语音/音频处理学术速递[5.23]

今日论文合集：cs.SD语音48篇，eess.AS音频处理48篇。

cs.SD语音

【1】 Modulation Extraction for LFO-driven Audio Effects标题：用于LFO驱动音频效果的调制提取链接：https://arxiv.org/abs/2305.13262

作者：Christopher Mitcheltree,Christian J. Steinmetz,Marco Comunità,Joshua D. Reiss机构：Centre for Digital Music, Queen Mary University of London, UK备注：Accepted to DAFx 2023. Listening samples and plugins can be found at this https URL

【2】 Computational models of sound-quality metrics using method for calculating loudness with gammatone/gammachirp auditory filterbank标题：用Gammatone/Gammachirp听觉滤波器组计算响度的声音质量度量的计算模型链接：https://arxiv.org/abs/2305.13213

作者：Takuto Isoyama,Shunsuke Kidani,Masashi Unoki机构：• A method for calculating loudness using the time-domain, gammatonegammachirp auditory filterbanks is proposed., • Three computational SQM models of sharpness, rough-, ness, and fluctuation strength are also proposed using the, proposed loudness method.

【3】 Learning to detect an animal sound from five examples标题：从五个例子中学习检测动物的声音链接：https://arxiv.org/abs/2305.13210

作者：Inês Nolasco,Shubhr Singh,Veronica Morfi,Vincent Lostanlen,Ariana Strandburg-Peshkin,Ester Vidaña-Vila,Lisa Gill,Hanna Pamuła,Helen Whitehead,Ivan Kiskin,Frants H. Jensen,Joe Morford,Michael G. Emmerson,Elisabetta Versace,Emily Grout,Haohe Liu,Dan Stowell机构：Naturalis Biodiversity Center, Leiden, The Netherlands, Tilburg University, Tilburg, The Netherlands, Queen Mary University of London, London, UK, Centre National de la Recherche Scientifique (CNRS), France

【4】 Improving Isochronous Machine Translation with Target Factors and Auxiliary Counters标题：利用目标因素和辅助计数器改进等时机器翻译链接：https://arxiv.org/abs/2305.13204

作者：Proyag Pal,Brian Thompson,Yogesh Virkar,Prashant Mathur,Alexandra Chronopoulou,Marcello Federico机构：AWS AI Labs, USA, School of Informatics, University of Edinburgh, Scotland, Center for Information and Language Processing, LMU Munich, Germany备注：Accepted at INTERSPEECH 2023

【5】 U-DiT TTS: U-Diffusion Vision Transformer for Text-to-Speech标题：U-DIT TTS：用于文本到语音的U-扩散视觉转换器链接：https://arxiv.org/abs/2305.13195

作者：Xin Jing,Yi Chang,Zijiang Yang,Jiangjian Xie,Andreas Triantafyllopoulos,Bjoern W. Schuller机构：Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Germany, School of Technology, Beijing Forestry University, GLAM – Group on Language, Audio, & Music, Imperial College London, UK

【6】 AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation标题：AudioToken：文本条件扩散模型在音像生成中的应用链接：https://arxiv.org/abs/2305.13050

作者：Guy Yariv,Itai Gat,Lior Wolf,Yossi Adi,Idan Schwartz机构：♥The Hebrew University of Jerusalem , ♦Technion - Israel Institute of Technology, ♠Tel-Aviv University, ♣NetApp备注：Accepted to INTERSPEECH 2023

【7】 Towards generalizing deep-audio fake detection networks标题：走向大众化的深度音频伪装检测网络链接：https://arxiv.org/abs/2305.13033

作者：Konstantin Gasenzer,Moritz Wolter机构：High Performance Computing, and Analytics Lab, Universität Bonn, Germany

【8】 Textually Pretrained Speech Language Models标题：文本预训练语音语言模型链接：https://arxiv.org/abs/2305.13009

作者：Michael Hassid,Tal Remez,Tu Anh Nguyen,Itai Gat,Alexis Conneau,Felix Kreuk,Jade Copet,Alexandre Defossez,Gabriel Synnaeve,Emmanuel Dupoux,Roy Schwartz,Yossi Adi机构：♥The Hebrew University of Jerusalem, ♦OpenAI, ♠Meta AI

【9】 Exploring Speaker-Related Information in Spoken Language Understanding for Better Speaker Diarization标题：在口语理解中探索与说话人相关的信息以更好地实现说话人二元化链接：https://arxiv.org/abs/2305.12927

作者：Luyao Cheng,Siqi Zheng,Zhang Qinglin,Hui Wang,Yafeng Chen,Qian Chen机构：Speech Lab of DAMO Academy, Alibaba Group备注：Accepted to Findings of ACL 2023

