发布求助
文献互助 智能选刊 最新文献

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

筛选
英文 中文
Sparse Representations with Cone Atoms 锥原子稀疏表示
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/icassp49357.2023.10095127
Denis C. Ilie-Ablachim, Andra Baltoiu, Bogdan Dumitrescu
{"title":"Sparse Representations with Cone Atoms","authors":"Denis C. Ilie-Ablachim, Andra Baltoiu, Bogdan Dumitrescu","doi":"10.1109/icassp49357.2023.10095127","DOIUrl":"https://doi.org/10.1109/icassp49357.2023.10095127","url":null,"abstract":"We extend the notion of sparse representation to the case where the atoms are not vectors, but cones, hence infinite sets. The sparse representation is linear, as usual, but the most convenient vector is chosen from each selected cone. We give a cone version of Orthogonal Matching Pursuit (OMP) and show that its complexity is only a few times larger than that of OMP. The new cone OMP can be used for anomaly detection; we apply it with very good results to the detection of abnormal heartbeats.","PeriodicalId":113072,"journal":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"69 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":"129422400","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
TDMA-Based Multi-User Binary Computation Offloading in the Finite-Block-Length Regime 有限块长度下基于tdma的多用户二进制计算卸载
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10095862
M. A. Manouchehrpour, Harvinder Lehal, Mahsa Salmani, T. Davidson
{"title":"TDMA-Based Multi-User Binary Computation Offloading in the Finite-Block-Length Regime","authors":"M. A. Manouchehrpour, Harvinder Lehal, Mahsa Salmani, T. Davidson","doi":"10.1109/ICASSP49357.2023.10095862","DOIUrl":"https://doi.org/10.1109/ICASSP49357.2023.10095862","url":null,"abstract":"Multi-user computation offloading inherently involves the allocation of communication resources among the offloading devices. Since the devices require timely results, that allocation ought to be guided by the fundamental rate limits for finite block lengths, rather than the classical (asymptotic) limits. We develop an efficient algorithm for such an allocation. It includes a relaxation-rounding approach that is based on a customized incremental rounding scheme for the block lengths. A special feature is that the relaxation is tightened in such a way that rounding a feasible solution to the relaxed problem is guaranteed to generate a feasible integer block length. By exploiting a closed-form approximation of the transmission powers, our design approach reduces to successively solving convex approximation problems over the transmission rates alone.","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":"129534842","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
HITSZ TMG at ICASSP 2023 SPGC Shared Task: Leveraging Pre-Training and Distillation Method for Title Generation with Limited Resource 在ICASSP 2023 SPGC共享任务:利用有限资源的预训练和蒸馏方法生成标题
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/icassp49357.2023.10097026
Tianxiao Xu, Zihao Zheng, Xinshuo Hu, Zetian Sun, Yu Zhao, Baotian Hu
{"title":"HITSZ TMG at ICASSP 2023 SPGC Shared Task: Leveraging Pre-Training and Distillation Method for Title Generation with Limited Resource","authors":"Tianxiao Xu, Zihao Zheng, Xinshuo Hu, Zetian Sun, Yu Zhao, Baotian Hu","doi":"10.1109/icassp49357.2023.10097026","DOIUrl":"https://doi.org/10.1109/icassp49357.2023.10097026","url":null,"abstract":"In this paper, we present our proposed method for the shared task of the ICASSP 2023 Signal Processing Grand Challenge (SPGC). We participate in Topic Title Generation (TTG), Track 3 of General Meeting Understanding and Generation (MUG) [1] in SPGC. The primary objective of this task is to generate a title that effectively summarizes the given topic segment. With the constraints of limited model size and external dataset availability, we propose a method as Pre-training - Distillation / Fine-tuning (PDF), which can efficiently leverage the knowledge from large model and corpus. Our method achieves first place during preliminary and final contests in ICASSP2023 MUG Challenge Track 3.","PeriodicalId":113072,"journal":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"17 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":"129739310","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: 1
A Topic-Enhanced Approach for Emotion Distribution Forecasting in Conversations 对话中情绪分布预测的话题增强方法
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10096414
Xin Lu, Weixiang Zhao, Yanyan Zhao, Bing Qin, Zhentao Zhang, Junjie Wen
{"title":"A Topic-Enhanced Approach for Emotion Distribution Forecasting in Conversations","authors":"Xin Lu, Weixiang Zhao, Yanyan Zhao, Bing Qin, Zhentao Zhang, Junjie Wen","doi":"10.1109/ICASSP49357.2023.10096414","DOIUrl":"https://doi.org/10.1109/ICASSP49357.2023.10096414","url":null,"abstract":"Emotion Forecasting in Conversations (EFC), the task aims to predict the emotion of next utterance (yet to come), has received more and more attention in recent years. However, this task ignores the one-to-many feature of dialogue and its prediction target is emotion label, which is flawed in most cases. In this work, we propose a new task: Emotion Distribution Forecasting in Conversations (EDFC), which aims to predict the emotion distribution of next utterance. Although this task is more reasonable in real applications, it can only learn using emotion labels in most cases because of the difficulty in obtaining emotion distribution. To address it, we explore the positive role of topic in this task and propose a topic-enhanced approach. Specifically, we first obtain the topic-based emotion distribution prior through topic model and emotion generation model, and then use the emotion distribution prior to enhance original label learning model. To effectively evaluate the distribution prediction results, we construct two datasets for this task, and the experimental results prove the feasibility of the EDFC task as well as the effectiveness of our approach.","PeriodicalId":113072,"journal":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"481 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":"129802090","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
