In this paper, we present our system developed by the team from the New Technologies for the Information Society (NTIS) research center of the University of West Bohemia in Pilsen, for the Second DIHARD Speech Diarization Challenge. The base of our system follows the currently-standard approach of segmentation, i/x-vector extraction, clustering, and resegmentation. The hyperparameters for each of the subsystems were selected according to the domain classifier trained on the development set of DIHARD II. We compared our system with results from the Kaldi diarization (with i/x-vectors) and combined these systems. At the time of writing of this abstract, our best submission achieved a DER of 23.47% and a JER of 48.99% on the evaluation set (in Track 1 using reference SAD).

In the last decade, several GPU implementations of Support Vector Machine (SVM) training with nonlinear kernels were published. Some of them even with source codes. The most effective ones are based on Sequential Minimal Optimization (SMO). They decompose the restricted quadratic problem into a series of smallest possible subproblems, which are then solved analytically. For large datasets, the majority of elapsed time is spent by a large amount of matrix-vector multiplications that cannot be computed efficiently on current GPUs because of limited memory bandwidth. In this paper, we introduce a novel GPU approach to the SVM training that we call Optimized Hierarchical Decomposition SVM (OHD-SVM). It uses a hierarchical decomposition iterative algorithm that fits better to actual GPU architecture. The low decomposition level uses a single GPU multiprocessor to efficiently solve a local subproblem. Nowadays a single GPU multiprocessor can run thousand or more threads that are able to synchronize quickly. It is an ideal platform for a single kernel SMO-based local solver with fast local iterations. The high decomposition level updates gradients of entire training set and selects a new local working set. The gradient update requires many kernel values that are costly to compute. However, solving a large local subproblem offers an efficient kernel values computation via a matrix-matrix multiplication that is much more efficient than the matrix-vector multiplication used in already published implementations. Along with a description of our implementation, the paper includes an exact comparison of five publicly available C++ SVM training GPU implementations. In this paper, the binary classification task and RBF kernel function are taken into account as it is usual in most of the recent papers. According to the measured results on a wide set of publicly available datasets, our proposed approach excelled significantly over the other methods in all datasets. The biggest difference was on the largest dataset where we achieved speed-up up to 12 times in comparison with the fastest already published GPU implementation. Moreover, our OHD-SVM is the only one that can handle dense as well as sparse datasets. Along with this paper, we published the source-codes at https://github.com/OrcusCZ/OHD-SVM.

In this paper, we describe an optimized version of a Gaussian-mixture-based acoustic model likelihood evaluation algorithm for graphical processing units (GPUs). The evaluation of these likelihoods is one of the most computationally intensive parts of automatic speech recognizers, but it can be parallelized and offloaded to GPU devices. Our approach offers a significant speed-up over the recently published approaches, because it utilizes the GPU architecture in a more effective manner. All the recent implementations have been intended only for NVIDIA graphics processors, programmed either in CUDA or OpenCL GPU programming frameworks. We present results for both CUDA and OpenCL. Further, we have developed an OpenCL implementation optimized for ATI/AMD GPUs. Results suggest that even very large acoustic models can be used in real-time speech recognition engines on computers equipped with a low-end GPU or laptops. In addition, the completely asynchronous GPU management provides additional CPU resources for the decoder part of the LVCSR. The optimized implementation enables us to apply fusion techniques together with evaluating many (10 or even more) speaker-specific acoustic models. We apply this technique to a real-time parliamentary speech recognition system where the speaker changes frequently.

In this paper we present a highly optimized implementation of \nGaussian mixture acoustic model evaluation algorithm. Evaluation \nof these likelihoods is one of the most computationally \nintensive parts of automatics speech recognizers but it can be \nwell-parallelized and offloaded to GPU devices. Our approach \noffers significant speed-up compared to the recently published \napproaches, since it exploits the GPU architecture better. All \nthe recent implementations were programmed either in CUDA \nor OpenCL GPU programming frameworks. We present results \nfor both; CUDA as well as OpenCL. \nResults suggest that even very large acoustic models can \nbe utilized in real-time speech recognition engines on computers \nand laptops equipped with a low-end GPU. Optimization \nof acoustic likelihoods computation on GPU enables to use \nthe remaining GPU resources for offloading of other computeintensive \nparts of LVCSR decoder. \nOther possible use of the freed GPU resources is to evaluate \nseveral acoustic models at the same time and use fusion \ntechniques or model selection techniques to improve the quality \nof resulting conditional likelihoods under diverse conditions.

Gaussian Mixture Models (GMMs) are widely used among scientists e.g. in statistics toolkits and data mining procedures. In order to estimate parameters of a GMM the Maximum Likelihood (ML) training is often utilized, more precisely the Expectation-Maximization (EM) algorithm. Nowadays, a lot of tasks works with huge datasets, what makes the estimation process time consuming (mainly for complex mixture models containing hundreds of components). The paper presents an efficient and robust implementation of the estimation of GMM statistics used in the EM algorithm on GPU using NVIDIA's Compute Unified Device Architecture (CUDA). Also an augmentation of the standard CPU version is proposed utilizing SSE instructions. Time consumptions of presented methods are tested on a large dataset of real speech data from the NIST Speaker Recognition Evaluation (SRE) 2008. Estimation on GPU proves to be more than 400 times faster than the standard CPU version and 130 times faster than the SSE version, thus a huge speed up was achieved without any approximations made in the estimation formulas. Proposed implementation was also compared to other implementations developed by other departments over the world and proved to be the fastest (at least 5 times faster than the best implementation published recently).

UNLABELLED: Mass spectrometers are sophisticated, fine instruments which are essential in a variety applications. However, the data they produce are usually interpreted in a rather primitive way, without considering the accuracy of this data and the potential errors in identifying peaks. Our new approach corrects this situation by dividing the LC-MS output into three components: (i) signature of the analyte, (ii) random noise and (iii) systemic noise. The systemic noise is related to the instrument and to the particular experiment; its characteristics change in time and depend on the analyzed substance. Working with these components allows us to quantify the probability of peak errors and, at the same time, to retrieve some peaks which get lost in the noise when using the existing methods. Our software tool, Expertomica metabolite profiling, automatically evaluates the given instrument, detects compounds and calculates the probability of individual peaks. It does not need any artificial user-defined parameters or thresholds. AVAILABILITY: MATLAB scripts with a simple graphical user interface are free to download from http://sourceforge.net/projects/expertomica-eda/. The software reads data exported by most Thermo and Agilent spectrometers, and it can also read the more general JCAMP-DX ASCII format. Other formats will be supported on request, assuming that the user can provide representative data samples.

Tento článek představuje expertní systém pro verifikaci řečníka. Naším hlavním úkolem bylo navrhnout nástroj pro kombinaci různých verifikačních systémů navrzených pro různé operační podmínky.

V článku prezentujeme komparativní studii nekolika dnes používaných metod pro extrakci a selekci příznaků. Porovnali jsme řadu ICA algoritmů oproti běžně používaným metodám DCT a PCA. Porovnání bylo provedeno na dvou úlohách. Jedná se jednak o úlohu verifikace řečníka a jednak o úlohu detekce řeči. Přesnost těchto systémů byla námi zvolenou metodikou významně pozitivně ovlivněna a to jen za cenu velmi mírně zvýšených nároků. Navíc, kde to bylo možné, jsme provedli stručné porovnání schopností extrahovat pro danou úlohu užitečnou informaci.