今日论文合集：cs.SD语音21篇，eess.AS音频处理39篇。cs.SD语音【1】 N-Shot Benchmarking of Whisper on Diverse Arabic Speech Recognition标题：不同阿拉伯语语音识别中密语的N-shot基准链接：https://arxiv.org/abs/2306.02902作者：Bashar Talafha,Abdul Waheed,Muhammad Abdul-Mageed机构：The University of British Columbia, Canada, Mohamed bin Zayed University of Artificial Intelligence, UAE备注：4 pages, INTERSPEECH 2023【2】 Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding标题：视频骆驼：一种面向视频理解的教学调谐视听语言模型链接：https://arxiv.org/abs/2306.02858作者：Hang Zhang,Xin Li,Lidong Bing机构：DAMO Academy, Alibaba Group备注：Technical Report【3】 The Learning Prescription, A Neural Network Hearing Aid Core标题：学习处方--神经网络助听器的核心链接：https://arxiv.org/abs/2306.02750作者：Matt R. Flax备注：this https URL【4】 Multiple output samples for each input in a single-output Gaussian process标题：单输出高斯过程中每个输入的多个输出样本链接：https://arxiv.org/abs/2306.02719作者：Jeremy H. M. Wong,Huayun Zhang,Nancy F. Chen机构：Institute for Infocomm Research (I,R), A⋆STAR, Singapore【5】 BeAts: Bengali Speech Acts Recognition using Multimodal Attention Fusion标题：Beats：基于多模式注意力融合的孟加拉语音行为识别链接：https://arxiv.org/abs/2306.02680作者：Ahana Deb,Sayan Nag,Ayan Mahapatra,Soumitri Chattopadhyay,Aritra Marik,Pijush Kanti Gayen,Shankha Sanyal,Archi Banerjee,Samir Karmakar机构：Jadavpur University, India, University of Toronto, Canada, IIT Kharagpur, India备注：Accepted at INTERSPEECH 2023【6】 Rethinking the visual cues in audio-visual speaker extraction标题：对视听说话人提取中视觉线索的再思考链接：https://arxiv.org/abs/2306.02625作者：Junjie Li,Meng Ge,Zexu pan,Rui Cao,Longbiao Wang,Jianwu Dang,Shiliang Zhang机构： Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China, Department of Electrical and Computer Engineering, National University of Singapore, Singapore备注：Accepted in Interspeech 2023【7】 Controllable Lyrics-to-Melody Generation标题：可控的歌词到旋律生成链接：https://arxiv.org/abs/2306.02613作者：Zhe Zhang,Yi Yu,Atsuhiro Takasu机构：Digital Content and Media Sciences Research Division, National Institute of Informatics, SOKENDAI, Tokyo, Japan【8】 Cross-Lingual Transfer Learning for Phrase Break Prediction with Multilingual Language Model标题：基于多语言模型的跨语言迁移学习词断预测链接：https://arxiv.org/abs/2306.02579作者：Hoyeon Lee,Hyun-Wook Yoon,Jong-Hwan Kim,Jae-Min Kim机构：NAVER Cloud, South Korea备注：Accepted by INTERSPEECH 2023【9】 Incorporating L2 Phonemes Using Articulatory Features for Robust Speech Recognition标题：利用节律特征结合二语音素进行稳健语音识别链接：https://arxiv.org/abs/2306.02534作者：Jisung Wang,Haram Lee,Myungwoo Oh机构：NAVER Cloud, South Korea备注：Accepted at INTERSPEECH 2023【10】 SpellMapper: A non-autoregressive neural spellchecker for ASR customization with candidate retrieval based on n-gram mappings标题：SpellMapper：用于ASR定制和基于n元语法映射的候选检索的非自回归神经拼写检查器链接：https://arxiv.org/abs/2306.02317作者：Alexandra Antonova,Evelina Bakhturina,Boris Ginsburg机构：NVIDIA, USA备注：Accepted by INTERSPEECH 2023【11】 End-to-End Joint Target and Non-Target Speakers