arXiv subjects

Yuexian Zou

Publications and source records attributed to Yuexian Zou.

130 records · Page 8Linked to original sources

arXiv2020

Temporal-Spatial Neural Filter: Direction Informed End-to-End Multi-channel Target Speech Separation

Target speech separation refers to extracting the target speaker's speech from mixed signals. Despite the recent advances in deep learning based close-talk speech separation, the applications to real-world are still an open issue. Two main challenges are the complex acoustic environment and the real-time processing requirement. To address these challenges, we propose a temporal-spatial neural filter, which directly estimates the target speech waveform from multi-speaker mixture in reverberant environments, assisted with directional information of the speaker(s). Firstly, against variations brought by complex environment, the key idea is to increase the acoustic representation completeness through the jointly modeling of temporal, spectral and spatial discriminability between the target and interference source. Specifically, temporal, spectral, spatial along with the designed directional features are integrated to create a joint acoustic representation. Secondly, to reduce the latency, we design a fully-convolutional autoencoder framework, which is purely end-to-end and single-pass. All the feature computation is implemented by the network layers and operations to speed up the separation procedure. Evaluation is conducted on simulated reverberant dataset WSJ0-2mix and WSJ0-3mix under speaker-independent scenario. Experimental results demonstrate that the proposed method outperforms state-of-the-art deep learning based multi-channel approaches with fewer parameters and faster processing speed. Furthermore, the proposed temporal-spatial neural filter can handle mixtures with varying and unknown number of speakers and exhibits persistent performance even when existing a direction estimation error. Codes and models will be released soon.

cs.SD↗

arXiv2019

End-to-End Multi-Channel Speech Separation

The end-to-end approach for single-channel speech separation has been studied recently and shown promising results. This paper extended the previous approach and proposed a new end-to-end model for multi-channel speech separation. The primary contributions of this work include 1) an integrated waveform-in waveform-out separation system in a single neural network architecture. 2) We reformulate the traditional short time Fourier transform (STFT) and inter-channel phase difference (IPD) as a function of time-domain convolution with a special kernel. 3) We further relaxed those fixed kernels to be learnable, so that the entire architecture becomes purely data-driven and can be trained from end-to-end. We demonstrate on the WSJ0 far-field speech separation task that, with the benefit of learnable spatial features, our proposed end-to-end multi-channel model significantly improved the performance of previous end-to-end single-channel method and traditional multi-channel methods.

cs.SD↗

arXiv2014

KCRC-LCD: Discriminative Kernel Collaborative Representation with Locality Constrained Dictionary for Visual Categorization

We consider the image classification problem via kernel collaborative representation classification with locality constrained dictionary (KCRC-LCD). Specifically, we propose a kernel collaborative representation classification (KCRC) approach in which kernel method is used to improve the discrimination ability of collaborative representation classification (CRC). We then measure the similarities between the query and atoms in the global dictionary in order to construct a locality constrained dictionary (LCD) for KCRC. In addition, we discuss several similarity measure approaches in LCD and further present a simple yet effective unified similarity measure whose superiority is validated in experiments. There are several appealing aspects associated with LCD. First, LCD can be nicely incorporated under the framework of KCRC. The LCD similarity measure can be kernelized under KCRC, which theoretically links CRC and LCD under the kernel method. Second, KCRC-LCD becomes more scalable to both the training set size and the feature dimension. Example shows that KCRC is able to perfectly classify data with certain distribution, while conventional CRC fails completely. Comprehensive experiments on many public datasets also show that KCRC-LCD is a robust discriminative classifier with both excellent performance and good scalability, being comparable or outperforming many other state-of-the-art approaches.

cs.CV↗

arXiv2010

Comparison of Spearman's rho and Kendall's tau in Normal and Contaminated Normal Models

This paper analyzes the performances of the Spearman's rho (SR) and Kendall's tau (KT) with respect to samples drawn from bivariate normal and bivariate contaminated normal populations. The exact analytical formulae of the variance of SR and the covariance between SR and KT are obtained based on the Childs's reduction formula for the quadrivariate normal positive orthant probabilities. Close form expressions with respect to the expectations of SR and KT are established under the bivariate contaminated normal models. The bias, mean square error (MSE) and asymptotic relative efficiency (ARE) of the three estimators based on SR and KT to the Pearson's product moment correlation coefficient (PPMCC) are investigated in both the normal and contaminated normal models. Theoretical and simulation results suggest that, contrary to the opinion of equivalence between SR and KT in some literature, the behaviors of SR and KT are strikingly different in the aspects of bias effect, variance, mean square error, and asymptotic relative efficiency. The new findings revealed in this work provide not only deeper insights into the two most widely used rank based correlation coefficients, but also a guidance for choosing which one to use under the circumstances where the PPMCC fails to apply.

cs.IT↗