Author
Laimutis Telksnys
Other affiliations: Vytautas Magnus University
Bio: Laimutis Telksnys is an academic researcher from Vilnius University. The author has contributed to research in topics: Speech corpus & Speaker recognition. The author has an hindex of 7, co-authored 30 publications receiving 160 citations. Previous affiliations of Laimutis Telksnys include Vytautas Magnus University.
Papers
More filters
••
TL;DR: The isolated word speech recognition system based on dynamic time warping (DTW) has been developed and performance is evaluated using 12 words of Lithuanian language pronounced ten times by ten speakers.
Abstract: The isolated word speech recognition system based on dynamic time warping (DTW) has been developed. Speaker adaptation is performed using speaker recognition techniques. Vector quantization is used to create reference templates for speaker recognition. Linear predictive coding (LPC) parameters are used as features for recognition. Performance is evaluated using 12 words of Lithuanian language pronounced ten times by ten speakers.
39 citations
••
TL;DR: A novel approach to improve the sensitivity of the "out of lab" portable capillary electrophoretic measurements by using an optimal averaging window size and a migration velocity-adaptive moving average method that can be easily implemented with a microcontroller.
Abstract: In the present work, we demonstrate a novel approach to improve the sensitivity of the “out of lab” portable capillary electrophoretic measurements. Nowadays, many signal enhancement methods are (i) underused (nonoptimal), (ii) overused (distorts the data), or (iii) inapplicable in field-portable instrumentation because of a lack of computational power. The described innovative migration velocity-adaptive moving average method uses an optimal averaging window size and can be easily implemented with a microcontroller. The contactless conductivity detection was used as a model for the development of a signal processing method and the demonstration of its impact on the sensitivity. The frequency characteristics of the recorded electropherograms and peaks were clarified. Higher electrophoretic mobility analytes exhibit higher-frequency peaks, whereas lower electrophoretic mobility analytes exhibit lower-frequency peaks. On the basis of the obtained data, a migration velocity-adaptive moving average algorithm ...
16 citations
••
TL;DR: The methodology for quality estimation of speech features is presented and the most proper metric was chosen in combination with Dynamic Time Warping (DTW) classifier.
Abstract: The best feature set selection is the key of successful speech recognition system. Quality measure is needed to characterize the chosen feature set. Variety of feature quality metrics are proposed by other authors. However, no guidance is given to choose the appropriate metric. Also no metrics investigations for speech features were made. In the paper the methodology for quality estimation of speech features is presented. Metrics have to be chosen on the ground of their correlation with classification results. Linear Frequency Cepstrum (LFCC), Mel Frequency Cepstrum (MFCC), Perceptual Linear Prediction (PLP) analyses were selected for experiment. The most proper metric was chosen in combination with Dynamic Time Warping (DTW) classifier. Experimental investigation results are presented. Ill. 5, bibl. 18, tabl. 3 (in English; abstracts in English and Lithuanian). http://dx.doi.org/10.5755/j01.eee.110.4.302
11 citations
••
TL;DR: Electropherogram baseline compensation that is suitable for the capillary electrophoresis–contactless conductivity detection analytical method and can be programmed in‐line using simple microcontroller, or on‐line and off‐line in data acquisition software.
Abstract: One of the main problems of the remote complex sample analysis instrumentation is that such systems are susceptible to temperature fluctuations. Temperature regulation is energetically ineffective, and it is not used in most of the field portable analytical systems. Separations performed in a changing temperature environment provide electropherograms with considerable baseline fluctuations, resulting in significant errors in detection and integration of the peaks. This paper describes electropherogram baseline compensation that is suitable for the capillary electrophoresis-contactless conductivity detection analytical method. The baseline compensation utilizes linear or polynomial data processing methods, and can be programmed in-line using simple microcontroller, or on-line and off-line in data acquisition software. This method is targeted for field portable and autonomous analytical systems that are utilized in a fluctuating environment.
11 citations
••
TL;DR: The analysis of experimental results proved that the biggest influence on recognition accuracy has environments’ in which speech commands’ recognition are used and size set of etalons of speech commands used for training.
Abstract: Factors influencing accuracy of speech recognitions is investigated The main attention was given to environment, training conditions and features The results of the influence of the factors to the accuracy of speech recognition are presented The analysis of experimental results proved that the biggest influence on recognition accuracy has environments’ in which speech commands’ recognition are used and size set of etalons of speech commands used for training
11 citations
Cited by
More filters
01 Jan 1979
TL;DR: This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis and addressing interesting real-world computer Vision and multimedia applications.
Abstract: In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to: • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information. Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.
1,758 citations
••
01 Jan 1990TL;DR: This chapter introduces the subject of statistical pattern recognition (SPR) by considering how features are defined and emphasizes that the nearest neighbor algorithm achieves error rates comparable with those of an ideal Bayes’ classifier.
Abstract: This chapter introduces the subject of statistical pattern recognition (SPR). It starts by considering how features are defined and emphasizes that the nearest neighbor algorithm achieves error rates comparable with those of an ideal Bayes’ classifier. The concepts of an optimal number of features, representativeness of the training data, and the need to avoid overfitting to the training data are stressed. The chapter shows that methods such as the support vector machine and artificial neural networks are subject to these same training limitations, although each has its advantages. For neural networks, the multilayer perceptron architecture and back-propagation algorithm are described. The chapter distinguishes between supervised and unsupervised learning, demonstrating the advantages of the latter and showing how methods such as clustering and principal components analysis fit into the SPR framework. The chapter also defines the receiver operating characteristic, which allows an optimum balance between false positives and false negatives to be achieved.
1,189 citations
•
01 Jan 1989
TL;DR: This paper presents principal characteristics of speech speech production models speech analysis and analysis-synthesis systems linear predictive coding (LPC) analysis speech coding speech synthesis speech recognition future directions of speech processing.
Abstract: Principal characteristics of speech speech production models speech analysis and analysis-synthesis systems linear predictive coding (LPC) analysis speech coding speech synthesis speech recognition future directions of speech processing. Appendices: convolution and z-transform vector quantization algorithm neural nests.
307 citations
01 Jan 2006
253 citations