ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)最新文献_第5页

SS-ADMM: Stationary and Sparse Granger Causal Discovery for Cortico-Muscular Coupling SS-ADMM:皮质-肌肉耦合的平稳稀疏格兰杰因果发现

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10095111

Farwa Abbas, V. McClelland, Z. Cvetkovic, Wei Dai

引用次数: 0

LeanSpeech: The Microsoft Lightweight Speech Synthesis System for Limmits Challenge 2023 LeanSpeech:微软轻量级语音合成系统的极限挑战赛2023

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10096039

Chen Zhang, Shubham Bansal, Aakash Lakhera, Jinzhu Li, G. Wang, Sandeepkumar Satpal, Sheng Zhao, Lei He

引用次数: 0

Defending Against Universal Patch Attacks by Restricting Token Attention in Vision Transformers 通过限制视觉变形器中的令牌注意力来防御通用补丁攻击

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10096862

Hongwei Yu, Jiansheng Chen, Huimin Ma, Cheng Yu, Xinlong Ding

引用次数: 1

SEPDIFF: Speech Separation Based on Denoising Diffusion Model 基于去噪扩散模型的语音分离

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10095979

Bo-Cheng Chen, Chao Wu, Wenbin Zhao

引用次数: 0

A Graph Neural Network Multi-Task Learning-Based Approach for Detection and Localization of Cyberattacks in Smart Grids 基于图神经网络多任务学习的智能电网网络攻击检测与定位方法

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10096822

Abdulrahman Takiddin, R. Atat, Muhammad Ismail, K. Davis, E. Serpedin

引用次数: 1

Hankel Structured Low Rank and Sparse Representation Via L0-Norm Optimization for Compressed Ultrasound Plane Wave Signal Reconstruction 基于l0范数优化的压缩超声平面波信号重构的Hankel结构低秩稀疏表示

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10095071

Miaomiao Zhang, Ji Chen, Xiaoyan Fu, Ge Xin, Jingzhi Zhang, Na Jiang, J. D’hooge

{"title":"Hankel Structured Low Rank and Sparse Representation Via L0-Norm Optimization for Compressed Ultrasound Plane Wave Signal Reconstruction","authors":"Miaomiao Zhang, Ji Chen, Xiaoyan Fu, Ge Xin, Jingzhi Zhang, Na Jiang, J. D’hooge","doi":"10.1109/ICASSP49357.2023.10095071","DOIUrl":"https://doi.org/10.1109/ICASSP49357.2023.10095071","url":null,"abstract":"Ultrasound plane wave imaging is widely used in many applications thanks to its capability in reaching high frame rates. However, the amount of data acquisition and storage in a period of time can become a bottleneck in ultrasound system design for thousands frames per second. In our previous study, we proposed a low-rank and joint-sparse model to reduce the amount of sampled channel data of focused beam imaging by considering all the received data as a 2D matrix. However, for a single plane wave transmission, the number of channels is limited and the low-rank property of the received data matrix is no longer achieved. In this study, a L0-norm based Hankel structured low-rank and sparse model is proposed to reduce the channel data. An optimization algorithm, based on the alternating direction method of multipliers (ADMM), is proposed to efficiently solve the resulting optimization problem. The performance of the proposed approach was evaluated using the data published in Plane Wave Imaging Challenge in Medical Ultrasound (PICMUS) in 2016. Results on channel and plane wave data show that the proposed method is better adapted to the ultrasound channel signal and can recover the image with fewer samples than the conventional CS method.","PeriodicalId":113072,"journal":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"11 18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116824222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Effective Training of RNN Transducer Models on Diverse Sources of Speech and Text Data RNN换能器模型在不同语音和文本数据源上的有效训练

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10095218

Takashi Fukuda, Samuel Thomas

{"title":"Effective Training of RNN Transducer Models on Diverse Sources of Speech and Text Data","authors":"Takashi Fukuda, Samuel Thomas","doi":"10.1109/ICASSP49357.2023.10095218","DOIUrl":"https://doi.org/10.1109/ICASSP49357.2023.10095218","url":null,"abstract":"This paper proposes a novel modeling framework for effective training of end-to-end automatic speech recognition (ASR) models on various sources of data from diverse domains: speech paired with clean ground truth transcripts, speech with noisy pseudo transcripts from semi-supervised decodes and unpaired text-only data. In our proposed approach, we build a recurrent neural network transducer (RNN-T) model with a shared multimodal encoder, multi-branch prediction networks and a shared common joint network. To train on unpaired text-only data sets along with transcribed speech data, the shared encoder is trained to process both speech and text modalities. Differences in data from multiple domains are effectively handled by training a multi-branch prediction network on various different data sets before an interpolation step combines the multi-branch prediction networks back into a computationally-efficient single branch. We show the benefit of our proposed technique on several ASR test sets by comparing our models to those trained by simple data mixing. The technique provides a significant relative improvement of up to 6% over baseline systems operating at a similar decoding cost.","PeriodicalId":113072,"journal":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117077621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Conditional LS-GAN Based Skylight Polarization Image Restoration and Application in Meridian Localization 基于条件LS-GAN的天窗偏振图像恢复及其在子午线定位中的应用

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10096855

T. Yang, Hongbo Bo, Xinyu Yang, Jun Gao, Zijian Shi

引用次数: 1

Implicitly Rotation Equivariant Neural Networks 隐式旋转等变神经网络

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10095020

Naman Khetan, Tushar Arora, S. U. Rehman, Deepak K. Gupta

{"title":"Implicitly Rotation Equivariant Neural Networks","authors":"Naman Khetan, Tushar Arora, S. U. Rehman, Deepak K. Gupta","doi":"10.1109/ICASSP49357.2023.10095020","DOIUrl":"https://doi.org/10.1109/ICASSP49357.2023.10095020","url":null,"abstract":"Convolutional Neural Networks (CNN) are inherently equivariant under translations, however, they do not have an equivalent embedded mechanism to handle other transformations such as rotations. The existing solutions require redesigning standard networks with filters mapped from combinations of predefined basis involving complex analytical functions. Such formulations are hard to implement as well as the imposed restrictions in the choice of basis can lead to model weights that are sub-optimal for the primary deep learning task (e.g. classification). We propose Implicitly Equivariant Network (IEN) which induces approximate equivariance in the different layers of a standard CNN by optimizing a multi-objective loss function. We show for ResNet models on Rot-MNIST and Rot-TinyImageNet that even with its simple formulation, IEN performs at par or even better than steerable networks. Also, IEN facilitates construction of heterogeneous filter groups allowing reduction in the number of channels in CNNs by a factor of over 30%. Further, we demonstrate that for the hard problem of visual object tracking, IEN outperforms the state-of-the-art rotation equivariant tracking method while providing faster inference speed.","PeriodicalId":113072,"journal":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129518166","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Surrogate Based Post-HOC Calibration for Distributional Shift 基于代理的分布位移事后校正

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/icassp49357.2023.10096090

Jun Zhang

引用次数: 0