【10】 NAS-FM: Neural Architecture Search for Tunable and Interpretable Sound Synthesis based on Frequency Modulation标题：NAS-FM：基于调频的可调谐和可解释声音合成的神经结构研究链接：https://arxiv.org/abs/2305.12868

作者：Zhen Ye,Wei Xue,Xu Tan,Qifeng Liu,Yike Guo机构：Hong Kong Baptist University, Hong Kong University of Science and Technology, Microsoft Research Asia, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences备注：None

【11】 The defender's perspective on automatic speaker verification: An overview标题：辩护人对自动说话人确认的观点：综述链接：https://arxiv.org/abs/2305.12804

作者：Haibin Wu,Jiawen Kang,Lingwei Meng,Helen Meng,Hung-yi Lee机构：Graduate Institute of Communication Engineering, National Taiwan University, Department of Systems Engineering & Engineering Management, The Chinese University of Hong Kong备注：Submitted to IJCAI 2023 Workshop

【12】 GNCformer Enhanced Self-attention for Automatic Speech Recognition标题：用于自动语音识别的GNCformer增强的自我注意链接：https://arxiv.org/abs/2305.12755

作者：J. Li,Z. Duan,S. Li,X. Yu,G. Yang机构：Shiren Li is from Sun Yat-Sen University备注：5 pages,3 figures,

【13】 LEAN: Light and Efficient Audio Classification Network标题：LEAN：轻便高效的音频分类网络链接：https://arxiv.org/abs/2305.12712

作者：Shwetank Choudhary,CR Karthik,Punuru Sri Lakshmi,Sumit Kumar机构：Samsung R&D Institute, Bangalore, India备注：Accepted at INDICON 2022

【14】 Progressive Sub-Graph Clustering Algorithm for Semi-Supervised Domain Adaptation Speaker Verification标题：半监督域自适应说话人确认的递进子图聚类算法链接：https://arxiv.org/abs/2305.12703

作者：Zhuo Li,Jingze Lu,Zhenduo Zhao,Wenchao Wang,Pengyuan Zhang机构： Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China, University of Chinese Academy of Sciences, Beijing, China

【15】 More Perspectives Mean Better: Underwater Target Recognition and Localization with Multimodal Data via Symbiotic Transformer and Multiview Regression标题：视角越多越好：基于共生变换和多视角回归的多模式数据水下目标识别与定位链接：https://arxiv.org/abs/2305.12701

作者：Shipei Liu,Xiaoya Fan,Guowei Wu

【16】 The HCCL system for VoxCeleb Speaker Recognition Challenge 2022标题：VoxCeleb说话人识别挑战赛2022的HCCL系统链接：https://arxiv.org/abs/2305.12642

作者：Zhenduo Zhao,Zhuo Li,Wenchao Wang,Pengyuan Zhang机构：Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese, University of Chinese Academy of Sciences, Beijing, China

【17】 Duplex Diffusion Models Improve Speech-to-Speech Translation标题：双向扩散模型改进了语音到语音的翻译链接：https://arxiv.org/abs/2305.12628

作者：Xianchao Wu机构：NVIDIA备注：11 pages, 3 figures. Accepted by ACL 2023 findings

【18】 Comparison of Multilingual Self-Supervised and Weakly-Supervised Speech Pre-Training for Adaptation to Unseen Languages标题：多语种自我监督和弱监督语音预训练对看不见语言适应的比较链接：https://arxiv.org/abs/2305.12606

作者：Andrew Rouditchenko,Sameer Khurana,Samuel Thomas,Rogerio Feris,Leonid Karlinsky,Hilde Kuehne,David Harwath,Brian Kingsbury,James Glass机构：MIT, USA, IBM Research AI, USA, MIT-IBM Watson AI Lab, USA, Goethe University, Frankfurt, Germany, UT Austin, USA备注：Accepted at Interspeech 2023

【19】 Hystoc: Obtaining word confidences for fusion of end-to-end ASR systems标题：Hystoc：获得端到端ASR系统融合的单词置信度链接：https://arxiv.org/abs/2305.12579

作者：Karel Beneš,Martin Kocour,Lukáš Burget机构：Brno University of Technology, Czechia

【20】 Wav2SQL: Direct Generalizable Speech-To-SQL Parsing标题：Wav2SQL：直接可泛化的语音到SQL解析链接：https://arxiv.org/abs/2305.12552

作者：Huadai Liu,Rongjie Huang,Jinzheng He,Gang Sun,Ran Shen,Xize Cheng,Zhou Zhao机构：Zhejiang University ,State Grid Corporation of China

