cs.SD语音，共计5篇

eess.AS音频处理，共计7篇

1.cs.SD语音:

【1】 Physics-Informed Neural Networks (PINNs) for Sound Field Predictions with Parameterized Sources and Impedance Boundaries具有参数化源和阻抗边界的物理信息神经网络(PINN)声场预测链接：https://arxiv.org/abs/2109.11313作者：Nikolas Borrel-Jensen,Allan P. Engsig-Karup,Cheol-Ho Jeong机构：)Acoustic Technology, Department of Electrical Engineering, Technical, University of Denmark, Kongens Lyngby, Denmark, )Department of Applied Mathematics and Computer Science, Technical备注：19 pages (double line spacing), 3 figures, 2 tables

【2】 Joint speaker diarisation and tracking in switching state-space model切换状态空间模型中的联合说话人跟踪链接：https://arxiv.org/abs/2109.11140作者：Jeremy H. M. Wong,Yifan Gong机构：Microsoft, USA

【3】 Unet-TTS: Improving Unseen Speaker and Style Transfer in One-shot Voice CloningUNET-TTS：改进一次语音克隆中看不见的说话人和风格转移链接：https://arxiv.org/abs/2109.11115作者：Rui Li,Dong Pu,Minnie Huang,Bill Huang机构：CloudMinds Inc., China备注：6 pages, 5 figures, Submitted to IEEE ICASSP 2022

【4】 Scenario Aware Speech Recognition: Advancements for Apollo Fearless Steps & CHiME-4 Corpora情景感知语音识别：Apollo Fearless Steps和CHAME-4语料库的进展链接：https://arxiv.org/abs/2109.11086作者：Szu-Jui Chen,Wei Xia,John H. L. Hansen机构：Center for Robust Speech Systems (CRSS), University of Texas at Dallas, TX 备注：Accepted for ASRU 2021

【5】 Alzheimers Dementia Detection using Acoustic & Linguistic features and Pre-Trained BERT基于声学语言特征和预训练BERT的阿尔茨海默病检测链接：https://arxiv.org/abs/2109.11010作者：Akshay Valsaraj,Ithihas Madala,Nikhil Garg,Veeky Baths机构：Cognitive Neuroscience Lab, BITS Pilani, K.K. Birla Goa Campus, Goa, India

2.eess.AS音频处理:

【1】 ChannelAugment: Improving generalization of multi-channel ASR by training with input channel randomization信道增强：通过输入信道随机化训练改进多信道ASR的泛化链接：https://arxiv.org/abs/2109.11225作者：Marco Gaudesi,Felix Weninger,Dushyant Sharma,Puming Zhan机构：Nuance Communications备注：To appear in ASRU 2021

【2】 Unified Signal Compression Using a GAN with Iterative Latent Representation Optimization基于迭代隐含表示优化的GAN统一信号压缩链接：https://arxiv.org/abs/2109.11168作者：Bowen Liu,Changwoo Lee,Ang Cao,Hun-Seok Kim机构： Kim are with the Department of Electricaland Computer Engineering, University of Michigan备注：13 pages, 10 figures

【3】 Lightweight dynamic filter for keyword spotting用于关键词定位的轻量级动态过滤链接：https://arxiv.org/abs/2109.11165作者：Donghyeon Kim,Kyungdeuk Ko,David K. Han,Hanseok Ko机构：School of Electrical Engineering, Korea University, Seoul, South Korea, Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA USA备注：5 pages, 1 figure, 4 tables, ICASSP 2022 conference

【4】 Masks Fusion with Multi-Target Learning For Speech Enhancement基于多目标学习的掩模融合语音增强链接：https://arxiv.org/abs/2109.11164作者：Liangchen Zhou,Wenbin Jiang,Jingyan Xu,Fei Wen,Peilin Liu机构：Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China, Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China

【5】 Physics-Informed Neural Networks (PINNs) for Sound Field Predictions with Parameterized Sources and Impedance Boundaries具有参数化源和阻抗边界的物理信息神经网络(PINN)声场预测链接：https://arxiv.org/abs/2109.11313作者：Nikolas Borrel-Jensen,Allan P. Engsig-Karup,Cheol-Ho Jeong机构：)Acoustic Technology, Department of Electrical Engineering, Technical, University of Denmark, Kongens Lyngby, Denmark, )Department of Applied Mathematics and Computer Science, Technical备注：19 pages (double line spacing), 3 figures, 2 tables

【6】 Unet-TTS: Improving Unseen Speaker and Style Transfer in One-shot Voice CloningUNET-TTS：改进一次语音克隆中看不见的说话人和风格转移链接：https://arxiv.org/abs/2109.11115作者：Rui Li,Dong Pu,Minnie Huang,Bill Huang机构：CloudMinds Inc., China备注：6 pages, 5 figures, Submitted to IEEE ICASSP 2022

【7】 Scenario Aware Speech Recognition: Advancements for Apollo Fearless Steps & CHiME-4 Corpora情景感知语音识别：Apollo Fearless Steps和CHAME-4语料库的进展链接：https://arxiv.org/abs/2109.11086作者：Szu-Jui Chen,Wei Xia,John H. L. Hansen机构：Center for Robust Speech Systems (CRSS), University of Texas at Dallas, TX 备注：Accepted for ASRU 2021

机器翻译，仅供参考