ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)最新文献_第9页

Adaptive Reduced-Dimensional Beamspace Beamformer Design by Analogue Beam Selection 基于模拟波束选择的自适应降维波束空间波束形成器设计

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2019-05-12 DOI: 10.1109/ICASSP.2019.8683360

Xiangrong Wang, E. Aboutanios

引用次数: 3

Reflection Symmetry Detection by Embedding Symmetry in a Graph 在图中嵌入对称的反射对称检测

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2019-05-12 DOI: 10.1109/ICASSP.2019.8682412

R. Nagar, S. Raman

引用次数: 4

Asymptotically Optimal Recovery of Gaussian Sources from Noisy Stationary Mixtures: the Least-noisy Maximally-separating Solution 高斯源在有噪声平稳混合中的渐近最优恢复:最小噪声最大分离解

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2019-05-12 DOI: 10.1109/ICASSP.2019.8682761

A. Weiss, A. Yeredor

{"title":"Asymptotically Optimal Recovery of Gaussian Sources from Noisy Stationary Mixtures: the Least-noisy Maximally-separating Solution","authors":"A. Weiss, A. Yeredor","doi":"10.1109/ICASSP.2019.8682761","DOIUrl":"https://doi.org/10.1109/ICASSP.2019.8682761","url":null,"abstract":"We address the problem of source separation from noisy mixtures in a semi-blind scenario, with stationary, temporally-diverse Gaussian sources and known spectra. In such noisy models, a dilemma arises regarding the desired objective. On one hand, a \"maximally separating\" solution, providing the minimal attainable Interference-to-Source-Ratio (ISR), would often suffer from significant residual noise. On the other hand, optimal Minimum Mean Square Error (MMSE) estimation would yield estimates which are the \"least distorted\" versions of the true sources, often at the cost of compromised ISR. Based on Maximum Likelihood (ML) estimation of the unknown underlying model parameters, we propose two ML-based estimates of the sources. One asymptotically coincides with the MMSE estimate of the sources, whereas the other asymptotically coincides with the (unbiased) \"least-noisy maximally-separating\" solution for this model. We prove the asymptotic optimality of the latter and present the corresponding Cramér-Rao lower bound. We discuss the differences in principal properties of the proposed estimates and demonstrate them empirically using simulation results.","PeriodicalId":13203,"journal":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"46 1","pages":"5466-5470"},"PeriodicalIF":0.0,"publicationDate":"2019-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85470901","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

Evolutionary Subspace Clustering: Discovering Structure in Self-expressive Time-series Data 演化子空间聚类:发现自表达时间序列数据的结构

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2019-05-12 DOI: 10.1109/ICASSP.2019.8682405

Abolfazl Hashemi, H. Vikalo

引用次数: 2

Bayesian and Gaussian Process Neural Networks for Large Vocabulary Continuous Speech Recognition 大词汇量连续语音识别的贝叶斯和高斯过程神经网络

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2019-05-12 DOI: 10.1109/ICASSP.2019.8682487

Shoukang Hu, Max W. Y. Lam, Xurong Xie, Shansong Liu, Jianwei Yu, Xixin Wu, Xunying Liu, H. Meng

{"title":"Bayesian and Gaussian Process Neural Networks for Large Vocabulary Continuous Speech Recognition","authors":"Shoukang Hu, Max W. Y. Lam, Xurong Xie, Shansong Liu, Jianwei Yu, Xixin Wu, Xunying Liu, H. Meng","doi":"10.1109/ICASSP.2019.8682487","DOIUrl":"https://doi.org/10.1109/ICASSP.2019.8682487","url":null,"abstract":"The hidden activation functions inside deep neural networks (DNNs) play a vital role in learning high level discriminative features and controlling the information flows to track longer history. However, the fixed model parameters used in standard DNNs can lead to over-fitting and poor generalization when given limited training data. Furthermore, the precise forms of activations used in DNNs are often manually set at a global level for all hidden nodes, thus lacking an automatic selection method. In order to address these issues, Bayesian neural networks (BNNs) acoustic models are proposed in this paper to explicitly model the uncertainty associated with DNN parameters. Gaussian Process (GP) activations based DNN and LSTM acoustic models are also used in this paper to allow the optimal forms of hidden activations to be stochastically learned for individual hidden nodes. An efficient variational inference based training algorithm is derived for BNN, GPNN and GPLSTM systems. Experiments were conducted on a LVCSR system trained on a 75 hour subset of Switchboard I data. The best BNN and GPNN systems outperformed both the baseline DNN systems constructed using fixed form activations and their combination via frame level joint decoding by 1% absolute in word error rate.","PeriodicalId":13203,"journal":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"9 1","pages":"6555-6559"},"PeriodicalIF":0.0,"publicationDate":"2019-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85768922","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: 9