AE-Flow: Autoencoder Normalizing Flow AE-Flow:自动编码器归一化流
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10095301
Jakub Mosiński, P. Bilinski, Thomas Merritt, Abdelhamid Ezzerg, Daniel Korzekwa
{"title":"AE-Flow: Autoencoder Normalizing Flow","authors":"Jakub Mosiński, P. Bilinski, Thomas Merritt, Abdelhamid Ezzerg, Daniel Korzekwa","doi":"10.1109/ICASSP49357.2023.10095301","DOIUrl":"https://doi.org/10.1109/ICASSP49357.2023.10095301","url":null,"abstract":"Recently normalizing flows have been gaining traction in text-to-speech (TTS) and voice conversion (VC) due to their state-of-the-art (SOTA) performance. Normalizing flows are unsupervised generative models. In this paper, we introduce supervision to the training process of normalizing flows, without the need for parallel data. We call this training paradigm AutoEncoder Normalizing Flow (AE-Flow). It adds a reconstruction loss forcing the model to use information from the conditioning to reconstruct an audio sample. Our goal is to understand the impact of each component and find the right combination of the negative log-likelihood (NLL) and the reconstruction loss in training normalizing flows with coupling blocks. For that reason we will compare flow-based mapping model trained with: (i) NLL loss, (ii) NLL and reconstruction losses, as well as (iii) reconstruction loss only. Additionally, we compare our model with SOTA VC baseline. The models are evaluated in terms of naturalness, speaker similarity, intelligibility in many-to-many and many-to-any VC settings. The results show that the proposed training paradigm systematically improves speaker similarity and naturalness when compared to regular training methods of normalizing flows. Furthermore, we show that our method improves speaker similarity and intelligibility over the state-of-the-art.","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":"130517630","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
Long-Term Synchronization of Wireless Acoustic Sensor Networks with Nonpersistent Acoustic Activity Using Coherence State 基于相干态的非持续声活动无线声传感器网络的长期同步
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10095792
Aleksej Chinaev, Niklas Knaepper, G. Enzner
{"title":"Long-Term Synchronization of Wireless Acoustic Sensor Networks with Nonpersistent Acoustic Activity Using Coherence State","authors":"Aleksej Chinaev, Niklas Knaepper, G. Enzner","doi":"10.1109/ICASSP49357.2023.10095792","DOIUrl":"https://doi.org/10.1109/ICASSP49357.2023.10095792","url":null,"abstract":"Sample-accurate synchronization of nodes is required to enable the full potential of acoustic sensor networks for cooperative and enhanced signal acquisition. While metrics of spatio-temporal sensor utility are key to successful aggregation of sensor nodes, for instance, to perform sound localization or beamforming, the same is true for waveform-based assessment and compensation of sampling-rate offset (SRO). This paper therefore proposes an acoustic coherence state (ACS) metric to support systems for SRO estimation to integrate estimations of various utility due to nonpersistent acoustic activity and geometrical diversity. Specifically, we consider systems with SRO estimation and compensation in open- and closed-loop structures and outline the architectures for embedding ACS-based sensor utility. It is demonstrated in both cases that the acoustic coherence metric is more appropriate in terms of end-to-end synchronization performance than voice or sound activity detectors.","PeriodicalId":113072,"journal":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"95 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":"126882293","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
Causal Discovery and Causal Inference Based Counterfactual Fairness in Machine Learning 机器学习中基于反事实公平性的因果发现和因果推理
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10095194
Yajing Wang, Zongwei Luo
{"title":"Causal Discovery and Causal Inference Based Counterfactual Fairness in Machine Learning","authors":"Yajing Wang, Zongwei Luo","doi":"10.1109/ICASSP49357.2023.10095194","DOIUrl":"https://doi.org/10.1109/ICASSP49357.2023.10095194","url":null,"abstract":"The fairness problem arouses attention in machine learning. One problem with traditional counterfactual fairness is the assumed causal models are constrained by prior knowledge. We propose a framework named Structural Causal Fairness Framework (SCFF) to achieve counterfactual fairness without assumptions like previous works. To correct observations adversely affected by the sensitive attributes, we follow the objectives of fair sampling and construct structural causal models based on causal discovery and causal inference. Experiments show our framework generates competitive results on both counterfactual fairness level and prediction accuracy compared with the other three baselines. More importantly, our framework is all based on data and has good generalization on machine learning problems.","PeriodicalId":113072,"journal":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"75 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":"126977205","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
