今日论文合集：cs.SD语音21篇，eess.AS音频处理23篇。本文经arXiv每日学术速递授权转载
【1】Pictures Of MIDI: Controlled Music Generation via Graphical Prompts for Image-Based Diffusion Inpainting
标题：预设图片：通过基于图像的扩散修复的图形预设控制音乐生成
链接：https://arxiv.org/abs/2407.01499
作者：Scott H. Hawley
备注：6 pages text + 2 pages references, 10 figures
【2】 FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds标题：FoleyCrafter：通过栩栩如生且同步的声音将无声视频带入生活作者：Yiming Zhang,Yicheng Gu,Yanhong Zeng,Zhening Xing,Yuancheng Wang,Zhizheng Wu,Kai Chen备注：Project page: this https URL【3】 On Feature Learning for Titi Monkey Activity Detection作者：Aditya Ravuri,Jen Muir,Neil D. Lawrence【4】 Leveraging Speaker Embeddings in End-to-End Neural Diarization for Two-Speaker Scenarios标题：在双扬声器场景的端到端神经扩展中利用扬声器嵌入作者：Juan Ignacio Alvarez-Trejos,Beltrán Labrador,Alicia Lozano-Diez备注：Submitted to Odyssey 2024【5】 Lightweight Zero-shot Text-to-Speech with Mixture of Adapters标题：具有混合适配器的轻量级Zero-Shot文本到语音作者：Kenichi Fujita,Takanori Ashihara,Marc Delcroix,Yusuke Ijima备注：5 pages,3 figures, Accepted to INTERSPEECH 2024【6】 uDistil-Whisper: Label-Free Data Filtering for Knowledge Distillation via Large-Scale Pseudo Labelling标题：uDistil-Whisper：通过大规模伪标签进行知识提炼的无标签数据过滤作者：Abdul Waheed,Karima Kadaoui,Muhammad Abdul-Mageed【7】 Are you sure? Analysing Uncertainty Quantification Approaches for Real-world Speech Emotion Recognition标题：你确定吗？现实世界语音情感识别的不确定性量化方法分析作者：Oliver Schrüfer,Manuel Milling,Felix Burkhardt,Florian Eyben,Björn Schuller备注：accepted for Interspeech 2024, 5 pages【8】 SecureSpectra: Safeguarding Digital Identity from Deep Fake Threats via Intelligent Signatures标题：SecureSpectra：通过智能签名保护数字身份免受深度虚假威胁作者：Oguzhan Baser,Kaan Kale,Sandeep P. Chinchali备注：5 pages, 4 figures, Proc. INTERSPEECH 2024【9】 Papez: Resource-Efficient Speech Separation with Auditory Working Memory标题：Papez：具有听觉工作记忆的资源高效语音分离作者：Hyunseok Oh,Juheon Yi,Youngki Lee备注：5 pages. Accepted by ICASSP 2023【10】 Towards Robust Speech Representation Learning for Thousands of Languages作者：William Chen,Wangyou Zhang,Yifan Peng,Xinjian Li,Jinchuan Tian,Jiatong Shi,Xuankai Chang,Soumi Maiti,Karen Livescu,Shinji Watanabe【11】 NAIST Simultaneous Speech Translation System for IWSLT 2024标题：NAIST IWSYS 2024同步语音翻译系统作者：Yuka Ko,Ryo Fukuda,Yuta Nishikawa,Yasumasa Kano,Tomoya Yanagita,Kosuke Doi,Mana Makinae,Haotian Tan,Makoto Sakai,Sakriani Sakti,Katsuhito Sudoh,Satoshi Nakamura备注：IWSLT 2024 system paper【12】 An Attribute Interpolation Method in Speech Synthesis by Model Merging作者：Masato Murata,Koichi Miyazaki,Tomoki Koriyama备注：Accepted by INTERSPEECH 2024【13】 Improving Real-Time Music Accompaniment Separation with MMDenseNet标题：利用MMDenseNet改进实时音乐伴奏分离作者：Chun-Hsiang Wang,Chung-Che Wang,Jun-You Wang,Jyh-Shing Roger Jang,Yen-Hsun Chu【14】 Interpreting Pretrained Speech Models for Automatic Speech Assessment of Voice Disorders作者：Hok-Shing Lau,Mark Huntly,Nathon Morgan,Adesua Iyenoma,Biao Zeng,Tim Bashford【15】 Detecting and Identifying Selection Structure in Sequential Data作者：Yujia Zheng,Zeyu Tang,Yiwen Qiu,Bernhard Schölkopf,Kun Zhang【16】 Characterizing Continual