ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)最新文献_第9页

MSN-net: Multi-Scale Normality Network for Video Anomaly Detection 用于视频异常检测的多尺度正态网络

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10097052

Y. Liu, Di Li, Wei Zhu, Dingkang Yang, Jing Liu, Liang Song

引用次数: 3

Robust Log-Based Anomaly Detection with Hierarchical Contrastive Learning 基于层次对比学习的鲁棒日志异常检测

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/icassp49357.2023.10094961

Yuhui Zhao, Ruichun Yang, Ning Yang, Tao Lin, Qiuai Fu, Yuchi Ma

引用次数: 1

Tensor Completion for Efficient and Accurate Hyperparameter Optimisation in Large-Scale Statistical Learning 大规模统计学习中高效准确超参数优化的张量补全

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10096491

Aaman Rebello, Kriton Konstantinidis, Y. Xu, D. Mandic

{"title":"Tensor Completion for Efficient and Accurate Hyperparameter Optimisation in Large-Scale Statistical Learning","authors":"Aaman Rebello, Kriton Konstantinidis, Y. Xu, D. Mandic","doi":"10.1109/ICASSP49357.2023.10096491","DOIUrl":"https://doi.org/10.1109/ICASSP49357.2023.10096491","url":null,"abstract":"Hyperparameter optimisation is a prerequisite for state-of-the- art performance in machine learning, with current strategies including Bayesian optimisation, hyperband, and evolutionary methods. While such methods have been shown to improve performance, none of these is designed to explicitly take advantage of the underlying data structure. To this end, we introduce a completely different approach for hyperparameter optimisation, based on low-rank tensor completion. This is achieved by first forming a multi-dimensional tensor which comprises performance scores for different combinations of hyperparameters. Based on the realistic underlying assumption that the so-formed tensor has a low-rank structure, reliable estimates of the unobserved validation scores of combinations of hyper- parameters are next obtained through tensor completion, from only a fraction of the known elements in the tensor. Through extensive experimentation on various datasets and learning models, the proposed method is shown to exhibit competitive or superior performance to state-of-the-art hyperparameter optimisation strategies. Distinctive advantages of the proposed method include its ability to simultaneously handle any hyper- parameter type (kind of optimiser, number of neurons, number of layer, etc.), its relative simplicity compared to competing methods, as well as the ability to suggest multiple optimal combinations of hyperparameters.","PeriodicalId":113072,"journal":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"7 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":"114796818","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

Robust Iterative Solution for Linear Array-Based 3-D Localization by Message Passing 基于消息传递的线性阵列三维定位鲁棒迭代解

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10095795

Yimao Sun, K. Ho, Yanbing Yang, Lei Zhang, Liangyin Chen

引用次数: 0

Hierarchical Hypergraph Recurrent Attention Network for Temporal Knowledge Graph Reasoning 时间知识图推理的层次超图递归注意网络

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10095378

Jiayan Guo, Meiqi Chen, Yan Zhang, Jianqiang Huang, Zhiwei Liu

引用次数: 0

Deep Adaptive Superpixels For Hadamard Single Pixel Imaging In Near-Infrared Spectrum 近红外光谱中Hadamard单像素成像的深度自适应超像素

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10095165

Brayan Monroy, Jorge Bacca, H. Arguello

引用次数: 0

Stereoscopic Video Retargeting Based on Camera Motion Classification 基于摄像机运动分类的立体视频重定位

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10094758

L. Cai, Zhenhua Tang

引用次数: 0

Domain Adaptation with External Off-Policy Acoustic Catalogs for Scalable Contextual End-to-End Automated Speech Recognition 领域适应与外部的政策声目录可扩展上下文端到端自动语音识别

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10094924

David Chan, Shalini Ghosh, A. Rastrow, Björn Hoffmeister

{"title":"Domain Adaptation with External Off-Policy Acoustic Catalogs for Scalable Contextual End-to-End Automated Speech Recognition","authors":"David Chan, Shalini Ghosh, A. Rastrow, Björn Hoffmeister","doi":"10.1109/ICASSP49357.2023.10094924","DOIUrl":"https://doi.org/10.1109/ICASSP49357.2023.10094924","url":null,"abstract":"Despite improvements to the generalization performance of automated speech recognition (ASR) models, specializing ASR models for downstream tasks remains a challenging task, primarily due to reduced data availability (necessitating increased data collection), and rapidly shifting data distributions (requiring more frequent model fine-tuning). In this work, we investigate the potential of leveraging external knowledge, particularly through off-policy generated text-to-speech key-value stores, to allow for flexible post-training adaptation to new data distributions. In our approach, audio embeddings captured from text-to-speech are used, along with semantic text embeddings, to bias ASR via an approximate k-nearest-neighbor (KNN) based attentive fusion step. Our experiments on LibiriSpeech and in-house voice assistant/search datasets show that the proposed approach can reduce domain adaptation time by up to 1K GPU-hours while providing up to 3% WER improvement compared to a fine-tuning baseline, suggesting a promising approach for adapting production ASR systems in challenging zero and few-shot scenarios.","PeriodicalId":113072,"journal":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"10 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":"126560684","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

The Ustc System for Adress-m Challenge Ustc address -m挑战系统

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10094714

Kangdi Mei, Xinyun Ding, Yinlong Liu, Zhiqiang Guo, Feiyang Xu, Xin Li, Tuya Naren, Jiahong Yuan, Zhenhua Ling

引用次数: 1

COVID-19 Detection from Speech in Noisy Conditions 基于噪声条件下语音的COVID-19检测

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10094304

Shuo Liu, Adria Mallol-Ragolta, B. Schuller

引用次数: 0