音频处理学术速递[9.26]

• 阅读： 2023/9/27 9:38:19

  eess.AS音频处理，共计44篇

  【1】 Towards General-Purpose Text-Instruction-Guided Voice Conversion

  链接：https://arxiv.org/abs/2309.14324

  作者：Chun-Yi Kuan, Chen An Li, Tsu-Yuan Hsu, Tse-Yang Lin, Ho-Lam Chung, Kai-Wei Chang, Shuo-yiin Chang, Hung-yi Lee

  备注：Accepted to ASRU 2023

  【2】 Speaker anonymization using neural audio codec language models

  链接：https://arxiv.org/abs/2309.14129

  作者：Michele Panariello, Francesco Nespoli, Massimiliano Todisco, Nicholas Evans

  备注：Submitted to ICASSP 2024

  【3】 Haha-Pod: An Attempt for Laughter-based Non-Verbal Speaker Verification

  链接：https://arxiv.org/abs/2309.14109

  作者：Yuke Lin, Xiaoyi Qin, Ning Jiang, Guoqing Zhao, Ming Li

  备注：accepted by ASRU 2023

  【4】 Wav2vec-based Detection and Severity Level Classification of Dysarthria from Speech

  链接：https://arxiv.org/abs/2309.14107

  作者：Farhad Javanmardi, Saska Tirronen, Manila Kodali, Sudarsana Reddy Kadiri, Paavo Alku

  【5】 BiSinger: Bilingual Singing Voice Synthesis

  链接：https://arxiv.org/abs/2309.14089

  作者：Huali Zhou, Yueqian Lin, Yao Shi, Peng Sun, Ming Li

  备注：Accepted by ASRU2023

  【6】 Analysis and Detection of Pathological Voice using Glottal Source Features

  链接：https://arxiv.org/abs/2309.14080

  作者：Sudarsana Reddy Kadiri, Paavo Alku

  【7】 Unsupervised Accent Adaptation Through Masked Language Model Correction Of Discrete Self-Supervised Speech Units

  链接：https://arxiv.org/abs/2309.13994

  作者：Jakob Poncelet, Hugo Van hamme

  备注：Submitted to ICASSP2024

  【8】 Connecting Speech Encoder and Large Language Model for ASR

  链接：https://arxiv.org/abs/2309.13963

  作者：Wenyi Yu, Changli Tang, Guangzhi Sun, Xianzhao Chen, Tian Tan, Wei Li, Lu Lu, Zejun Ma, Chao Zhang

  【9】 Evaluating Classification Systems Against Soft Labels with Fuzzy Precision and Recall

  链接：https://arxiv.org/abs/2309.13938

  作者：Manu Harju, Annamaria Mesaros

  备注：published in DCASE 2023

  【10】 Frame-wise streaming end-to-end speaker diarization with non-autoregressive self-attention-based attractors

  链接：https://arxiv.org/abs/2309.13916

  作者：Di Liang, Nian Shao, Xiaofei Li

  【11】 AutoPrep: An Automatic Preprocessing Framework for In-the-Wild Speech Data

  链接：https://arxiv.org/abs/2309.13905

  作者：Jianwei Yu, Hangting Chen, Yanyao Bian, Xiang Li, Yi Luo, Jinchuan Tian, Mengyang Liu, Jiayi Jiang, Shuai Wang

  【12】 Diffusion Conditional Expectation Model for Efficient and Robust Target Speech Extraction

  链接：https://arxiv.org/abs/2309.13874

  作者：Leying Zhang, Yao Qian, Linfeng Yu, Heming Wang, Xinkai Wang, Hemin Yang, Long Zhou, Shujie Liu, Yanmin Qian, Michael Zeng

  备注：Submitted to ICASSP 2024

  【13】 A Two-Step Approach for Narrowband Source Localization in Reverberant Rooms

  链接：https://arxiv.org/abs/2309.13819

  作者：Wei-Ting Lai, Lachlan Birnie, Thushara Abhayapala, Amy Bastine, Shaoheng Xu, Prasanga Samarasinghe

  【14】 VoiceLDM: Text-to-Speech with Environmental Context

  链接：https://arxiv.org/abs/2309.13664

  作者：Yeonghyeon Lee, Inmo Yeon, Juhan Nam, Joon Son Chung

  备注：Demos and code are available at this https URL

  【15】 Cross-modal Alignment with Optimal Transport for CTC-based ASR

  链接：https://arxiv.org/abs/2309.13650

  作者：Xugang Lu, Peng Shen, Yu Tsao, Hisashi Kawai

  备注：Accepted to IEEE ASRU 2023

  【16】 Efficient Black-Box Speaker Verification Model Adaptation with Reprogramming and Backend Learning