【21】 Towards robust paralinguistic assessment for real-world mobile health (mHealth) monitoring: an initial study of reverberation effects on speech标题：用于真实世界移动健康(MHealth)监测的稳健副语言评估：混响对语音影响的初步研究链接：https://arxiv.org/abs/2305.12514

作者：Judith Dineley,Ewan Carr,Faith Matcham,Johnny Downs,Richard Dobson,Thomas F Quatieri,Nicholas Cummins机构：Institute of Psychiatry, Psychology and Neuroscience, King’s College London, London, UK, School of Psychology, University of Sussex, Falmer, UK, Institute of Health Informatics, University College London, London, UK, MIT Lincoln Laboratory, Lexington, MA, USA备注：Accepted for publication at Interspeech 2023

【22】 Exploring How Generative Adversarial Networks Learn Phonological Representations标题：探索生成性对抗性网络如何学习语音表征链接：https://arxiv.org/abs/2305.12501

作者：Jingyi Chen,Micha Elsner机构：Department of Linguistics, The Ohio State University

【23】 Self-supervised Predictive Coding Models Encode Speaker and Phonetic Information in Orthogonal Subspaces标题：自监督预测编码模型在正交子空间中编码说话人和语音信息链接：https://arxiv.org/abs/2305.12464

作者：Oli Liu,Hao Tang,Sharon Goldwater机构：School of Informatics, University of Edinburgh, United Kingdom

【24】 Study of GANs for Noisy Speech Simulation from Clean Speech标题：基于清洁语音的带噪语音模拟遗传算法研究链接：https://arxiv.org/abs/2305.12460

作者：Leander Melroy Maben,Zixun Guo,Chen Chen,Utkarsh Chudiwal,Chng Eng Siong机构：Manipal Institute of Technology, Manipal, India ,Nanyang Technological University, Singapore, Indian Institute of Technology, Indore, India

【25】 JNV Corpus: A Corpus of Japanese Nonverbal Vocalizations with Diverse Phrases and Emotions标题：JNV语料库：日语非言语发声语料库链接：https://arxiv.org/abs/2305.12445

作者：Detai Xin,Shinnosuke Takamichi,Hiroshi Saruwatari机构：Graduate School of Information Science and Technology, The University of Tokyo, Japan备注：4 pages, 3 figures

【26】 Laughter Synthesis using Pseudo Phonetic Tokens with a Large-scale In-the-wild Laughter Corpus标题：利用大规模野外笑声语料库的伪音标词合成笑声链接：https://arxiv.org/abs/2305.12442

作者：Detai Xin,Shinnosuke Takamichi,Ai Morimatsu,Hiroshi Saruwatari机构：Graduate School of Information Science and Technology, The University of Tokyo, Japan备注：Accepted by INTERSPEECH 2023

【27】 Sentence Embedder Guided Utterance Encoder (SEGUE) for Spoken Language Understanding标题：用于口语理解的语句嵌入器引导的话语编码器(SEGUE)链接：https://arxiv.org/abs/2305.12301

作者：Yi Xuan Tan,Navonil Majumder,Soujanya Poria机构：Singapore University of Technology and Design, Singapore备注：Interspeech 2023

【28】 Self-supervised representations in speech-based depression detection标题：自监督表示在基于语音的抑郁检测中的应用链接：https://arxiv.org/abs/2305.12263

作者：Wen Wu,Chao Zhang,Philip C. Woodland机构：Department of Engineering, University of Cambridge, Trumpington St., Cambridge, UK.

【29】 ComedicSpeech: Text To Speech For Stand-up Comedies in Low-Resource Scenarios标题：ComedicSpeech：在低资源场景下为单口喜剧提供文本到语音转换链接：https://arxiv.org/abs/2305.12200

作者：Yuyue Wang,Huan Xiao,Yihan Wu,Ruihua Song机构： Gaoling School of Artificial Intelligence, Renmin University of China, China, School of Statistics, Renmin University of China, China备注：5 pages, 4 tables, 2 figure

【30】 ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attention标题：ACA-Net：基于非对称交叉注意力的轻量级说话人确认链接：https://arxiv.org/abs/2305.12121

作者：Jia Qi Yip,Tuan Truong,Dianwen Ng,Chong Zhang,Yukun Ma,Trung Hieu Nguyen,Chongjia Ni,Shengkui Zhao,Eng Siong Chng,Bin Ma机构：Alibaba Group, Nanyang Technological University, Singapore备注：Accepted to INTERSPEECH 2023

【31】 EE-TTS: Emphatic Expressive TTS with Linguistic Information标题：EE-TTS：带有语言信息的强调表达的TTS链接：https://arxiv.org/abs/2305.12107