Learning Scenarios and Strategies for Audio Analysis作者：Ruchi Bhatt,Pratibha Kumari,Dwarikanath Mahapatra,Abdulmotaleb El Saddik,Mukesh Saini【17】 A Novel Labeled Human Voice Signal Dataset for Misbehavior Detection标题：用于不当行为检测的新型标记人类语音信号数据集作者：Ali Raza,Faizan Younas【18】 Less Forgetting for Better Generalization: Exploring Continual-learning Fine-tuning Methods for Speech Self-supervised Representations标题：更少的遗忘，更好的概括：探索语音自我监督表示的连续学习微调方法作者：Salah Zaiem,Titouan Parcollet,Slim Essid【19】 FLY-TTS: Fast, Lightweight and High-Quality End-to-End Text-to-Speech Synthesis标题：FLY-TTC：快速、轻量级、高质量的端到端文本到语音合成作者：Yinlin Guo,Yening Lv,Jinqiao Dou,Yan Zhang,Yuehai Wang备注：Accepted to Interspeech 2024. 5 pages, 1 figure【20】 FMSG-JLESS Submission for DCASE 2024 Task4 on Sound Event Detection with Heterogeneous Training Dataset and Potentially Missing Labels标题：FMSG-JLESS提交DUSE 2024 Task 4，使用异类训练数据集和潜在缺失标签进行声音事件检测作者：Yang Xiao,Han Yin,Jisheng Bai,Rohan Kumar Das备注：Technical report for DCASE 2024 Challenge Task 4【21】 Cochlear Wave Propagation and Dynamics in the Human Base and Apex: Model-Based Estimates from Noninvasive Measurements标题：人体底部和顶部的Costa波传播和动力学：无创测量的基于模型的估计【1】 Less Forgetting for Better Generalization: Exploring Continual-learning Fine-tuning Methods for Speech Self-supervised Representations标题：更少的遗忘，更好的概括：探索语音自我监督表示的连续学习微调方法作者：Salah Zaiem,Titouan Parcollet,Slim Essid【2】 FLY-TTS: Fast, Lightweight and High-Quality End-to-End Text-to-Speech Synthesis标题：FLY-TTC：快速、轻量级、高质量的端到端文本到语音合成作者：Yinlin Guo,Yening Lv,Jinqiao Dou,Yan Zhang,Yuehai Wang备注：Accepted to Interspeech 2024. 5 pages, 1 figure【3】 FMSG-JLESS Submission for DCASE 2024 Task4 on Sound Event Detection with Heterogeneous Training Dataset and Potentially Missing Labels标题：FMSG-JLESS提交DUSE 2024 Task 4，使用异类训练数据集和潜在缺失标签进行声音事件检测作者：Yang Xiao,Han Yin,Jisheng Bai,Rohan Kumar Das备注：Technical report for DCASE 2024 Challenge Task 4【4】 Pictures Of MIDI: Controlled Music Generation via Graphical Prompts for Image-Based Diffusion Inpainting标题：预设图片：通过基于图像的扩散修复的图形预设控制音乐生成备注：6 pages text + 2 pages references, 10 figures【5】 FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds标题：FoleyCrafter：通过栩栩如生且同步的声音将无声视频带入生活作者：Yiming Zhang,Yicheng Gu,Yanhong Zeng,Zhening Xing,Yuancheng Wang,Zhizheng Wu,Kai Chen备注：Project page: this https URL【6】 On Feature Learning for Titi Monkey Activity Detection作者：Aditya Ravuri,Jen Muir,Neil D. Lawrence【7】 Leveraging Speaker Embeddings in End-to-End Neural Diarization for Two-Speaker Scenarios标题：在双扬声器场景的端到端神经扩展中利用扬声器嵌入作者：Juan Ignacio Alvarez-Trejos,Beltrán Labrador,Alicia Lozano-Diez备注：Submitted to Odyssey 2024【8】 Lightweight Zero-shot Text-to-Speech with Mixture of Adapters标题：具有混合适配器的轻量级Zero-Shot文本到语音作者：Kenichi Fujita,Takanori Ashihara,Marc Delcroix,Yusuke Ijima备注：5 pages,3 figures, Accepted to INTERSPEECH 2024【9】 uDistil-Whisper: Label-Free Data Filtering for Knowledge Distillation via Large-Scale Pseudo Labelling标题：uDistil-Whisper：通过大规模伪标签进行知识提炼的无标签数据过滤作者：Abdul Waheed,Karima Kadaoui,Muhammad Abdul-Mageed【10】 Are you sure? Analysing Uncertainty Quantification Approaches for Real-world Speech Emotion Recognition标题：你确定吗？