2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)最新文献_第2页

Individual Difference of Ultrasonic Transducers for Parametric Array Loudspeaker 参数阵列扬声器超声换能器的个体差异

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2018-09-10 DOI: 10.1109/ICASSP.2018.8462189

Shota Minami, Jun Kuroda, Yasuhiro Oikawa

引用次数: 2

Harnessing Bandit Online Learning to Low-Latency Fog Computing 利用强盗在线学习低延迟雾计算

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2018-09-10 DOI: 10.1109/ICASSP.2018.8461641

Tianyi Chen, G. Giannakis

引用次数: 7

An Analytical Method to Determine Minimum Per-Layer Precision of Deep Neural Networks 一种确定深度神经网络最小逐层精度的解析方法

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2018-09-10 DOI: 10.1109/ICASSP.2018.8461702

Charbel Sakr, Naresh R Shanbhag

{"title":"An Analytical Method to Determine Minimum Per-Layer Precision of Deep Neural Networks","authors":"Charbel Sakr, Naresh R Shanbhag","doi":"10.1109/ICASSP.2018.8461702","DOIUrl":"https://doi.org/10.1109/ICASSP.2018.8461702","url":null,"abstract":"There has been growing interest in the deployment of deep learning systems onto resource-constrained platforms for fast and efficient inference. However, typical models are overwhelmingly complex, making such integration very challenging and requiring compression mechanisms such as reduced precision. We present a layer-wise granular precision analysis which allows us to efficiently quantize pre-trained deep neural networks at minimal cost in terms of accuracy degradation. Our results are consistent with recent findings that perturbations in earlier layers are most destructive and hence needing more precision than in later layers. Our approach allows for significant complexity reduction demonstrated by numerical results on the MNIST and CIFAR-10 datasets. Indeed, for an equivalent level of accuracy, our fine-grained approach reduces the minimum precision in the network up to 8 bits over a naive uniform assignment. Furthermore, we match the accuracy level of a state-of-the-art binary network while requiring up to ~ 3.5 × lower complexity. Similarly, when compared to a state-of-the-art fixed-point network, the complexity savings are even higher (up to ~ 14×) with no loss in accuracy.","PeriodicalId":6638,"journal":{"name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"124 1","pages":"1090-1094"},"PeriodicalIF":0.0,"publicationDate":"2018-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88035638","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: 32

Kalman Filtering and Clustering in Sensor Networks 传感器网络中的卡尔曼滤波与聚类

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2018-09-10 DOI: 10.1109/ICASSP.2018.8462039

S. Talebi, Stefan Werner, V. Koivunen

引用次数: 2

End-to-End Multi-Speaker Speech Recognition 端到端多说话人语音识别

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2018-09-10 DOI: 10.1109/ICASSP.2018.8461893

Shane Settle, Jonathan Le Roux, Takaaki Hori, Shinji Watanabe, J. Hershey

{"title":"End-to-End Multi-Speaker Speech Recognition","authors":"Shane Settle, Jonathan Le Roux, Takaaki Hori, Shinji Watanabe, J. Hershey","doi":"10.1109/ICASSP.2018.8461893","DOIUrl":"https://doi.org/10.1109/ICASSP.2018.8461893","url":null,"abstract":"Current advances in deep learning have resulted in a convergence of methods across a wide range of tasks, opening the door for tighter integration of modules that were previously developed and optimized in isolation. Recent ground-breaking works have produced end-to-end deep network methods for both speech separation and end-to-end automatic speech recognition (ASR). Speech separation methods such as deep clustering address the challenging cocktail-party problem of distinguishing multiple simultaneous speech signals. This is an enabling technology for real-world human machine interaction (HMI). However, speech separation requires ASR to interpret the speech for any HMI task. Likewise, ASR requires speech separation to work in an unconstrained environment. Although these two components can be trained in isolation and connected after the fact, this paradigm is likely to be sub-optimal, since it relies on artificially mixed data. In this paper, we develop the first fully end-to-end, jointly trained deep learning system for separation and recognition of overlapping speech signals. The joint training framework synergistically adapts the separation and recognition to each other. As an additional benefit, it enables training on more realistic data that contains only mixed signals and their transcriptions, and thus is suited to large scale training on existing transcribed data.","PeriodicalId":6638,"journal":{"name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"38 1","pages":"4819-4823"},"PeriodicalIF":0.0,"publicationDate":"2018-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74298807","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: 63