作者：Yi Zhong,Chen Zhang,Xule Liu,Chenxi Sun,Weishan Deng,Haifeng Hu,Zhongqian Sun机构：Tencent AI Lab, ShenZhen, China, Zhejiang University, China备注：Accepted by INTERSPEECH2023

【32】 MParrotTTS: Multilingual Multi-speaker Text to Speech Synthesis in Low Resource Setting标题：MParrotTTS：低资源环境下的多语言多说话人文语合成链接：https://arxiv.org/abs/2305.11926

作者：Neil Shah,Vishal Tambrahalli,Saiteja Kosgi,Niranjan Pedanekar,Vineet Gandhi机构：Kohli Centre on Intelligent Systems, IIIT Hyderabad, India, TCS Research, Pune, India备注：5 pages, 1 figure

【33】 Debiased Automatic Speech Recognition for Dysarthric Speech via Sample Reweighting with Sample Affinity Test标题：基于样本重加权和样本亲和度检验的无偏自动语音识别链接：https://arxiv.org/abs/2305.13108

作者：Eungbeom Kim,Yunkee Chae,Jaeheon Sim,Kyogu Lee机构：IPAI,AIIS, Seoul National University, Seoul, Republic of Korea备注：Accepted by Interspeech 2023

【34】 ZS-MSTM: Zero-Shot Style Transfer for Gesture Animation driven by Text and Speech using Adversarial Disentanglement of Multimodal Style Encoding标题：ZS-MSTM：基于多模式风格编码对抗性解缠的文本和语音驱动手势动画的Zero-Shot风格转移链接：https://arxiv.org/abs/2305.12887

作者：Mireille Fares,Catherine Pelachaud,Nicolas Obin机构：ISIR, STMS, Sorbonne University, Paris, France, ISIR, CNRS备注：arXiv admin note: substantial text overlap with arXiv:2208.01917

【35】 An Enhanced Res2Net with Local and Global Feature Fusion for Speaker Verification标题：一种基于局部和全局特征融合的增强型Res2Net说话人确认链接：https://arxiv.org/abs/2305.12838

作者：Yafeng Chen,Siqi Zheng,Hui Wang,Luyao Cheng,Qian Chen,Jiajun Qi机构：Speech Lab, Alibaba Group, Hangzhou, China, University of Science and Technology of China, Hefei, China

【36】 Target Active Speaker Detection with Audio-visual Cues标题：基于视听线索的目标活动说话人检测链接：https://arxiv.org/abs/2305.12831

作者：Yidi Jiang,Ruijie Tao,Zexu Pan,Haizhou Li机构：Department of Electrical and Computer Engineering, National University of Singapore, Singapore, SRIBD, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China备注：Accepted to INTERSPEECH2023

【37】 Zero-Shot End-to-End Spoken Language Understanding via Cross-Modal Selective Self-Training标题：通过跨通道选择性自我训练实现零射端到端口语理解链接：https://arxiv.org/abs/2305.12793

作者：Jianfeng He,Julian Salazar,Kaisheng Yao,Haoqi Li,Jinglun Cai机构： AWS AI Labs, Seattle, Washington, USA, Sanghani Center for Artificial Intelligence & Data Analytics, Virginia Tech, Falls Church, VA, USA备注：15 pages, 7 figures

【38】 Coswara: A respiratory sounds and symptoms dataset for remote screening of SARS-CoV-2 infection标题：Coswara：用于SARS-CoV-2感染远程筛查的呼吸音和症状数据集链接：https://arxiv.org/abs/2305.12741

作者：Debarpan Bhattacharya,Neeraj Kumar Sharma,Debottam Dutta,Srikanth Raj Chetupalli,Pravin Mote,Sriram Ganapathy,Chandrakiran C,Sahiti Nori,Suhail K K,Sadhana Gonuguntla,Murali Alagesan机构：Department of Electrical Engineering, Indian Institute of Science, Bangalore, India, Mehta Family School of Data Science and Artificial Intelligence, Indian Institute of Technology, Guwahati, India备注：Accepted for publiation in Nature Scientific Data

【39】 ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformer标题：VIT-TTS：具有可扩展扩散转换器的可视文本到语音转换链接：https://arxiv.org/abs/2305.12708

作者：Huadai Liu,Rongjie Huang,Xuan Lin,Wenqiang Xu,Maozong Zheng,Hong Chen,Jinzheng He,Zhou Zhao机构：Zhejiang University, AntGroup

【40】 On the Efficacy and Noise-Robustness of Jointly Learned Speech Emotion and Automatic Speech Recognition标题：联合学习语音情感和自动语音识别的有效性和抗噪性能研究链接：https://arxiv.org/abs/2305.12540