现实世界语音情感识别的不确定性量化方法分析作者：Oliver Schrüfer,Manuel Milling,Felix Burkhardt,Florian Eyben,Björn Schuller备注：accepted for Interspeech 2024, 5 pages【11】 SecureSpectra: Safeguarding Digital Identity from Deep Fake Threats via Intelligent Signatures标题：SecureSpectra：通过智能签名保护数字身份免受深度虚假威胁作者：Oguzhan Baser,Kaan Kale,Sandeep P. Chinchali备注：5 pages, 4 figures, Proc. INTERSPEECH 2024【12】 Papez: Resource-Efficient Speech Separation with Auditory Working Memory标题：Papez：具有听觉工作记忆的资源高效语音分离作者：Hyunseok Oh,Juheon Yi,Youngki Lee备注：5 pages. Accepted by ICASSP 2023【13】 Towards Robust Speech Representation Learning for Thousands of Languages作者：William Chen,Wangyou Zhang,Yifan Peng,Xinjian Li,Jinchuan Tian,Jiatong Shi,Xuankai Chang,Soumi Maiti,Karen Livescu,Shinji Watanabe【14】 NAIST Simultaneous Speech Translation System for IWSLT 2024标题：NAIST IWSYS 2024同步语音翻译系统作者：Yuka Ko,Ryo Fukuda,Yuta Nishikawa,Yasumasa Kano,Tomoya Yanagita,Kosuke Doi,Mana Makinae,Haotian Tan,Makoto Sakai,Sakriani Sakti,Katsuhito Sudoh,Satoshi Nakamura备注：IWSLT 2024 system paper【15】 An Attribute Interpolation Method in Speech Synthesis by Model Merging作者：Masato Murata,Koichi Miyazaki,Tomoki Koriyama备注：Accepted by INTERSPEECH 2024【16】 AIMDiT: Modality Augmentation and Interaction via Multimodal Dimension Transformation for Emotion Recognition in Conversations标题：AIMDiT：通过多模式维度转换进行模式增强和互动，用于对话中的情感识别作者：Sheng Wu,Jiaxing Liu,Longbiao Wang,Dongxiao He,Xiaobao Wang,Jianwu Dang【17】 Improving Real-Time Music Accompaniment Separation with MMDenseNet标题：利用MMDenseNet改进实时音乐伴奏分离作者：Chun-Hsiang Wang,Chung-Che Wang,Jun-You Wang,Jyh-Shing Roger Jang,Yen-Hsun Chu【18】 Interpreting Pretrained Speech Models for Automatic Speech Assessment of Voice Disorders作者：Hok-Shing Lau,Mark Huntly,Nathon Morgan,Adesua Iyenoma,Biao Zeng,Tim Bashford【19】 Detecting and Identifying Selection Structure in Sequential Data作者：Yujia Zheng,Zeyu Tang,Yiwen Qiu,Bernhard Schölkopf,Kun Zhang【20】 Characterizing Continual Learning Scenarios and Strategies for Audio Analysis作者：Ruchi Bhatt,Pratibha Kumari,Dwarikanath Mahapatra,Abdulmotaleb El Saddik,Mukesh Saini【21】 Open-Source Conversational AI with SpeechBrain 1.0标题：SpeechBrain 1.0开源对话人工智能作者：Mirco Ravanelli,Titouan Parcollet,Adel Moumen,Sylvain de Langen,Cem Subakan,Peter Plantinga,Yingzhi Wang,Pooneh Mousavi,Luca Della Libera,Artem Ploujnikov,Francesco Paissan,Davide Borra,Salah Zaiem,Zeyu Zhao,Shucong Zhang,Georgios Karakasidis,Sung-Lin Yeh,Aku Rouhe,Rudolf Braun,Florian Mai,Juan Zuluaga-Gomez,Seyed Mahed Mousavi,Andreas Nautsch,Xuechen Liu,Sangeet Sagar,Jarod Duret,Salima Mdhaffar,Gaelle Laperriere,Renato De Mori,Yannick Esteve备注：Submitted to JMLR (Machine Learning Open Source Software)【22】 A Novel Labeled Human Voice Signal Dataset for Misbehavior Detection标题：用于不当行为检测的新型标记人类语音信号数据集作者：Ali Raza,Faizan Younas【23】 Cochlear Wave Propagation and Dynamics in the Human Base and Apex: Model-Based Estimates from Noninvasive Measurements标题：人体底部和顶部的Costa波传播和动力学：无创测量的基于模型的估计
每日语音速递