How are the Centered Kernel Principal Components Relevant to Regression Task? -An Exact Analysis 中心核主成分是如何与回归任务相关的?——准确的分析

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2018-09-10 DOI: 10.1109/ICASSP.2018.8462392

M. Yukawa, K. Müller, Yuto Ogino

引用次数: 0

Large-Scale Regularized Sumcor GCCA via Penalty-Dual Decomposition 基于惩罚对偶分解的大规模正则化Sumcor GCCA

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2018-09-10 DOI: 10.1109/ICASSP.2018.8462354

Charilaos I. Kanatsoulis, Xiao Fu, N. Sidiropoulos, Mingyi Hong

{"title":"Large-Scale Regularized Sumcor GCCA via Penalty-Dual Decomposition","authors":"Charilaos I. Kanatsoulis, Xiao Fu, N. Sidiropoulos, Mingyi Hong","doi":"10.1109/ICASSP.2018.8462354","DOIUrl":"https://doi.org/10.1109/ICASSP.2018.8462354","url":null,"abstract":"The sum-of-correlations (SUMCOR) generalized canonical correlation analysis (GCCA) aims at producing low-dimensional representations of multiview data via enforcing pairwise similarity of the reduced-dimension views. SUMCOR has been applied to a large variety of applications including blind separation, multilingual word embedding, and cross-modality retrieval. Despite the NP-hardness of SUMCOR, recent work has proposed effective algorithms for handling it at very large scale. However, the existing scalable algorithms are not easy to extend to incorporate structural regularization and prior information - which are critical for real-world applications where outliers and modeling mismatches are present. In this work, we propose a new computational framework for large-scale SUMCOR GCCA. The algorithm can easily incorporate a suite of structural regularizers which are frequently used in data analytics, has lightweight updates and low memory complexity, and can be easily implemented in a parallel fashion. The proposed algorithm is also guaranteed to converge to a Karush-Kuhn-Tucker (KKT) point of the regularized SUMCOR problem. Carefully designed simulations are employed to demonstrate the effectiveness of the proposed algorithm.","PeriodicalId":6638,"journal":{"name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"7 1","pages":"6363-6367"},"PeriodicalIF":0.0,"publicationDate":"2018-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84153948","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

Bitwise Neural Networks for Efficient Single-Channel Source Separation 高效单通道源分离的位神经网络

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2018-09-10 DOI: 10.1109/ICASSP.2018.8461824

Minje Kim, P. Smaragdis

引用次数: 19

Particle Filtering and Inference for Limit Order Books in High Frequency Finance 高频金融中限价订单的粒子滤波与推理

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2018-09-10 DOI: 10.1109/ICASSP.2018.8462072

Pinzhang Wang, Lin Li, S. Godsill

引用次数: 2

Identifying Susceptible Agents in Time Varying Opinion Dynamics Through Compressive Measurements 通过压缩测量识别时变意见动态中的敏感因素

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2018-09-10 DOI: 10.1109/ICASSP.2018.8462377

Hoi-To Wai, A. Ozdaglar, A. Scaglione

{"title":"Identifying Susceptible Agents in Time Varying Opinion Dynamics Through Compressive Measurements","authors":"Hoi-To Wai, A. Ozdaglar, A. Scaglione","doi":"10.1109/ICASSP.2018.8462377","DOIUrl":"https://doi.org/10.1109/ICASSP.2018.8462377","url":null,"abstract":"We provide a compressive-measurement based method to detect susceptible agents who may receive misinformation through their contact with ‘stubborn agents’ whose goal is to influence the opinions of agents in the network. We consider a DeGroot-type opinion dynamics model where regular agents revise their opinions by linearly combining their neighbors' opinions, but stubborn agents, while influencing others, do not change their opinions. Our proposed method hinges on estimating the temporal difference vector of network-wide opinions, computed at time instances when the stubborn agents interact. We show that this temporal difference vector has approximately the same support as the locations of the susceptible agents. Moreover, both the interaction instances and the temporal difference vector can be estimated from a small number of aggregated opinions. The performance of our method is studied both analytically and empirically. We show that the detection error decreases when the social network is better connected, or when the stubborn agents are ‘less talkative’.","PeriodicalId":6638,"journal":{"name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"36 1","pages":"4114-4118"},"PeriodicalIF":0.0,"publicationDate":"2018-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77438276","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: 4