Search Results for author: Xiao-Feng Gong

Found 7 papers, 0 papers with code

A Coupled Random Projection Approach to Large-Scale Canonical Polyadic Decomposition

no code implementations10 May 2021 Lu-Ming Wang, Ya-Nan Wang, Xiao-Feng Gong, Qiu-Hua Lin, Fei Xiang

We propose a novel algorithm for the computation of canonical polyadic decomposition (CPD) of large-scale tensors.

Fully Dense Neural Network for the Automatic Modulation Recognition

no code implementations7 Dec 2019 Miao Du, Qin Yu, Shaomin Fei, Chen Wang, Xiao-Feng Gong, Ruisen Luo

Nowadays, we mainly use various convolution neural network (CNN) structures to extract features from radio data or spectrogram in AMR.

Multi-layer Attention Mechanism for Speech Keyword Recognition

no code implementations10 Jul 2019 Ruisen Luo, Tianran Sun, Chen Wang, Miao Du, Zuodong Tang, Kai Zhou, Xiao-Feng Gong, Xiaomei Yang

The key idea is that, in addition to the conventional attention mechanism, information of layers prior to feature extraction and LSTM are introduced into attention weights calculations.

Ranked #4 on Keyword Spotting on Google Speech Commands (Google Speech Commands V2 20 metric)

Keyword Spotting speech-recognition +1

Scalar Quantization as Sparse Least Square Optimization

no code implementations1 Mar 2018 Chen Wang, Xiaomei Yang, Shaomin Fei, Kai Zhou, Xiao-Feng Gong, Miao Du, Ruisen Luo

Furthermore, to compute quantization results with a given amount of values/clusters, this paper designed an iterative method and a clustering-based method, and both of them are built on sparse least square.


Double Coupled Canonical Polyadic Decomposition for Joint Blind Source Separation

no code implementations30 Dec 2016 Xiao-Feng Gong, Qiu-Hua Lin, Feng-Yu Cong, Lieven De Lathauwer

We show how, by using second-order multi-set statistics in J-BSS, a specific double coupled canonical polyadic decomposition (DC-CPD) problem can be formulated.

Generalized Non-orthogonal Joint Diagonalization with LU Decomposition and Successive Rotations

no code implementations3 Dec 2013 Xiao-Feng Gong, Xiu-Lin Wang, Qiu-Hua Lin

Non-orthogonal joint diagonalization (NJD) free of prewhitening has been widely studied in the context of blind source separation (BSS) and array signal processing, etc.

Combined Independent Component Analysis and Canonical Polyadic Decomposition via Joint Diagonalization

no code implementations5 Nov 2013 Xiao-Feng Gong, Cheng-Yuan Wang, Ya-Na Hao, Qiu-Hua Lin

Recently, there has been a trend to combine independent component analysis and canonical polyadic decomposition (ICA-CPD) for an enhanced robustness for the computation of CPD, and ICA-CPD could be further converted into CPD of a 5th-order partially symmetric tensor, by calculating the eigenmatrices of the 4th-order cumulant slices of a trilinear mixture.

Cannot find the paper you are looking for? You can Submit a new open access paper.