  链接：https://arxiv.org/abs/2309.13605

  作者：Jingyu Li, Tan Lee

  【17】 Speech enhancement with frequency domain auto-regressive modeling

  链接：https://arxiv.org/abs/2309.13537

  作者：Anurenjan Purushothaman, Debottam Dutta, Rohit Kumar, Sriram Ganapathy

  备注：10 pages

  【18】 Attention Is All You Need For Blind Room Volume Estimation

  链接：https://arxiv.org/abs/2309.13504

  作者：Chunxi Wang, Maoshen Jia, Meiran Li, Changchun Bao, Wenyu Jin

  备注：5 pages, 4 figures, submitted ICASSP 2024

  【19】 Contrastive Speaker Embedding With Sequential Disentanglement

  链接：https://arxiv.org/abs/2309.13253

  作者：Youzhi Tu, Man-Wai Mak, Jen-Tzung Chien

  备注：Submitted to ICASSP 2024

  【20】 Importance of Smoothness Induced by Optimizers in FL4ASR: Towards Understanding Federated Learning for End-to-End ASR

  链接：https://arxiv.org/abs/2309.13102

  作者：Sheikh Shams Azam, Tatiana Likhomanenko, Martin Pelikan, Jan "Honza" Silovsky

  备注：In Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) 2023

  【21】 An Investigation of Distribution Alignment in Multi-Genre Speaker Recognition

  链接：https://arxiv.org/abs/2309.14158

  作者：Zhenyu Zhou, Junhui Chen, Namin Wang, Lantian Li, Dong Wang

  备注：submitted to ICASSP 2024

  【22】 Multi-Domain Adaptation by Self-Supervised Learning for Speaker Verification

  链接：https://arxiv.org/abs/2309.14149

  作者：Wan Lin, Lantian Li, Dong Wang

  备注：submitted to ICASSP 2024

  【23】 On the Relation between Internal Language Model and Sequence Discriminative Training for Neural Transducers

  链接：https://arxiv.org/abs/2309.14130

  作者：Zijian Yang, Wei Zhou, Ralf Schlüter, Hermann Ney

  备注：submitted to ICASSP 2024

  【24】 VoiceLens: Controllable Speaker Generation and Editing with Flow

  链接：https://arxiv.org/abs/2309.14094

  作者：Yao Shi, Ming Li

  【25】 Audio classification with Dilated Convolution with Learnable Spacings

  链接：https://arxiv.org/abs/2309.13972

  作者：Ismail Khalfaoui-Hassani, Timothée Masquelier, Thomas Pellegrini

  【26】 Speed Co-Augmentation for Unsupervised Audio-Visual Pre-training

  链接：https://arxiv.org/abs/2309.13942

  作者：Jiangliu Wang, Jianbo Jiao, Yibing Song, Stephen James, Zhan Tong, Chongjian Ge, Pieter Abbeel, Yun-hui Liu

  备注：Published at the CVPR 2023 Sight and Sound workshop

  【27】 Real-Time Emergency Vehicle Detection using Mel Spectrograms and Regular Expressions

  链接：https://arxiv.org/abs/2309.13920

  作者：Alberto Pacheco-Gonzalez, Raymundo Torres, Raul Chacon, Isidro Robledo

  备注：in Spanish language

  【28】 HiGNN-TTS: Hierarchical Prosody Modeling with Graph Neural Networks for Expressive Long-form TTS

  链接：https://arxiv.org/abs/2309.13907

  作者：Dake Guo, Xinfa Zhu, Liumeng Xue, Tao Li, Yuanjun Lv, Yuepeng Jiang, Lei Xie

  备注：Accepted by ASRU2023

  【29】 Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data

  链接：https://arxiv.org/abs/2309.13876

  作者：Yifan Peng, Jinchuan Tian, Brian Yan, Dan Berrebbi, Xuankai Chang, Xinjian Li, Jiatong Shi, Siddhant Arora, William Chen, Roshan Sharma, Wangyou Zhang, Yui Sudo, Muhammad Shakeel, Jee-weon Jung, Soumi Maiti, Shinji Watanabe

  备注：Accepted at ASRU 2023

  【30】 Fast-HuBERT: An Efficient Training Framework for Self-Supervised Speech Representation Learning