ASR标题：端到端联合目标和非目标说话人ASR链接：https://arxiv.org/abs/2306.02273作者：Ryo Masumura,Naoki Makishima,Taiga Yamane,Yoshihiko Yamazaki,Saki Mizuno,Mana Ihori,Mihiro Uchida,Keita Suzuki,Hiroshi Sato,Tomohiro Tanaka,Akihiko Takashima,Satoshi Suzuki,Takafumi Moriya,Nobukatsu Hojo,Atsushi Ando机构：NTT Computer and Data Science Laboratories, NTT Corporation, Japan备注：Accepted at Interspeech 2023【12】 MAVD: The First Open Large-Scale Mandarin Audio-Visual Dataset with Depth Information标题：MAVD：第一个开放的具有深度信息的大规模普通话视听数据集链接：https://arxiv.org/abs/2306.02263作者：Jianrong Wang,Yuchen Huo,Li Liu,Tianyi Xu,Qi Li,Sen Li机构：College of Intelligence and Computing, Tianjin University, Tianjin, China, Tianjin International Engineering Institute, Tianjin University, Tianjin, China, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China【13】 Effects of Tonal Coarticulation and Prosodic Positions on Tonal Contours of Low Rising Tones: In the Case of Xiamen Dialect标题：声调协同清晰度和韵律位置对低上调声调轮廓的影响：以厦门方言为例链接：https://arxiv.org/abs/2306.02251作者：Yiying Hu,Hui Feng,Qinghua Zhao,Aijun Li机构：Tianjin University, China, Institute of linguistics, Chinese Academy of Social Sciences, China备注：To be published in InterSpeech 2023【14】 Acoustic Word Embeddings for Untranscribed Target Languages with Continued Pretraining and Learned Pooling标题：持续预训练和习得池的未转录目标语言的声学单词嵌入链接：https://arxiv.org/abs/2306.02153作者：Ramon Sanabria,Ondrej Klejch,Hao Tang,Sharon Goldwater机构：The University of Edinburgh备注：Accepted to Interspeech 2023【15】 Adapting Pretrained ASR Models to Low-resource Clinical Speech using Epistemic Uncertainty-based Data Selection标题：使用基于认知不确定性的数据选择使预先训练的ASR模型适应低资源的临床语音链接：https://arxiv.org/abs/2306.02105作者：Bonaventure F. P. Dossou,Atnafu Lambebo Tonja,Chris Chinenye Emezue,Tobi Olatunji,Naome A Etori,Salomey Osei,Tosin Adewumi,Sahib Singh机构：∗Masakhane NLP,Mila Quebec AI Institute, McGill University, Lelapa AI, Lanfrica, Instituto Politécnico Nacional,Technical University of Munich,Intron Health Inc,Georgia Institute of Technology【16】 BEDRF: Bidirectional Edge Diffraction Response Function for Interactive Sound Propagation标题：BEDRF：交互式声传播的双向边缘绕射响应函数链接：https://arxiv.org/abs/2306.01974作者：Chunxiao Cao,Zili An,Zhong Ren,Dinesh Manocha,Kun Zhou机构： State Key Laboratory of CAD&CG, Zhejiang UniversityZHONG REN, Zhejiang UniversityDINESH MANOCHA, Department of Computer Science, University of Maryland, Zhejiang UniversityWe introduce bidirectional edge diffraction response function (BEDRF)【17】 Can Contextual Biasing Remain Effective with Whisper and GPT-2?标题：语境偏见能在Whisper和GPT-2中保持有效吗？链接：https://arxiv.org/abs/2306.01942作者：Guangzhi Sun,Xianrui Zheng,Chao Zhang,Philip C. Woodland机构：University of Cambridge Department of Engineering, Trumpington St., Cambridge, CB,PZ U.K.