LiNuIQA: Lightweight No-Reference Image Quality Assessment Based on Non-Uniform Weighting 基于非均匀加权的轻量级无参考图像质量评估
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10096440
Wook-Hyung Kim, Cheul-hee Hahm, A. Baijal, NamUk Kim, Ilhyun Cho, Jayoon Koo
{"title":"LiNuIQA: Lightweight No-Reference Image Quality Assessment Based on Non-Uniform Weighting","authors":"Wook-Hyung Kim, Cheul-hee Hahm, A. Baijal, NamUk Kim, Ilhyun Cho, Jayoon Koo","doi":"10.1109/ICASSP49357.2023.10096440","DOIUrl":"https://doi.org/10.1109/ICASSP49357.2023.10096440","url":null,"abstract":"No-Reference Image Quality Assessment (NR-IQA) techniques have shown improved performance with the help of deep-learning but lightweight architectures have not received attention. In this paper, we propose an NR-IQA network named Lightweight Non-uniform Weighting-based NR-IQA (LiNuIQA) that adopts an efficient network as a feature extractor for a resource constraint environment and harnesses non-uniformly self-weighted local (from each patch) and global information (from all patches) to overcome the inherent problem of low performance stemming from use of lightweight feature extractor. This non-uniform weighting technique is designed to utilize combinations of local and global information with very low resources unlike conventional weighting techniques. The experimental results show that our network outperforms several recently popular NR-IQA networks in terms of both PLCC and SRCC while having the smallest number of parameters and multiply-adds (MAdd) operations. In addition, it can be seen from our experiments that appropriate weighting method plays an important role in IQA and can be implemented with extremely low resources.","PeriodicalId":113072,"journal":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"79 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":"126980792","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
Classification via Subspace Learning Machine (SLM): Methodology and Performance Evaluation 基于子空间学习机(SLM)的分类:方法与性能评价
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10096564
Hongyu Fu, Yijing Yang, Vinod K. Mishra, C.-C. Jay Kuo
{"title":"Classification via Subspace Learning Machine (SLM): Methodology and Performance Evaluation","authors":"Hongyu Fu, Yijing Yang, Vinod K. Mishra, C.-C. Jay Kuo","doi":"10.1109/ICASSP49357.2023.10096564","DOIUrl":"https://doi.org/10.1109/ICASSP49357.2023.10096564","url":null,"abstract":"Inspired by the decision learning process of multilayer per-ceptron (MLP) and decision tree (DT), a new classification model, named the subspace learning machine (SLM), is proposed in this work. SLM first identifies a discriminant subspace, S0, by examining the discriminant power of each input feature. Then, it learns projections of features in S0 to yield 1D subspaces and finds the optimal partition for each. A criterion is developed to choose the best q partitions that yield 2q partitioned subspaces. The partitioning process is recursively applied at each child node to build an SLM tree. When the samples at a child node are sufficiently pure, the partitioning process stops, and each leaf node makes a prediction. The ensembles of SLM trees can yield a stronger predictor. Extensive experiments are conducted for performance benchmarking among SLM trees, ensembles and classical classifiers.","PeriodicalId":113072,"journal":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"31 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":"130594611","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: 1
Dynamic Scalable Self-Attention Ensemble for Task-Free Continual Learning 无任务持续学习的动态可扩展自注意集成
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2023-06-04 DOI: 10.1109/ICASSP49357.2023.10094791
Fei Ye, A. Bors
{"title":"Dynamic Scalable Self-Attention Ensemble for Task-Free Continual Learning","authors":"Fei Ye, A. Bors","doi":"10.1109/ICASSP49357.2023.10094791","DOIUrl":"https://doi.org/10.1109/ICASSP49357.2023.10094791","url":null,"abstract":"Continual learning represents a challenging task for modern deep neural networks due to the catastrophic forgetting following the adaptation of network parameters to new tasks. In this paper, we address a more challenging learning paradigm called Task-Free Continual Learning (TFCL), in which the task information is missing during the training. To deal with this problem, we introduce the Dynamic Scalable Self-Attention Ensemble (DSSAE) model, which dynamically adds new Vision Transformer (ViT) based-experts to deal with the data distribution shift during the training. To avoid frequent expansions and ensure an appropriate number of experts for the model, we propose a new dynamic expansion mechanism that evaluates the novelty of incoming samples as expansion signals. Furthermore, the proposed expansion mechanism does not require knowing the task information or the class label, which can be used in a realistic learning environment. Empirical results demonstrate that the proposed DSSAE achieves state-of-the-art performance in a series of TFCL experiments.","PeriodicalId":113072,"journal":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"24 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":"130621378","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
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信