变递归神经网络在声源跟踪中的应用链接：https://arxiv.org/abs/2306.08510

【8】 BRUDEX Database: Binaural Room Impulse Responses with Uniformly Distributed External Microphones标题：BRUDEX数据库：均匀分布外部麦克风的双耳室内脉冲响应链接：https://arxiv.org/abs/2306.08484

【9】 MCR-Data2vec 2.0: Improving Self-supervised Speech Pre-training via Model-level Consistency Regularization标题：MCR-Data2vec 2.0：通过模型级一致性正则化改进自监督语音预训练链接：https://arxiv.org/abs/2306.08463

作者：Ji Won Yoon,Seok Min Kim,Nam Soo Kim机构：Department of ECE and INMC, Seoul National University, Seoul, Republic of Korea备注：INTERSPEECH 2023

【10】 Feature Normalization for Fine-tuning Self-Supervised Models in Speech Enhancement标题：语音增强中精调自监督模型的特征归一化链接：https://arxiv.org/abs/2306.08406

作者：Hejung Yang,Hong-Goo Kang机构：Dept. of Electrical and Electronic Engineering, Yonsei University, South Korea备注：INTERSPEECH 2023 accepted

【11】 DCTX-Conformer: Dynamic context carry-over for low latency unified streaming and non-streaming Conformer标题：DCTX-Conform：低延迟统一流和非流Conformator的动态上下文结转链接：https://arxiv.org/abs/2306.08175

作者：Goeric Huybrechts,Srikanth Ronanki,Xilai Li,Hadis Nosrati,Sravan Bodapati,Katrin Kirchhoff机构：Kirchhoff, AWS AI Labs, USA, AWS AI Labs, Australia

【12】 Large-scale Language Model Rescoring on Long-form Data标题：基于长格式数据的大规模语言模型研究链接：https://arxiv.org/abs/2306.08133

作者：Tongzhou Chen,Cyril Allauzen,Yinghui Huang,Daniel Park,David Rybach,W. Ronny Huang,Rodrigo Cabrera,Kartik Audhkhasi,Bhuvana Ramabhadran,Pedro J. Moreno,Michael Riley机构：Google LLC, USA备注：None

【13】 Efficient Adapters for Giant Speech Models标题：适用于巨型语音模型的高效适配器链接：https://arxiv.org/abs/2306.08131

作者：Nanxin Chen,Izhak Shafran,Yu Zhang,Chung-Cheng Chiu,Hagen Soltau,James Qin,Yonghui Wu机构：Google DeepMind, USA

【14】 Evaluation of Spatial Distortion in Multichannel Audio标题：多声道音频的空间失真评估链接：https://arxiv.org/abs/2306.08053

作者：Karn N. Watcharasupat,Alexander Lerch机构： Georgia Institute ofTechnology备注：Submitted to IEEE Signal Processing Letters

【15】 Cognitive performance in open-plan office acoustic simulations: Effects of room acoustics and semantics but not spatial separation of sound sources标题：开放式办公室声学模拟中的认知表现：房间声学和语义的影响，而不是声源的空间分离链接：https://arxiv.org/abs/2306.08051

作者：Manuj Yadav,Markus Georgi,Larissa Leist,Maria Klatte,Sabine J. Schlittmeier,Janina Fels机构： Institute of Hearing Technology and Acoustics, RWTH Aachen University, Germany, Institute for Psychology, RWTH Aachen University, Germany, Center for Cognitive and Developmental Psychology, RPTU Kaiserslautern-Landau, Germany

【16】 Few-shot bioacoustic event detection at the DCASE 2023 challenge标题：DCASE 2023挑战赛的少发生物声事件探测链接：https://arxiv.org/abs/2306.09223

【17】 STARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events标题：STARSS23：一个具有声音事件时空标注的真实场景空间记录视听数据集链接：https://arxiv.org/abs/2306.09126

【18】 Audio Tagging on an Embedded Hardware Platform标题：嵌入式硬件平台上的音频标记链接：https://arxiv.org/abs/2306.09106

作者：Gabriel Bibbo,Arshdeep Singh,Mark D. Plumbley机构：Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK备注：Submitted to DCASE 2023 Workshop

【19】 CoverHunter: Cover Song Identification with Refined Attention and Alignments标题：CoverHunter：用精致的注意力和排列来掩饰歌曲识别链接：https://arxiv.org/abs/2306.09025

作者：Feng Liu,Deyi Tuo,Yinan Xu,Xintong Han机构：Intelligent Media Technology Department, Huya Inc, GuangZhou, China备注：6 pages, 3 figures

【20】 Team AcieLee: Technical Report for EPIC-SOUNDS Audio-Based Interaction Recognition Challenge 2023标题：AcieLee团队：基于史诗声音的交互识别挑战赛2023的技术报告链接：https://arxiv.org/abs/2306.08998