备注：To appear in Interspeech 2023【18】 Discovering COVID-19 Coughing and Breathing Patterns from Unlabeled Data Using Contrastive Learning with Varying Pre-Training Domains标题：利用不同训练前领域的对比学习从未标记数据中发现新冠肺炎咳嗽和呼吸模式链接：https://arxiv.org/abs/2306.01864作者：Jinjin Cai,Sudip Vhaduri,Xiao Luo机构：Comp & Info Tech Dept, Purdue University, West Lafayette, IN , USA, Comp & Info Tech Dept, IUPUI, Indianapolis, IN , USA备注：None【19】 Multi-View Multi-Task Representation Learning for Mispronunciation Detection标题：用于错误发音检测的多视点多任务表征学习链接：https://arxiv.org/abs/2306.01845作者：Yassine El Kheir,Shammur Absar Chowdhury,Ahmed Ali机构：Qatar Computing Research Institute, HBKU, Doha, Qatar备注：5 pages【20】 Edit Distance based RL for RNNT decoding标题：基于编辑距离的RNNT解码RL链接：https://arxiv.org/abs/2306.01789作者：Dongseong Hwang,Changwan Ryu,Khe Chai Sim机构：Google, U.S.A备注：5 pages, 2 figures【21】 On the Behavior of Intrusive and Non-intrusive Speech Enhancement Metrics in Predictive and Generative Settings标题：预测性和生成性环境下侵入式和非侵入式语音增强指标的行为研究链接：https://arxiv.org/abs/2306.03014作者：Danilo de Oliveira,Julius Richter,Jean-Marie Lemercier,Tal Peer,Timo Gerkmann机构：Universität Hamburg, Hamburg, Germany备注：Submitted to ITG Conference on Speech Communicationeess.AS音频处理【1】 On the Behavior of Intrusive and Non-intrusive Speech Enhancement Metrics in Predictive and Generative Settings标题：预测性和生成性环境下侵入式和非侵入式语音增强指标的行为研究链接：https://arxiv.org/abs/2306.03014作者：Danilo de Oliveira,Julius Richter,Jean-Marie Lemercier,Tal Peer,Timo Gerkmann机构：Universität Hamburg, Hamburg, Germany备注：Submitted to ITG Conference on Speech Communication【2】 Simultaneous or Sequential Training? How Speech Representations Cooperate in a Multi-Task Self-Supervised Learning System标题：同步训练还是顺序训练？语音表征在多任务自监督学习系统中的协作链接：https://arxiv.org/abs/2306.02972作者：Khazar Khorrami,María Andrea Cruz Blandón,Tuomas Virtanen,Okko Räsänen机构：Unit of Computing Sciences, Tampere University, Tampere, Finland, nd Mar´ıa Andrea Cruz Bland´on, rd Okko R¨as¨anen备注：5 pages, accepted by EUSIPCO 2023【3】 Vocoder drift in x-vector-based speaker anonymization标题：基于x向量的说话人匿名化中的声码器漂移链接：https://arxiv.org/abs/2306.02892作者：Michele Panariello,Massimiliano Todisco,Nicholas Evans机构：EURECOM, Sophia Antipolis, France备注：Accepted at INTERSPEECH 2023【4】 EffCRN: An Efficient Convolutional Recurrent Network for High-Performance Speech Enhancement标题：EffCRN：一种用于高性能语音增强的高效卷积递归网络链接：https://arxiv.org/abs/2306.02778作者：Marvin Sach,Jan Franzen,Bruno Defraene,Kristoff Fluyt,Maximilian Strake,Wouter Tirry,Tim Fingscheidt机构：Technische Universit¨at Braunschweig, Institute for Communications Technology, Braunschweig, Germany, ◦Goodix Technology (Belgium) BV, Leuven, Belgium备注：5 pages, 5 figures, accepted for Interspeech 2023【5】 A Novel Interpretable and Generalizable Re-synchronization Model for Cued Speech based on a Multi-Cuer Corpus标题：一种新的基于多Cuer语料库的可解释、可推广的线索语音再同步模型链接：https://arxiv.org/abs/2306.02596作者：Lufei Gao,Shan Huang,Li Liu机构：Shenzhen Research Institute of Big Data, China, The Hong Kong University of Science and Technology (Guangzhou), China备注：5 pages, 4 figures, Accepted to INTERSPEECH2023【6】 Divided spectro-temporal attention for sound event localization and detection in real scenes for DCASE2023 challenge标题：DCASE2023挑战中真实场景声事件定位和检测的分离频谱-时间注意链接：https://arxiv.org/abs/2306.02591作者：Yusun Shul,Byeong-Yun Ko,Jung-Woo Choi机构：Korea Advanced Institute of Science and Technology, School of Electrical Engineering, Dept. of Mechanical Engineering, Yuseong-gu, Daejeon, Republic of Korea【7】 OTF: Optimal Transport based Fusion of Supervised and Self-Supervised Learning Models for Automatic Speech Recognition标题：OTF：基于最优传输的自动语音识别监督和自监督学习模型融合链接：https://arxiv.org/abs/2306.02541作者：Li Fu,Siqi Li,Qingtao Li,Fangzhu Li,Liping Deng,Lu Fan,Meng Chen,Youzheng Wu,Xiaodong He机构：JD AI Research, Beijing, China备注：Accepted by Interspeech 2023【8】 End-To-End Deep Learning-based Adaptation Control for Linear Acoustic Echo Cancellation标题：基于深度学习的端到端自适应线性声学回波抵消控制链接：https://arxiv.org/abs/2306.02450作者：Thomas Haubner,Andreas Brendel,Walter Kellermann机构： Friedrich-Alexander-Universit¨at Erlangen-N¨urnberg, He is now with theFraunhofer Institute for Integrated Circuits (IIS)备注：This article has been submitted to IEEE/ACM Transactions on Audio, Speech, and Language Processing【9】 SingNet: A Real-time Singing Voice Beat and Downbeat Tracking System标题：SingNet：一种实时的歌声节拍和弱拍跟踪系统链接：https://arxiv.org/abs/2306.02372作者：Mojtaba Heydari,Ju-Chiang Wang,Zhiyao Duan机构：† University of Rochester, Rochester, NY, USA, ⋆ TikTok, Mountain View, CA, USA备注：Accepted for 2023 International Conference on Acoustics, Speech, and Signal Processing (ICASSP-2023)【10】 Influence of Lossy Speech Codecs on Hearing-aid, Binaural Sound Source Localisation using DNNs标题：有损语音编解码器对助听器、双耳声源定位的影响链接：https://arxiv.org/abs/2306.02344作者：Siyuan Song,Stijn Kindt,Jasper Maes,Alexander Bohlender. Nilesh Madhu机构：IDLab, Department of Electronics and Information Systems, Ghent University - imec, Belgium【11】 SpeechGen: Unlocking the Generative Power of Speech Language Models with Prompts标题：SpeechGen：通过提示释放语音语言模型的生成能力链接：https://arxiv.org/abs/2306.02207作者：Haibin Wu,Kai-Wei Chang,Yuan-Kuei Wu,Hung-yi Lee机构：Graduate Institute of Communication Engineering, National Taiwan University备注：Work in progress. The first three authors contributed equally【12】 Low-Complexity Acoustic Scene Classification Using Data Augmentation and Lightweight ResNet标题：基于数据增强和轻量级ResNet的低复杂度声场景分类链接：https://arxiv.org/abs/2306.02054作者：Yanxiong Li,Wenchang Cao,Wei Xie,Qisheng Huang,Wenfeng Pang,Qianhua He机构：School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China备注：5 pages, 5 figures, 4 tables. Accepted for publication in the 16th IEEE International Conference on Signal Processing (IEEE ICSP)【13】 Few-shot Class-incremental Audio Classification Using Stochastic Classifier标题：基于随机分类器的Few-Shot类增量音频分类链接：https://arxiv.org/abs/2306.02053作者：Yanxiong Li,Wenchang