  链接：https://arxiv.org/abs/2309.13860

  作者：Guanrou Yang, Ziyang Ma, Zhisheng Zheng, Yakun Song, Zhikang Niu, Xie Chen

  【31】 The second multi-channel multi-party meeting transcription challenge (M2MeT) 2.0): A benchmark for speaker-attributed ASR

  链接：https://arxiv.org/abs/2309.13573

  作者：Yuhao Liang, Mohan Shi, Fan Yu, Yangze Li, Shiliang Zhang, Zhihao Du, Qian Chen, Lei Xie, Yanmin Qian, Jian Wu, Zhuo Chen, Kong Aik Lee, Zhijie Yan, Hui Bu

  备注：8 pages, Accepted by ASRU2023

  【32】 Related Rhythms: Recommendation System To Discover Music You May Like

  链接：https://arxiv.org/abs/2309.13544

  作者：Rahul Singh, Pranav Kanuparthi

  【33】 Coco-Nut: Corpus of Japanese Utterance and Voice Characteristics Description for Prompt-based Control

  链接：https://arxiv.org/abs/2309.13509

  作者：Aya Watanabe, Shinnosuke Takamichi, Yuki Saito, Wataru Nakata, Detai Xin, Hiroshi Saruwatari

  备注：Submitted to ASRU2023

  【34】 Hierarchical attention interpretation: an interpretable speech-level transformer for bi-modal depression detection

  链接：https://arxiv.org/abs/2309.13476

  作者：Qingkun Deng, Saturnino Luz, Sofia de la Fuente Garcia

  备注：5 pages, 3 figures, submitted to IEEE International Conference on Acoustics, Speech, and Signal Processing

  【35】 Asca: less audio data is more insightful

  链接：https://arxiv.org/abs/2309.13373

  作者：Xiang Li, Junhao Chen, Chao Li, Hongwu Lv

  备注：6 pages,3 figures

  【36】 My Science Tutor (MyST) -- A Large Corpus of Children's Conversational Speech

  链接：https://arxiv.org/abs/2309.13347

  作者：Sameer S. Pradhan, Ronald A. Cole, Wayne H. Ward

  【37】 Two vs. Four-Channel Sound Event Localization and Detection

  链接：https://arxiv.org/abs/2309.13343

  作者：Julia Wilkins, Magdalena Fuentes, Luca Bondi, Shabnam Ghaffarzadegan, Ali Abavisani, Juan Pablo Bello

  【38】 Beyond Fairness: Age-Harmless Parkinson's Detection via Voice

  链接：https://arxiv.org/abs/2309.13292

  作者：Yicheng Wang, Xiaotian Han, Leisheng Yu, Na Zou

  【39】 WikiMT++ Dataset Card

  链接：https://arxiv.org/abs/2309.13259

  作者：Monan Zhou, Shangda Wu, Yuan Wang, Wei Li

  【40】 Importance of negative sampling in weak label learning

  链接：https://arxiv.org/abs/2309.13227

  作者：Ankit Shah, Fuyu Tang, Zelin Ye, Rita Singh, Bhiksha Raj

  【41】 Invisible Watermarking for Audio Generation Diffusion Models

  链接：https://arxiv.org/abs/2309.13166

  作者：Xirong Cao, Xiang Li, Divyesh Jadav, Yanzhao Wu, Zhehui Chen, Chen Zeng, Wenqi Wei

  备注：This is an invited paper for IEEE TPS, part of the IEEE CIC/CogMI/TPS 2023 conference

  【42】 Towards Lexical Analysis of Dog Vocalizations via Online Videos

  链接：https://arxiv.org/abs/2309.13086

  作者：Yufei Wang, Chunhao Zhang, Jieyi Huang, Mengyue Wu, Kenny Zhu

  【43】 Does My Dog ''Speak'' Like Me? The Acoustic Correlation between Pet Dogs and Their Human Owners

  链接：https://arxiv.org/abs/2309.13085

  作者：Jieyi Huang, Chunhao Zhang, Yufei Wang, Mengyue Wu, Kenny Zhu

  【44】 Applied design thinking in urban air mobility: creating the airtaxi cabin design of the future from a user perspective

  链接：https://arxiv.org/abs/2309.05353

  作者：F.Reimer, J.Herzig, L.Winkler, J.Biedermann, F.Meller, B.Nagel

  备注：13 pages

  转自：“arXiv每日学术速递”微信公众号

  如有侵权，请联系本站删除！

  
  

  浏览(170)

  点赞(0)

  收藏(0)