Neural Variational Identification and Filtering for Stochastic Non-linear Dynamical Systems with Application to Non-intrusive Load Monitoring 随机非线性动力系统的神经变分辨识与滤波及其在非侵入式负荷监测中的应用

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2019-05-12 DOI: 10.1109/ICASSP.2019.8683552

Henning Lange, M. Berges, J. Z. Kolter

引用次数: 6

Surgical Activities Recognition Using Multi-scale Recurrent Networks 基于多尺度递归网络的手术活动识别

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2019-05-12 DOI: 10.1109/ICASSP.2019.8683849

Ilker Gurcan, H. Nguyen

{"title":"Surgical Activities Recognition Using Multi-scale Recurrent Networks","authors":"Ilker Gurcan, H. Nguyen","doi":"10.1109/ICASSP.2019.8683849","DOIUrl":"https://doi.org/10.1109/ICASSP.2019.8683849","url":null,"abstract":"Recently, surgical activity recognition has been receiving significant attention from the medical imaging community. Existing state-of-the-art approaches employ recurrent neural networks such as long-short term memory networks (LSTMs). However, our experiments show that these networks are not effective in capturing the relationship of features with different temporal scales. Such limitation will lead to sub-optimal recognition performance of surgical activities containing complex motions at multiple time scales. To overcome this shortcoming, our paper proposes a multi-scale recurrent neural network (MS-RNN) that combines the strength of both wavelet scattering operations and LSTM. We validate the effectiveness of the proposed network using both real and synthetic datasets. Our experimental results show that MS-RNN outperforms state-of-the-art methods in surgical activity recognition by a significant margin. On a synthetic dataset, the proposed network achieves more than 90% classification accuracy while LSTM’s accuracy is around chance level. Experiments on real surgical activity dataset shows a significant improvement of recognition accuracy over the current state of the art (90.2% versus 83.3%).","PeriodicalId":13203,"journal":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"13 1","pages":"2887-2891"},"PeriodicalIF":0.0,"publicationDate":"2019-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82478817","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: 8

Multi-step Self-attention Network for Cross-modal Retrieval Based on a Limited Text Space 基于有限文本空间的跨模态检索多步自关注网络

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2019-05-12 DOI: 10.1109/ICASSP.2019.8682424

Zheng Yu, Wenmin Wang, Ge Li

引用次数: 0

Dilated Residual Network with Multi-head Self-attention for Speech Emotion Recognition 基于多头自注意的扩展残差网络语音情绪识别

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2019-05-12 DOI: 10.1109/ICASSP.2019.8682154

Runnan Li, Zhiyong Wu, Jia Jia, Sheng Zhao, H. Meng

{"title":"Dilated Residual Network with Multi-head Self-attention for Speech Emotion Recognition","authors":"Runnan Li, Zhiyong Wu, Jia Jia, Sheng Zhao, H. Meng","doi":"10.1109/ICASSP.2019.8682154","DOIUrl":"https://doi.org/10.1109/ICASSP.2019.8682154","url":null,"abstract":"Speech emotion recognition (SER) plays an important role in intelligent speech interaction. One vital challenge in SER is to extract emotion-relevant features from speech signals. In state-of-the-art SER techniques, deep learning methods, e.g, Convolutional Neural Networks (CNNs), are widely employed for feature learning and have achieved significant performance. However, in the CNN-oriented methods, two performance limitations have raised: 1) the loss of temporal structure of speech in the progressive resolution reduction; 2) the ignoring of relative dependencies between elements in suprasegmental feature sequence. In this paper, we proposed the combining use of Dilated Residual Network (DRN) and Multi-head Self-attention to alleviate the above limitations. By employing DRN, the network can retain high resolution of temporal structure in feature learning, with similar size of receptive field to CNN based approach. By employing Multi-head Self-attention, the network can model the inner dependencies between elements with different positions in the learned suprasegmental feature sequence, which enhances the importing of emotion-salient information. Experiments on emotional benchmarking dataset IEMOCAP have demonstrated the effectiveness of the proposed framework, with 11.7% to 18.6% relative improvement to state-of-the-art approaches.","PeriodicalId":13203,"journal":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"80 1 1","pages":"6675-6679"},"PeriodicalIF":0.0,"publicationDate":"2019-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89560647","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: 45

Baseline Wander Removal and Isoelectric Correction in Electrocardiograms Using Clustering 基于聚类的心电图基线漂移去除和等电校正

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2019-05-12 DOI: 10.1109/ICASSP.2019.8683084

Kjell Le, T. Eftestøl, K. Engan, Ø. Kleiven, S. Ørn

引用次数: 1