今日论文合集：cs.SD语音15篇，eess.AS音频处理22篇。cs.SD语音【1】 Audio-visual segmentation, sound localization, semantic-aware sounding objects localization标题：视听分割、声音定位、语义感知的发声对象定位链接：https://arxiv.org/abs/2307.16620作者：Chen Liu,Peike Li,Xingqun Qi,Hu Zhang,Lincheng Li,Dadong Wang,Xin Yu备注：This paper has been received by ACM MM 23【2】 Audio-visual video-to-speech synthesis with synthesized input audio标题：具有合成输入音频的视听视频到语音合成链接：https://arxiv.org/abs/2307.16584作者：Triantafyllos Kefalas,Yannis Panagakis,Maja Pantic备注：This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible【3】 Contrastive Conditional Latent Diffusion for Audio-visual Segmentation标题：用于视听分割的对比条件隐含扩散算法链接：https://arxiv.org/abs/2307.16579作者：Yuxin Mao,Jing Zhang,Mochu Xiang,Yunqiu Lv,Yiran Zhong,Yuchao Dai【4】 DiffProsody: Diffusion-based Latent Prosody Generation for Expressive Speech Synthesis with Prosody Conditional Adversarial Training标题：DiffProsody：基于扩散的潜在韵律生成与韵律条件对抗训练的表现性语音合成链接：https://arxiv.org/abs/2307.16549作者：Hyung-Seok Oh,Sang-Hoon Lee,Seong-Whan Lee备注：10 pages, 8 figures, 5 tables, under review【5】 SpatialNet: Extensively Learning Spatial Information for Multichannel Joint Speech Separation, Denoising and Dereverberation标题：SpatialNet：广泛学习空间信息用于多通道联合语音分离、去噪和去混响链接：https://arxiv.org/abs/2307.16516作者：Changsheng Quan,Xiaofei Li【6】 VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design标题：VITS2：利用对抗性学习和架构设计提高单级文语转换的质量和效率链接：https://arxiv.org/abs/2307.16430作者：Jungil Kong,Jihoon Park,Beomjeong Kim,Jeongmin Kim,Dohee Kong,Sangjin Kim备注：Interspeech 2023【7】 LP-MusicCaps: LLM-Based Pseudo Music Captioning标题：LP-MusicCaps：基于LLM的伪音乐字幕链接：https://arxiv.org/abs/2307.16372作者：SeungHeon Doh,Keunwoo Choi,Jongpil Lee,Juhan Nam备注：Accepted for publication at the 24th International Society for Music Information Retrieval Conference (ISMIR 2023)【8】 Mispronunciation detection using self-supervised speech representations标题：使用自监督语音表示的发音错误检测链接：https://arxiv.org/abs/2307.16324作者：Jazmin Vidal,Pablo Riera,Luciana Ferrer【9】 Unified Model for Image, Video, Audio and Language Tasks标题：图像、视频、音频和语言任务的统一模型链接：https://arxiv.org/abs/2307.16184作者：Mustafa Shukor,Corentin Dancette,Alexandre Rame,Matthieu Cord备注：40 pages. Project page: this https URL【10】 HierVST: Hierarchical Adaptive Zero-shot Voice Style Transfer标题：HierVST：层次化自适应零发语音风格转换链接：https://arxiv.org/abs/2307.16171作者：Sang-Hoon Lee,Ha-Yeong Choi,Hyung-Seok Oh,Seong-Whan Lee备注：INTERSPEECH 2023 (Oral)【11】 ÌròyìnSpeech: A multi-purpose Yorùbá Speech Corpus标题：语料库：一个多用途的语音语料库链接：https://arxiv.org/abs/2307.16071作者：Tolulope Ogunremi,Kola Tubosun,Anuoluwapo Aremu,Iroro Orife,David Ifeoluwa Adelani备注：working paper【12】 MSStyleTTS: Multi-Scale Style Modeling with Hierarchical Context Information for Expressive Speech Synthesis标题：MSStyleTTS：用于表现性语音合成的分层上下文信息多尺度风格建模链接：https://arxiv.org/abs/2307.16012作者：Shun Lei,Yixuan Zhou,Liyang Chen,Zhiyong Wu,Xixin Wu,Shiyin Kang,Helen Meng备注：Accepted by IEEE/ACM Transactions on Audio, Speech, and Language Processing【13】 Moisesdb: A dataset for source separation beyond 4-stems标题：Moisesdb：一个用于4个词干以外的源分离的数据集链接：https://arxiv.org/abs/2307.15913作者：Igor Pereira,Felipe