Cao,Jialong Li,Wei Xie,Qianhua He机构：School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China备注：5 pages, 3 figures, 4 tables. Accepted for publication in INTERSPEECH 2023【14】 Why We Should Report the Details in Subjective Evaluation of TTS More Rigorously标题：为什么我们应该更严格地报道TTS主观评价中的细节链接：https://arxiv.org/abs/2306.02044作者：Cheng-Han Chiang,Wei-Ping Huang,Hung-yi Lee机构：National Taiwan University, Taiwan备注：Interspeech 2023 camera-ready version【15】 SGEM: Test-Time Adaptation for Automatic Speech Recognition via Sequential-Level Generalized Entropy Minimization标题：SGEM：基于序贯广义熵最小化的自动语音识别测试时间自适应链接：https://arxiv.org/abs/2306.01981作者：Changhun Kim,Joonhyung Park,Hajin Shim,Eunho Yang机构：Korea Advanced Institute of Science and Technology (KAIST), South Korea, AITRICS, South Korea备注：Accepted to INTERSPEECH 2023【16】 Speaker-independent neural formant synthesis标题：非特定人神经共振峰合成链接：https://arxiv.org/abs/2306.01957作者：Pablo Pérez Zarazaga,Zofia Malisz,Gustav Eje Henter,Lauri Juvela机构：Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Sweden, Department of Information and Communications Engineering, Aalto University, Finland备注：5 pages, 4 figures. Article accepted at INTERSPEECH 2023【17】 In-the-wild Speech Emotion Conversion Using Disentangled Self-Supervised Representations and Neural Vocoder-based Resynthesis标题：基于解缠自监督表示和基于神经声码器的再合成的野外语音情感转换链接：https://arxiv.org/abs/2306.01916作者：Navin Raj Prabhu,Nale Lehmann-Willenbrock,Timo Gerkmann机构：⋆Signal Processing, †Industrial and Organizational Psychology, Universität Hamburg, Germany备注：Submitted to 15th ITG Conference on Speech Communication【18】 Non-uniform Speaker Disentanglement For Depression Detection From Raw Speech Signals标题：非均匀说话人解缠用于原始语音信号中的抑郁检测链接：https://arxiv.org/abs/2306.01861作者：Jinhan Wang,Vijay Ravi,Abeer Alwan机构：Dept . of Electrical and Computer Engineering, University of California, Los Angeles, USA【19】 PolyVoice: Language Models for Speech to Speech Translation标题：PolyVoice：语音到语音翻译的语言模型链接：https://arxiv.org/abs/2306.02982作者：Qianqian Dong,Zhiying Huang,Chen Xu,Yunlong Zhao,Kexin Wang,Xuxin Cheng,Tom Ko,Qiao Tian,Tang Li,Fengpeng Yue,Ye Bai,Xi Chen,Lu Lu,Zejun Ma,Yuping Wang,Mingxuan Wang,Yuxuan Wang机构：ByteDance【20】 N-Shot Benchmarking of Whisper on Diverse Arabic Speech Recognition标题：不同阿拉伯语语音识别中密语的N-shot基准链接：https://arxiv.org/abs/2306.02902作者：Bashar Talafha,Abdul Waheed,Muhammad Abdul-Mageed机构：The University of British Columbia, Canada, Mohamed bin Zayed University of Artificial Intelligence, UAE备注：4 pages, INTERSPEECH 2023【21】 Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding标题：视频骆驼：一种面向视频理解的教学调谐视听语言模型链接：https://arxiv.org/abs/2306.02858作者：Hang Zhang,Xin Li,Lidong Bing机构：DAMO Academy, Alibaba Group备注：Technical Report【22】 The Learning Prescription, A Neural Network Hearing Aid Core标题：学习处方--神经网络助听器的核心链接：https://arxiv.org/abs/2306.02750作者：Matt R. Flax备注：this https URL【23】 