Vladimir Despotovic

Nonlinear Long-Term Prediction of Speech Based on Truncated Volterra Series

Previous studies of nonlinear prediction of speech have been mostly focused on short-term prediction. This paper presents long-term nonlinear prediction based on second-order Volterra filters. It will be shown that the presented predictor can outperform conventional linear prediction techniques in terms of prediction gain and “whiter” residuals.

Artificial Intelligence Techniques for Modelling of Temperature in the Metal Cutting Process

© 2012 Tanikić and Despotović., licensee InTech. This is an open access chapter distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Artificial Intelligence Techniques for Modelling of Temperature in the Metal Cutting Process

Half a Century of Computing in the Serbian Copper Mining and Metallurgy Industry

The Copper Mining and Smelting Complex Bor (RTB Bor) in the Republic of Serbia has a long history of computer control and computer-aided data processing. Working within the confines of the Cold War era, RTB implemented and developed four generations of computers, becoming a major influence in the IT sector and the primary computer training resource in the region.

Forward Adaptive Laplacian Source Coding Based on Restricted Quantization

A novel solution for Laplacian source coding based on three-level quantization is proposed in this paper. The restricted three-level quantizer is designed by assuming the restricted Laplacian distribution of the input signal. Quantizer and Huffman encoder are jointly designed. Forward adaptive scheme was employed, where the adaptation to the signal variance (power) was performed on frame-by frame basis. We employ switched model that consists of two restricted quantizers having unequal support regions. The simulation results (measured as SQNR) of the proposed scheme with a switched restricted three-level quantizer are compared to the cases when it involves three-level unrestricted quantizer and the Lloyd-Max quantizers having N =2 and N =4 levels. It is shown that the proposed solution offers performance comparable to the one of N =4 levels Lloyd-Max’s baseline with large savings in bit rate, while outperforming two other baselines. DOI: http://dx.doi.org/10.5755/j01.itc.47.2.16670

Machine learning techniques for semantic analysis of dysarthric speech: An experimental study

Abstract We present an experimental comparison of seven state-of-the-art machine learning algorithms for the task of semantic analysis of spoken input, with a special emphasis on applications for dysarthric speech. Dysarthria is a motor speech disorder, which is characterized by poor articulation of phonemes. In order to cater for these non-canonical phoneme realizations, we employed an unsupervised learning approach to estimate the acoustic models for speech recognition, which does not require a literal transcription of the training data. Even for the subsequent task of semantic analysis, only weak supervision is employed, whereby the training utterance is accompanied by a semantic label only, rather than a literal transcription. Results on two databases, one of them containing dysarthric speech, are presented showing that Markov logic networks and conditional random fields substantially outperform other machine learning approaches. Markov logic networks have proved to be especially robust to recognition errors, which are caused by imprecise articulation in dysarthric speech.

Dual-mode quasi-logarithmic quantizer with embedded G.711 codec

Abstract The G.711 codec has been accepted as a standard for high quality coding in many applications. A dual-mode quantizer, which combines the nonlinear logarithmic quantizer for restricted input signals and G.711 quantizer for unrestricted input signals is proposed in this paper. The parameters of the proposed quantizer are optimized, where the minimal distortion is used as the criterion. It is shown that the optimized version of the proposed quantizer provides 5.4 dB higher SQNR (Signal to Quantization Noise Ratio) compared to G.711 quantizer, or equivalently it performs savings in the bit rate of approximately 0.9 bit/sample for the same signal quality. Although the complexity is slightly increased, we believe that due to the superior performance it can be successfully implemented for high-quality quantization.

SWITCHED UNIFORM SCALAR QUANTIZATION ADAPTED TO MEAN AND VARIANCE FOR SPEECH CODING

Average power and variance are widely used in adaptation techniques in signal coding. A speech signal is usually assumed to be zero-mean; thus an average signal power is equal to the signal variance. However, this assumption is valid only for longer signals with a large number of samples. When the signal is divided into frames (especially if the number of samples within the frame is small) the speech signal within the frame may not be zero-mean. Hence, frame-by-frame adaptation to signal mean might be beneficial. A switched uniform scalar quantizer with adaptation to signal mean and variance is proposed in this paper. The analysis is performed for different frame lengths and the results are compared to an adaptive uniform quantizer that uses adaptation only to average signal power, showing an improved performance. Signal to quantization noise ratio (SQNR) is used as a performance measure.

The Use of the Internet and Wireless Communications in the Monitoring and Control of Industrial Processes

This paper describes the application of Internet and wireless communications in the monitoring and control of production processes in the metallurgical company RTB Bor, Serbia. A special attention is paid to the presentation of the software solutions. Implemented distributed control systems have shown remarkable reliability in practical work, low cost of maintenance and investment in their expansion. The described solution is applicable for monitoring and control of processes with the control system response time of about a minute or longer.

Design of nonlinear predictors for adaptive predictive coding of speech signals

Linear predictive coding is probably the most frequently used technique in speech signal processing. Its main advantage comes from the analogy of the simplified vocal tract model with speech production system. However, this neglects nonlinearities in the speech production process. The paper deals with nonlinear prediction of speech based on truncated Volterra series. Long-term one-tap Volterra predictor is designed in order to decrease computational complexity. Further improvements are obtained using frame/subframe structure and fractional delay.

The artificial neural network based system for validation of thermocouples used in biomedicine

Machining operations are widely used in the orthopedic surgery. The temperature which occurs in the cutting zone, during the machining of the bones, may have many negative consequences in the postoperative period. Therefore, the measuring and the modeling of this parameter is a very important task. In this paper, the thermocouples are presented as a potential tool for the temperature measuring. The paper also deals with the system for validation of the thermocouples. The artificial neural network is used for modeling of the relationship between the electromotive force (as the thermocouple output) and the corresponding temperature. It is shown that the results of the modeling are in good correlation with the measured data.