【21】 Multi-Loss Convolutional Network with Time-Frequency Attention for Speech Enhancement标题：具有时频关注的多损耗卷积网络语音增强链接：https://arxiv.org/abs/2306.08956

【22】 Pushing the Limits of Unsupervised Unit Discovery for SSL Speech Representation标题：突破无监督单元发现的极限用于SSL语音表示链接：https://arxiv.org/abs/2306.08920

【23】 Exploring Isolated Musical Notes as Pre-training Data for Predominant Instrument Recognition in Polyphonic Music标题：探索孤立的音符作为复调音乐中主要乐器识别的预训练数据链接：https://arxiv.org/abs/2306.08850

【24】 Unsupervised speech intelligibility assessment with utterance level alignment distance between teacher and learner Wav2Vec-2.0 representations标题：基于Wav2Vec-2.0表征的非监督语音清晰度评价链接：https://arxiv.org/abs/2306.08845

作者：Nayan Anand,Meenakshi Sirigiraju,Chiranjeevi Yarra机构：Speech Lab, Language Technologies Research Center (LTRC), IIIT, Hyderabad, India

【25】 When to Use Efficient Self Attention? Profiling Text, Speech and Image Transformer Variants标题：什么时候使用有效的自我注意？分析文本、语音和图像转换器变体链接：https://arxiv.org/abs/2306.08667

作者：Anuj Diwan,Eunsol Choi,David Harwath机构：Department of Computer Science, The University of Texas at Austin备注：10 pages, 6 pages. Accepted to ACL 2023

【26】 Anticipatory Music Transformer标题：期待中的音乐Transformer链接：https://arxiv.org/abs/2306.08620

作者：John Thickstun,David Hall,Chris Donahue,Percy Liang机构：Stanford University, Google DeepMind备注：33 pages, 6 figures

【27】 Improving Code-Switching and Named Entity Recognition in ASR with Speech Editing based Data Augmentation标题：基于语音编辑的数据增强改进ASR中的代码切换和命名实体识别链接：https://arxiv.org/abs/2306.08588

【28】 Tagged End-to-End Simultaneous Speech Translation Training using Simultaneous Interpretation Data标题：使用同声传译数据的标记端到端同声翻译训练链接：https://arxiv.org/abs/2306.08582

作者：Yuka Ko,Ryo Fukuda,Yuta Nishikawa,Yasumasa Kano,Katsuhito Sudoh,Satoshi Nakamura机构：Nara Institute of Science and Technology备注：Accepted to IWSLT2023 scientific paper

【29】 Learning Cross-lingual Mappings for Data Augmentation to Improve Low-Resource Speech Recognition标题：学习用于数据增强的跨语言映射以改进低资源语音识别链接：https://arxiv.org/abs/2306.08577

作者：Muhammad Umar Farooq,Thomas Hain机构：Speech and Hearing Research Group, University of Sheffield, UK.备注：Accepted for Interspeech 2023

【30】 ITALIC: An Italian Intent Classification Dataset标题：斜体：意大利意向分类数据集链接：https://arxiv.org/abs/2306.08502

【31】 Combining piano performance dimensions for score difficulty classification标题：结合钢琴演奏维度进行乐谱难度分类链接：https://arxiv.org/abs/2306.08480

【32】 Gesper: A Restoration-Enhancement Framework for General Speech Reconstruction标题：Gesper：一种通用语音重建的恢复增强框架链接：https://arxiv.org/abs/2306.08454

【33】 SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?标题：SpeechGLUE：自我监督的语音模型能多好地捕捉语言知识？链接：https://arxiv.org/abs/2306.08374

作者：Takanori Ashihara,Takafumi Moriya,Kohei Matsuura,Tomohiro Tanaka,Yusuke Ijima,Taichi Asami,Marc Delcroix,Yukinori Honma机构：NTT Corporation, Japan备注：Accepted at INTERSPEECH 2023

【34】 Research on an improved Conformer end-to-end Speech Recognition Model with R-Drop Structure标题：一种改进的R-Drop结构整形端到端语音识别模型研究链接：https://arxiv.org/abs/2306.08329

作者：Weidong Ji,Shijie Zan,Guohui Zhou,Xu Wang机构： College of Computer Information Engineering, Harbin Normal University, Harbin, China备注：15 pages, 9 figures

【35】 A Novel Scheme to classify Read and Spontaneous Speech标题：一种新的朗读和自发语音分类方案链接：https://arxiv.org/abs/2306.08012

作者：Sunil Kumar Kopparapu机构：TCS Research, India备注：14 pages, 8 figures

【36】 Domain Information Control at Inference Time for Acoustic Scene Classification标题：声场分类推理时的域信息控制链接：https://arxiv.org/abs/2306.08010

机器翻译，仅供参考

语音/音频处理学术速递[6.16]

评论 0