2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)最新文献_第4页

Improvements to filterbank and delta learning within a deep neural network framework 在深度神经网络框架下对滤波器组和增量学习的改进

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2014-05-04 DOI: 10.1109/ICASSP.2014.6854925

Tara N. Sainath, Brian Kingsbury, Abdel-rahman Mohamed, G. Saon, B. Ramabhadran

引用次数: 12

Frequency-shift filtering for OFDM recovery in narrowband power line communications 窄带电力线通信中OFDM恢复的移频滤波

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2014-05-04 DOI: 10.1109/ICASSP.2014.6855173

Nir Shlezinger, R. Dabora

引用次数: 1

Reconstruction of sparse signals from highly corrupted measurements by nonconvex minimization 用非凸极小化方法重建高度损坏测量的稀疏信号

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2014-05-04 DOI: 10.1109/ICASSP.2014.6854230

Marko Filipovic

引用次数: 5

A computationally efficient calibration algorithm for the LOFAR radio astronomical array 一种计算效率高的LOFAR射电天文阵列标定算法

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2014-05-04 DOI: 10.1109/ICASSP.2014.6854635

Yuntao Wu, Amir Leshem, S. Wijnholds

{"title":"A computationally efficient calibration algorithm for the LOFAR radio astronomical array","authors":"Yuntao Wu, Amir Leshem, S. Wijnholds","doi":"10.1109/ICASSP.2014.6854635","DOIUrl":"https://doi.org/10.1109/ICASSP.2014.6854635","url":null,"abstract":"In this paper, the problem of self-calibration for large astronomical arrays such as the Dutch Low Frequency Array (LOFAR) is considered. We assume direction dependent gain and phase errors which need to be estimated and calibrated out. Combining the subspace fitting and least square approaches, the signal subspace of the received single short-term interval (STI) sample data of the LOFAR is used to build a cost function whose minimizer is a statistically efficient estimator of the unknown parameters-the gains and phases of the telescopes. Subsequently, an iterative algorithm for finding the minimum of the cost function is presented and the unknown calibration parameters of both the core stations and the external subarray are separated. As a result, the computational complexity of the proposed method is significantly reduced compared to the existing methods based on a direct covariance fitting. Finally, the performance of the proposed method is compared with the conventional peeling method in computer simulation. An example for calibrating the core of the LOFAR array on Cyg A is also provided.","PeriodicalId":6545,"journal":{"name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"13 1","pages":"5402-5406"},"PeriodicalIF":0.0,"publicationDate":"2014-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74875531","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

Retrieving the syntactic structure of erroneous ASR transcriptions for open-domain Spoken Language Understanding 开放域口语理解中错误ASR转录的句法结构检索

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2014-05-04 DOI: 10.1109/ICASSP.2014.6854372

Frédéric Béchet, Benoit Favre, Alexis Nasr, Mathieu Morey

引用次数: 4

Investigation of unsupervised adaptation of DNN acoustic models with filter bank input 带滤波器组输入的DNN声学模型的无监督自适应研究

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2014-05-04 DOI: 10.1109/ICASSP.2014.6854825

Takuya Yoshioka, A. Ragni, M. Gales

{"title":"Investigation of unsupervised adaptation of DNN acoustic models with filter bank input","authors":"Takuya Yoshioka, A. Ragni, M. Gales","doi":"10.1109/ICASSP.2014.6854825","DOIUrl":"https://doi.org/10.1109/ICASSP.2014.6854825","url":null,"abstract":"Adaptation to speaker variations is an essential component of speech recognition systems. One common approach to adapting deep neural network (DNN) acoustic models is to perform global constrained maximum likelihood linear regression (CMLLR) at some point of the systems. Using CMLLR (or more generally, generative approaches) is advantageous especially in unsupervised adaptation scenarios with high baseline error rates. On the other hand, as the DNNs are less sensitive to the increase in the input dimensionality than GMMs, it is becoming more popular to use rich speech representations, such as log mel-filter bank channel outputs, instead of conventional low-dimensional feature vectors, such as MFCCs and PLP coefficients. This work discusses and compares three different configurations of DNN acoustic models that allow CMLLR-based speaker adaptive training (SAT) to be performed in systems with filter bank inputs. Results of unsupervised adaptation experiments conducted on three different data sets are presented, demonstrating that, by choosing an appropriate configuration, SAT with CMLLR can improve the performance of a well-trained filter bank-based speaker independent DNN system by 10.6% relative in a challenging task with a baseline error rate above 40%. It is also shown that the filter bank features are advantageous than the conventional features even when they are used with SAT models. Some other insights are also presented, including the effects of block diagonal transforms and system combination.","PeriodicalId":6545,"journal":{"name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"13 1","pages":"6344-6348"},"PeriodicalIF":0.0,"publicationDate":"2014-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73112069","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: 42

Improved low-delay MDCT-based coding of both stationary and transient audio signals 改进的低延迟mdct编码的平稳和瞬态音频信号

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2014-05-04 DOI: 10.1109/ICASSP.2014.6854948

Christian R. Helmrich, Goran Markovic, B. Edler

引用次数: 12

New bivariate statistical model of natural image correlations 自然图像相关性的新二元统计模型

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2014-05-04 DOI: 10.1109/ICASSP.2014.6854627

Che-Chun Su, L. Cormack, A. Bovik

引用次数: 2

Selective analytic signal construction from a non-uniformly sampled bandpass signal 非均匀采样带通信号的选择性分析信号构建

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2014-05-04 DOI: 10.1109/ICASSP.2014.6854549

Jean-Adrien Vernhes, M. Chabert, B. Lacaze, G. Lesthievent, R. Baudin

引用次数: 3

Lossless/near-lossless color image coding by inverse demosaicing 基于反去马赛克的无损/近无损彩色图像编码

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2014-05-04 DOI: 10.1109/ICASSP.2014.6853951

Ryo Kuroiwa, Ryo Matsuoka, Seisuke Kyochi, K. Shirai, M. Okuda

引用次数: 2