作者：Lokesh Bansal,S. Pavankumar Dubagunta,Malolan Chetlur,Pushpak Jagtap,Aravind Ganapathiraju机构：Uniphore Software Systems, India, Indian Institute of Science, Bengaluru, India备注：accepted to be part of INTERSPEECH 2023

【41】 Towards Robust Family-Infant Audio Analysis Based on Unsupervised Pretraining of Wav2vec 2.0 on Large-Scale Unlabeled Family Audio标题：基于Wav2vec 2.0对大规模无标签家庭音频的无监督预训练的稳健家庭-婴儿音频分析链接：https://arxiv.org/abs/2305.12530

作者：Jialu Li,Mark Hasegawa-Johnson,Nancy L. McElwain机构：Department of Electrical and Computer Engineering, University of Illinois, Beckman Institute for Advanced Science and Technology, University of Illinois, Department of Human Development and Family Studies, University of Illinois备注：Accepted to Interspeech 2023

【42】 Multi-Head State Space Model for Speech Recognition标题：用于语音识别的多头状态空间模型链接：https://arxiv.org/abs/2305.12498

作者：Yassir Fathullah,Chunyang Wu,Yuan Shangguan,Junteng Jia,Wenhan Xiong,Jay Mahadeokar,Chunxi Liu,Yangyang Shi,Ozlem Kalinli,Mike Seltzer,Mark J. F. Gales机构：University of Cambridge, UK, Meta AI, USA备注：Interspeech 2023

【43】 Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Network标题：基于语境短语预测网络的语境化端到端语音识别链接：https://arxiv.org/abs/2305.12493

作者：Kaixun Huang,Ao Zhang,Zhanheng Yang,Pengcheng Guo,Bingshen Mu,Tianyi Xu,Lei Xie机构：Northwestern Polytechnical University, Xi’an, China备注：Accepted by interspeech2023

【44】 CASA-ASR: Context-Aware Speaker-Attributed ASR标题：CASA-ASR：上下文感知的说话人属性ASR链接：https://arxiv.org/abs/2305.12459

作者：Mohan Shi,Zhihao Du,Qian Chen,Fan Yu,Yangze Li,Shiliang Zhang,Jie Zhang,Li-Rong Dai机构：Dai, NERC-SLIP, University of Science and Technology of China (USTC), China, Speech Lab of DAMO Academy, Alibaba Group, China备注：Accepted by Interspeech2023

【45】 Semantic VAD: Low-Latency Voice Activity Detection for Speech Interaction标题：语义VAD：面向语音交互的低延迟语音活动检测链接：https://arxiv.org/abs/2305.12450

作者：Mohan Shi,Yuchun Shu,Lingyun Zuo,Qian Chen,Shiliang Zhang,Jie Zhang,Li-Rong Dai机构：NERC-SLIP, University of Science and Technology of China (USTC), China, Tianjin University, China, Speech Lab, Alibaba Group, China备注：Accepted by Interspeech2023

【46】 DualVC: Dual-mode Voice Conversion using Intra-model Knowledge Distillation and Hybrid Predictive Coding标题：DualVC：基于模型内知识提取和混合预测编码的双模语音转换链接：https://arxiv.org/abs/2305.12425

作者：Ziqian Ning,Yuepeng Jiang,Pengcheng Zhu,Jixun Yao,Shuai Wang,Lei Xie,Mengxiao Bi机构：Northwestern Polytechnical University, Xi’an, China, Fuxi AI Lab, NetEase Inc., Hangzhou, China, Shenzhen Research Institute of Big Data, Shenzhen, China

【47】 DCCRN-KWS: an audio bias based model for noise robust small-footprint keyword spotting标题：DCCRN-KWS：一种基于音频偏差的抗噪小足迹关键词检测模型链接：https://arxiv.org/abs/2305.12331

作者：Shubo Lv,Xiong Wang,Sining Sun,Long Ma,Lei Xie机构：Northwestern Polytechnical University, Xi’an, China, Tencent Technology Co., Ltd, Beijing, China

【48】 Joint Generative-Contrastive Representation Learning for Anomalous Sound Detection标题：用于异常声音检测的生成-对比联合表征学习链接：https://arxiv.org/abs/2305.12111

作者：Xiao-Min Zeng,Yan Song,Zhu Zhuo,Yu Zhou,Yu-Hong Li,Hui Xue,Li-Rong Dai,Ian McLoughlin机构：National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China., ICT Cluster, Singapore Institute of Technology, Singapore., Alibaba Group, China.备注：Accepted by ICASSP2023

eess.AS音频处理

【1】 Debiased Automatic Speech Recognition for Dysarthric Speech via Sample Reweighting with Sample Affinity Test标题：基于样本重加权和样本亲和度检验的无偏自动语音识别链接：https://arxiv.org/abs/2305.13108