Araújo,Filip Korzeniowski,Richard Vogl【14】 UniBriVL: Robust Universal Representation and Generation of Audio Driven Diffusion Models标题：UniBriVL：音频驱动扩散模型的稳健通用表示和生成链接：https://arxiv.org/abs/2307.15898作者：Sen Fang,Bowen Gao,Yangjian Wu,Jingwen Cai,Teik Toe Teoh备注：Voice-Text fusion input; First audio drive diffusion model work; Ver.2023.5【15】 SAMbA: Speech enhancement with Asynchronous ad-hoc Microphone Arrays标题：Samba：使用异步自组织麦克风阵列增强语音链接：https://arxiv.org/abs/2307.16582作者：Nicolas Furnon,Romain Serizel,Slim Essid,Irina Illina备注：Submitted to INTERSPEECH 2022eess.AS音频处理【1】 An enhanced system for the detection and active cancellation of snoring signals标题：一种用于检测和主动消除鼾声信号的增强系统链接：https://arxiv.org/abs/2307.16809作者：Valeria Bruschi,Michela Cantarini,Luca Serafini,Stefano Nobili,Stefania Cecchi,Stefano Squartini【2】 Comparing normalizing flows and diffusion models for prosody and acoustic modelling in text-to-speech标题：文本到语音转换中韵律和声学建模的归一化流动和扩散模型的比较链接：https://arxiv.org/abs/2307.16679作者：Guangyan Zhang,Thomas Merritt,Manuel Sam Ribeiro,Biel Tura-Vecino,Kayoko Yanagisawa,Kamil Pokora,Abdelhamid Ezzerg,Sebastian Cygert,Ammar Abbas,Piotr Bilinski,Roberto Barra-Chicote,Daniel Korzekwa,Jaime Lorenzo-Trueba备注：5 pages, 2 figures, 5 tables. Interspeech 2023【3】 Improving grapheme-to-phoneme conversion by learning pronunciations from speech recordings标题：通过从语音记录中学习发音来提高字素到音素的转换链接：https://arxiv.org/abs/2307.16643作者：Manuel Sam Ribeiro,Giulia Comini,Jaime Lorenzo-Trueba备注：5 pages, 2 figures, 4 tables. Interspeech 2023【4】 SAMbA: Speech enhancement with Asynchronous ad-hoc Microphone Arrays标题：Samba：使用异步自组织麦克风阵列增强语音链接：https://arxiv.org/abs/2307.16582作者：Nicolas Furnon,Romain Serizel,Slim Essid,Irina Illina备注：Submitted to INTERSPEECH 2022【5】 All-In-One Metrical And Functional Structure Analysis With Neighborhood Attentions on Demixed Audio标题：解混音音频的邻域关注度和功能结构分析链接：https://arxiv.org/abs/2307.16425作者：Taejun Kim,Juhan Nam备注：This paper has been accepted for publication at the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2023【6】 Robust Self Supervised Speech Embeddings for Child-Adult Classification in Interactions involving Children with Autism标题：自闭症儿童互动中用于儿童-成人分类的鲁棒自监督语音嵌入链接：https://arxiv.org/abs/2307.16398作者：Rimita Lahiri,Tiantian Feng,Rajat Hebbar,Catherine Lord,So Hyun Kim,Shrikanth Narayanan【7】 Pre-training End-to-end ASR Models with Augmented Speech Samples Queried by Text标题：利用文本查询的增强语音样本预训练端到端ASR模型链接：https://arxiv.org/abs/2307.16332作者：Eric Sun,Jinyu Li,Jian Xue,Yifan Gong【8】 METTS: Multilingual Emotional Text-to-Speech by Cross-speaker and Cross-lingual Emotion Transfer标题：Metts：基于跨语者和跨语言情感传递的多语言情感文语转换链接：https://arxiv.org/abs/2307.15951作者：Xinfa Zhu,Yi Lei,Tao Li,Yongmao Zhang,Hongbin Zhou,Heng Lu,Lei Xie备注：10 pages, 3 figures【9】 Multilingual context-based pronunciation learning for Text-to-Speech标题：基于多语言语境的文语转换发音学习链接：https://arxiv.org/abs/2307.16709作者：Giulia Comini,Manuel Sam Ribeiro,Fan Yang,Heereen Shim,Jaime Lorenzo-Trueba备注：5 pages, 2 figures, 5 tables. Interspeech 2023【10】 Audio-visual segmentation, sound localization, semantic-aware sounding objects