Multiple output samples for each input in a single-output Gaussian process标题：单输出高斯过程中每个输入的多个输出样本链接：https://arxiv.org/abs/2306.02719作者：Jeremy H. M. Wong,Huayun Zhang,Nancy F. Chen机构：Institute for Infocomm Research (I,R), A⋆STAR, Singapore【24】 End-to-End Word-Level Pronunciation Assessment with MASK Pre-training标题：带有口罩预训练的端到端单词级发音评估链接：https://arxiv.org/abs/2306.02682作者：Yukang Liang,Kaitao Song,Shaoguang Mao,Huiqiang Jiang,Luna Qiu,Yuqing Yang,Dongsheng Li,Linli Xu,Lili Qiu机构：School of Computer Science and Technology, University of Science and Technology of China, State Key Laboratory of Cognitive Intelligence ,Microsoft Research备注：Accepted by InterSpeech 2023【25】 BeAts: Bengali Speech Acts Recognition using Multimodal Attention Fusion标题：Beats：基于多模式注意力融合的孟加拉语音行为识别链接：https://arxiv.org/abs/2306.02680作者：Ahana Deb,Sayan Nag,Ayan Mahapatra,Soumitri Chattopadhyay,Aritra Marik,Pijush Kanti Gayen,Shankha Sanyal,Archi Banerjee,Samir Karmakar机构：Jadavpur University, India, University of Toronto, Canada, IIT Kharagpur, India备注：Accepted at INTERSPEECH 2023【26】 Rethinking the visual cues in audio-visual speaker extraction标题：对视听说话人提取中视觉线索的再思考链接：https://arxiv.org/abs/2306.02625作者：Junjie Li,Meng Ge,Zexu pan,Rui Cao,Longbiao Wang,Jianwu Dang,Shiliang Zhang机构： Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China, Department of Electrical and Computer Engineering, National University of Singapore, Singapore备注：Accepted in Interspeech 2023【27】 Controllable Lyrics-to-Melody Generation标题：可控的歌词到旋律生成链接：https://arxiv.org/abs/2306.02613作者：Zhe Zhang,Yi Yu,Atsuhiro Takasu机构：Digital Content and Media Sciences Research Division, National Institute of Informatics, SOKENDAI, Tokyo, Japan【28】 Cross-Lingual Transfer Learning for Phrase Break Prediction with Multilingual Language Model标题：基于多语言模型的跨语言迁移学习词断预测链接：https://arxiv.org/abs/2306.02579作者：Hoyeon Lee,Hyun-Wook Yoon,Jong-Hwan Kim,Jae-Min Kim机构：NAVER Cloud, South Korea备注：Accepted by INTERSPEECH 2023【29】 Incorporating L2 Phonemes Using Articulatory Features for Robust Speech Recognition标题：利用节律特征结合二语音素进行稳健语音识别链接：https://arxiv.org/abs/2306.02534作者：Jisung Wang,Haram Lee,Myungwoo Oh机构：NAVER Cloud, South Korea备注：Accepted at INTERSPEECH 2023【30】 SpellMapper: A non-autoregressive neural spellchecker for ASR customization with candidate retrieval based on n-gram mappings标题：SpellMapper：用于ASR定制和基于n元语法映射的候选检索的非自回归神经拼写检查器链接：https://arxiv.org/abs/2306.02317作者：Alexandra Antonova,Evelina Bakhturina,Boris Ginsburg机构：NVIDIA, USA备注：Accepted by INTERSPEECH 2023【31】 End-to-End Joint Target and Non-Target Speakers ASR标题：端到端联合目标和非目标说话人ASR链接：https://arxiv.org/abs/2306.02273作者：Ryo Masumura,Naoki Makishima,Taiga Yamane,Yoshihiko Yamazaki,Saki Mizuno,Mana Ihori,Mihiro Uchida,Keita Suzuki,Hiroshi Sato,Tomohiro Tanaka,Akihiko Takashima,Satoshi Suzuki,Takafumi Moriya,Nobukatsu Hojo,Atsushi Ando机构：NTT Computer and Data