作者：Eungbeom Kim,Yunkee Chae,Jaeheon Sim,Kyogu Lee机构：IPAI,AIIS, Seoul National University, Seoul, Republic of Korea备注：Accepted by Interspeech 2023

【2】 ZS-MSTM: Zero-Shot Style Transfer for Gesture Animation driven by Text and Speech using Adversarial Disentanglement of Multimodal Style Encoding标题：ZS-MSTM：基于多模式风格编码对抗性解缠的文本和语音驱动手势动画的Zero-Shot风格转移链接：https://arxiv.org/abs/2305.12887

作者：Mireille Fares,Catherine Pelachaud,Nicolas Obin机构：ISIR, STMS, Sorbonne University, Paris, France, ISIR, CNRS备注：arXiv admin note: substantial text overlap with arXiv:2208.01917

【3】 An Enhanced Res2Net with Local and Global Feature Fusion for Speaker Verification标题：一种基于局部和全局特征融合的增强型Res2Net说话人确认链接：https://arxiv.org/abs/2305.12838

作者：Yafeng Chen,Siqi Zheng,Hui Wang,Luyao Cheng,Qian Chen,Jiajun Qi机构：Speech Lab, Alibaba Group, Hangzhou, China, University of Science and Technology of China, Hefei, China

【4】 Target Active Speaker Detection with Audio-visual Cues标题：基于视听线索的目标活动说话人检测链接：https://arxiv.org/abs/2305.12831

【5】 Zero-Shot End-to-End Spoken Language Understanding via Cross-Modal Selective Self-Training标题：通过跨通道选择性自我训练实现零射端到端口语理解链接：https://arxiv.org/abs/2305.12793

【6】 Coswara: A respiratory sounds and symptoms dataset for remote screening of SARS-CoV-2 infection标题：Coswara：用于SARS-CoV-2感染远程筛查的呼吸音和症状数据集链接：https://arxiv.org/abs/2305.12741

【7】 ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformer标题：VIT-TTS：具有可扩展扩散转换器的可视文本到语音转换链接：https://arxiv.org/abs/2305.12708

作者：Huadai Liu,Rongjie Huang,Xuan Lin,Wenqiang Xu,Maozong Zheng,Hong Chen,Jinzheng He,Zhou Zhao机构：Zhejiang University, AntGroup

【8】 On the Efficacy and Noise-Robustness of Jointly Learned Speech Emotion and Automatic Speech Recognition标题：联合学习语音情感和自动语音识别的有效性和抗噪性能研究链接：https://arxiv.org/abs/2305.12540

【9】 Towards Robust Family-Infant Audio Analysis Based on Unsupervised Pretraining of Wav2vec 2.0 on Large-Scale Unlabeled Family Audio标题：基于Wav2vec 2.0对大规模无标签家庭音频的无监督预训练的稳健家庭-婴儿音频分析链接：https://arxiv.org/abs/2305.12530

【10】 Multi-Head State Space Model for Speech Recognition标题：用于语音识别的多头状态空间模型链接：https://arxiv.org/abs/2305.12498

【11】 Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Network标题：基于语境短语预测网络的语境化端到端语音识别链接：https://arxiv.org/abs/2305.12493

作者：Kaixun Huang,Ao Zhang,Zhanheng Yang,Pengcheng Guo,Bingshen Mu,Tianyi Xu,Lei Xie机构：Northwestern Polytechnical University, Xi’an, China备注：Accepted by interspeech2023

【12】 CASA-ASR: Context-Aware Speaker-Attributed ASR标题：CASA-ASR：上下文感知的说话人属性ASR链接：https://arxiv.org/abs/2305.12459

【13】 Semantic VAD: Low-Latency Voice Activity Detection for Speech Interaction标题：语义VAD：面向语音交互的低延迟语音活动检测链接：https://arxiv.org/abs/2305.12450

【14】 DualVC: Dual-mode Voice Conversion using Intra-model Knowledge Distillation and Hybrid Predictive Coding标题：DualVC：基于模型内知识提取和混合预测编码的双模语音转换链接：https://arxiv.org/abs/2305.12425

【15】 DCCRN-KWS: an audio bias based model for noise robust small-footprint keyword spotting标题：DCCRN-KWS：一种基于音频偏差的抗噪小足迹关键词检测模型链接：https://arxiv.org/abs/2305.12331

作者：Shubo Lv,Xiong Wang,Sining Sun,Long Ma,Lei Xie机构：Northwestern Polytechnical University, Xi’an, China, Tencent Technology Co., Ltd, Beijing, China