localization标题：视听分割、声音定位、语义感知的发声对象定位链接：https://arxiv.org/abs/2307.16620作者：Chen Liu,Peike Li,Xingqun Qi,Hu Zhang,Lincheng Li,Dadong Wang,Xin Yu备注：This paper has been received by ACM MM 23【11】 Audio-visual video-to-speech synthesis with synthesized input audio标题：具有合成输入音频的视听视频到语音合成链接：https://arxiv.org/abs/2307.16584作者：Triantafyllos Kefalas,Yannis Panagakis,Maja Pantic备注：This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible【12】 Contrastive Conditional Latent Diffusion for Audio-visual Segmentation标题：用于视听分割的对比条件隐含扩散算法链接：https://arxiv.org/abs/2307.16579作者：Yuxin Mao,Jing Zhang,Mochu Xiang,Yunqiu Lv,Yiran Zhong,Yuchao Dai【13】 DiffProsody: Diffusion-based Latent Prosody Generation for Expressive Speech Synthesis with Prosody Conditional Adversarial Training标题：DiffProsody：基于扩散的潜在韵律生成与韵律条件对抗训练的表现性语音合成链接：https://arxiv.org/abs/2307.16549作者：Hyung-Seok Oh,Sang-Hoon Lee,Seong-Whan Lee备注：10 pages, 8 figures, 5 tables, under review【14】 SpatialNet: Extensively Learning Spatial Information for Multichannel Joint Speech Separation, Denoising and Dereverberation标题：SpatialNet：广泛学习空间信息用于多通道联合语音分离、去噪和去混响链接：https://arxiv.org/abs/2307.16516作者：Changsheng Quan,Xiaofei Li【15】 VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design标题：VITS2：利用对抗性学习和架构设计提高单级文语转换的质量和效率链接：https://arxiv.org/abs/2307.16430作者：Jungil Kong,Jihoon Park,Beomjeong Kim,Jeongmin Kim,Dohee Kong,Sangjin Kim备注：Interspeech 2023【16】 LP-MusicCaps: LLM-Based Pseudo Music Captioning标题：LP-MusicCaps：基于LLM的伪音乐字幕链接：https://arxiv.org/abs/2307.16372作者：SeungHeon Doh,Keunwoo Choi,Jongpil Lee,Juhan Nam备注：Accepted for publication at the 24th International Society for Music Information Retrieval Conference (ISMIR 2023)【17】 Mispronunciation detection using self-supervised speech representations标题：使用自监督语音表示的发音错误检测链接：https://arxiv.org/abs/2307.16324作者：Jazmin Vidal,Pablo Riera,Luciana Ferrer【18】 HierVST: Hierarchical Adaptive Zero-shot Voice Style Transfer标题：HierVST：层次化自适应零发语音风格转换链接：https://arxiv.org/abs/2307.16171作者：Sang-Hoon Lee,Ha-Yeong Choi,Hyung-Seok Oh,Seong-Whan Lee备注：INTERSPEECH 2023 (Oral)【19】 ÌròyìnSpeech: A multi-purpose Yorùbá Speech Corpus标题：语料库：一个多用途的语音语料库链接：https://arxiv.org/abs/2307.16071作者：Tolulope Ogunremi,Kola Tubosun,Anuoluwapo Aremu,Iroro Orife,David Ifeoluwa Adelani备注：working paper【20】 MSStyleTTS: Multi-Scale Style Modeling with Hierarchical Context Information for Expressive Speech Synthesis标题：MSStyleTTS：用于表现性语音合成的分层上下文信息多尺度风格建模链接：https://arxiv.org/abs/2307.16012作者：Shun Lei,Yixuan Zhou,Liyang Chen,Zhiyong Wu,Xixin Wu,Shiyin Kang,Helen Meng备注：Accepted by IEEE/ACM Transactions on Audio, Speech, and Language Processing【21】 Moisesdb: A dataset for source separation beyond 4-stems标题：Moisesdb：一个用于4个词干以外的源分离的数据集链接：https://arxiv.org/abs/2307.15913作者：Igor Pereira,Felipe Araújo,Filip Korzeniowski,Richard Vogl【22】 UniBriVL: Robust Universal Representation and Generation of Audio Driven Diffusion Models标题：UniBriVL：音频驱动扩散模型的稳健通用表示和生成链接：https://arxiv.org/abs/2307.15898作者：Sen Fang,Bowen Gao,Yangjian Wu,Jingwen Cai,Teik Toe Teoh备注：Voice-Text fusion input; First audio drive diffusion model work; Ver.2023.5机器翻译，仅供参考
每日语音速递