Science Laboratories, NTT Corporation, Japan备注：Accepted at Interspeech 2023【32】 Effects of Tonal Coarticulation and Prosodic Positions on Tonal Contours of Low Rising Tones: In the Case of Xiamen Dialect标题：声调协同清晰度和韵律位置对低上调声调轮廓的影响：以厦门方言为例链接：https://arxiv.org/abs/2306.02251作者：Yiying Hu,Hui Feng,Qinghua Zhao,Aijun Li机构：Tianjin University, China, Institute of linguistics, Chinese Academy of Social Sciences, China备注：To be published in InterSpeech 2023【33】 Acoustic Word Embeddings for Untranscribed Target Languages with Continued Pretraining and Learned Pooling标题：持续预训练和习得池的未转录目标语言的声学单词嵌入链接：https://arxiv.org/abs/2306.02153作者：Ramon Sanabria,Ondrej Klejch,Hao Tang,Sharon Goldwater机构：The University of Edinburgh备注：Accepted to Interspeech 2023【34】 Adapting Pretrained ASR Models to Low-resource Clinical Speech using Epistemic Uncertainty-based Data Selection标题：使用基于认知不确定性的数据选择使预先训练的ASR模型适应低资源的临床语音链接：https://arxiv.org/abs/2306.02105作者：Bonaventure F. P. Dossou,Atnafu Lambebo Tonja,Chris Chinenye Emezue,Tobi Olatunji,Naome A Etori,Salomey Osei,Tosin Adewumi,Sahib Singh机构：∗Masakhane NLP,Mila Quebec AI Institute, McGill University, Lelapa AI, Lanfrica, Instituto Politécnico Nacional,Technical University of Munich,Intron Health Inc,Georgia Institute of Technology【35】 BEDRF: Bidirectional Edge Diffraction Response Function for Interactive Sound Propagation标题：BEDRF：交互式声传播的双向边缘绕射响应函数链接：https://arxiv.org/abs/2306.01974作者：Chunxiao Cao,Zili An,Zhong Ren,Dinesh Manocha,Kun Zhou机构： State Key Laboratory of CAD&CG, Zhejiang UniversityZHONG REN, Zhejiang UniversityDINESH MANOCHA, Department of Computer Science, University of Maryland, Zhejiang UniversityWe introduce bidirectional edge diffraction response function (BEDRF)【36】 Can Contextual Biasing Remain Effective with Whisper and GPT-2?标题：语境偏见能在Whisper和GPT-2中保持有效吗？链接：https://arxiv.org/abs/2306.01942作者：Guangzhi Sun,Xianrui Zheng,Chao Zhang,Philip C. Woodland机构：University of Cambridge Department of Engineering, Trumpington St., Cambridge, CB,PZ U.K.备注：To appear in Interspeech 2023【37】 Discovering COVID-19 Coughing and Breathing Patterns from Unlabeled Data Using Contrastive Learning with Varying Pre-Training Domains标题：利用不同训练前领域的对比学习从未标记数据中发现新冠肺炎咳嗽和呼吸模式链接：https://arxiv.org/abs/2306.01864作者：Jinjin Cai,Sudip Vhaduri,Xiao Luo机构：Comp & Info Tech Dept, Purdue University, West Lafayette, IN , USA, Comp & Info Tech Dept, IUPUI, Indianapolis, IN , USA备注：None【38】 Multi-View Multi-Task Representation Learning for Mispronunciation Detection标题：用于错误发音检测的多视点多任务表征学习链接：https://arxiv.org/abs/2306.01845作者：Yassine El Kheir,Shammur Absar Chowdhury,Ahmed Ali机构：Qatar Computing Research Institute, HBKU, Doha, Qatar备注：5 pages【39】 Edit Distance based RL for RNNT decoding标题：基于编辑距离的RNNT解码RL链接：https://arxiv.org/abs/2306.01789作者：Dongseong Hwang,Changwan Ryu,Khe Chai Sim机构：Google, U.S.A备注：5 pages, 2 figures机器翻译，仅供参考
每日语音速递