【16】 Joint Generative-Contrastive Representation Learning for Anomalous Sound Detection标题：用于异常声音检测的生成-对比联合表征学习链接：https://arxiv.org/abs/2305.12111

【17】 Modulation Extraction for LFO-driven Audio Effects标题：用于LFO驱动音频效果的调制提取链接：https://arxiv.org/abs/2305.13262

【18】 Computational models of sound-quality metrics using method for calculating loudness with gammatone/gammachirp auditory filterbank标题：用Gammatone/Gammachirp听觉滤波器组计算响度的声音质量度量的计算模型链接：https://arxiv.org/abs/2305.13213

【19】 Learning to detect an animal sound from five examples标题：从五个例子中学习检测动物的声音链接：https://arxiv.org/abs/2305.13210

【20】 Improving Isochronous Machine Translation with Target Factors and Auxiliary Counters标题：利用目标因素和辅助计数器改进等时机器翻译链接：https://arxiv.org/abs/2305.13204

【21】 U-DiT TTS: U-Diffusion Vision Transformer for Text-to-Speech标题：U-DIT TTS：用于文本到语音的U-扩散视觉转换器链接：https://arxiv.org/abs/2305.13195

【22】 AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation标题：AudioToken：文本条件扩散模型在音像生成中的应用链接：https://arxiv.org/abs/2305.13050

【23】 Towards generalizing deep-audio fake detection networks标题：走向大众化的深度音频伪装检测网络链接：https://arxiv.org/abs/2305.13033

作者：Konstantin Gasenzer,Moritz Wolter机构：High Performance Computing, and Analytics Lab, Universität Bonn, Germany

【24】 Textually Pretrained Speech Language Models标题：文本预训练语音语言模型链接：https://arxiv.org/abs/2305.13009

【25】 Exploring Speaker-Related Information in Spoken Language Understanding for Better Speaker Diarization标题：在口语理解中探索与说话人相关的信息以更好地实现说话人二元化链接：https://arxiv.org/abs/2305.12927

作者：Luyao Cheng,Siqi Zheng,Zhang Qinglin,Hui Wang,Yafeng Chen,Qian Chen机构：Speech Lab of DAMO Academy, Alibaba Group备注：Accepted to Findings of ACL 2023

【26】 NAS-FM: Neural Architecture Search for Tunable and Interpretable Sound Synthesis based on Frequency Modulation标题：NAS-FM：基于调频的可调谐和可解释声音合成的神经结构研究链接：https://arxiv.org/abs/2305.12868

【27】 The defender's perspective on automatic speaker verification: An overview标题：辩护人对自动说话人确认的观点：综述链接：https://arxiv.org/abs/2305.12804

【28】 GNCformer Enhanced Self-attention for Automatic Speech Recognition标题：用于自动语音识别的GNCformer增强的自我注意链接：https://arxiv.org/abs/2305.12755

作者：J. Li,Z. Duan,S. Li,X. Yu,G. Yang机构：Shiren Li is from Sun Yat-Sen University备注：5 pages,3 figures,

【29】 LEAN: Light and Efficient Audio Classification Network标题：LEAN：轻便高效的音频分类网络链接：https://arxiv.org/abs/2305.12712

作者：Shwetank Choudhary,CR Karthik,Punuru Sri Lakshmi,Sumit Kumar机构：Samsung R&D Institute, Bangalore, India备注：Accepted at INDICON 2022

【30】 Progressive Sub-Graph Clustering Algorithm for Semi-Supervised Domain Adaptation Speaker Verification标题：半监督域自适应说话人确认的递进子图聚类算法链接：https://arxiv.org/abs/2305.12703

【31】 More Perspectives Mean Better: Underwater Target Recognition and Localization with Multimodal Data via Symbiotic Transformer and Multiview Regression标题：视角越多越好：基于共生变换和多视角回归的多模式数据水下目标识别与定位链接：https://arxiv.org/abs/2305.12701

作者：Shipei Liu,Xiaoya Fan,Guowei Wu

【32】 The HCCL system for VoxCeleb Speaker Recognition Challenge 2022标题：VoxCeleb说话人识别挑战赛2022的HCCL系统链接：https://arxiv.org/abs/2305.12642

【33】 Duplex Diffusion Models Improve Speech-to-Speech Translation标题：双向扩散模型改进了语音到语音的翻译链接：https://arxiv.org/abs/2305.12628

作者：Xianchao Wu机构：NVIDIA备注：11 pages, 3 figures. Accepted by ACL 2023 findings

【34】 Comparison of Multilingual Self-Supervised and Weakly-Supervised Speech Pre-Training for Adaptation to Unseen Languages标题：多语种自我监督和弱监督语音预训练对看不见语言适应的比较链接：https://arxiv.org/abs/2305.12606

【35】 Hystoc: Obtaining word confidences for fusion of end-to-end ASR systems标题：Hystoc：获得端到端ASR系统融合的单词置信度链接：https://arxiv.org/abs/2305.12579

作者：Karel Beneš,Martin Kocour,Lukáš Burget机构：Brno University of Technology, Czechia

【36】 Wav2SQL: Direct Generalizable Speech-To-SQL Parsing标题：Wav2SQL：直接可泛化的语音到SQL解析链接：https://arxiv.org/abs/2305.12552

作者：Huadai Liu,Rongjie Huang,Jinzheng He,Gang Sun,Ran Shen,Xize Cheng,Zhou Zhao机构：Zhejiang University ,State Grid Corporation of China

【37】 Towards robust paralinguistic assessment for real-world mobile health (mHealth) monitoring: an initial study of reverberation effects on speech标题：用于真实世界移动健康(MHealth)监测的稳健副语言评估：混响对语音影响的初步研究链接：https://arxiv.org/abs/2305.12514

【38】 Exploring How Generative Adversarial Networks Learn Phonological Representations标题：探索生成性对抗性网络如何学习语音表征链接：https://arxiv.org/abs/2305.12501

作者：Jingyi Chen,Micha Elsner机构：Department of Linguistics, The Ohio State University

【39】 Study of GANs for Noisy Speech Simulation from Clean Speech标题：基于清洁语音的带噪语音模拟遗传算法研究链接：https://arxiv.org/abs/2305.12460

【40】 JNV Corpus: A Corpus of Japanese Nonverbal Vocalizations with Diverse Phrases and Emotions标题：JNV语料库：日语非言语发声语料库链接：https://arxiv.org/abs/2305.12445

作者：Detai Xin,Shinnosuke Takamichi,Hiroshi Saruwatari机构：Graduate School of Information Science and Technology, The University of Tokyo, Japan备注：4 pages, 3 figures

【41】 Laughter Synthesis using Pseudo Phonetic Tokens with a Large-scale In-the-wild Laughter Corpus标题：利用大规模野外笑声语料库的伪音标词合成笑声链接：https://arxiv.org/abs/2305.12442

【42】 i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data标题：I-Code V2：一种基于视觉、语言和语音数据的自回归生成框架链接：https://arxiv.org/abs/2305.12311

作者：Ziyi Yang,Mahmoud Khademi,Yichong Xu,Reid Pryzant,Yuwei Fang,Chenguang Zhu,Dongdong Chen,Yao Qian,Mei Gao,Yi-Ling Chen,Robert Gmyr,Naoyuki Kanda,Noel Codella,Bin Xiao,Yu Shi,Lu Yuan,Takuya Yoshioka,Michael Zeng,Xuedong Huang机构：Microsoft Azure Cognitive Services Research

【43】 Sentence Embedder Guided Utterance Encoder (SEGUE) for Spoken Language Understanding标题：用于口语理解的语句嵌入器引导的话语编码器(SEGUE)链接：https://arxiv.org/abs/2305.12301

作者：Yi Xuan Tan,Navonil Majumder,Soujanya Poria机构：Singapore University of Technology and Design, Singapore备注：Interspeech 2023

【44】 Self-supervised representations in speech-based depression detection标题：自监督表示在基于语音的抑郁检测中的应用链接：https://arxiv.org/abs/2305.12263

作者：Wen Wu,Chao Zhang,Philip C. Woodland机构：Department of Engineering, University of Cambridge, Trumpington St., Cambridge, UK.

【45】 ComedicSpeech: Text To Speech For Stand-up Comedies in Low-Resource Scenarios标题：ComedicSpeech：在低资源场景下为单口喜剧提供文本到语音转换链接：https://arxiv.org/abs/2305.12200

【46】 ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attention标题：ACA-Net：基于非对称交叉注意力的轻量级说话人确认链接：https://arxiv.org/abs/2305.12121

【47】 EE-TTS: Emphatic Expressive TTS with Linguistic Information标题：EE-TTS：带有语言信息的强调表达的TTS链接：https://arxiv.org/abs/2305.12107

作者：Yi Zhong,Chen Zhang,Xule Liu,Chenxi Sun,Weishan Deng,Haifeng Hu,Zhongqian Sun机构：Tencent AI Lab, ShenZhen, China, Zhejiang University, China备注：Accepted by INTERSPEECH2023

【48】 MParrotTTS: Multilingual Multi-speaker Text to Speech Synthesis in Low Resource Setting标题：MParrotTTS：低资源环境下的多语言多说话人文语合成链接：https://arxiv.org/abs/2305.11926

机器翻译，仅供参考

语音/音频处理学术速递[5.23]

评论 0