基礎講座 電気泳動(Electrophoresis)

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.

IEEE transactions on pattern analysis and machine intelligence

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.

Statistical Pattern Recognition

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.

Digital speech processing, synthesis, and recognition

Gæðastjórnunarkerfi : grunnatriði og íðorðasafn = Quality Management Systems : fundamentals and vocabulary.

The phoneme set influence for Lithuanian speech commands recognition accuracy is investigated. Four phoneme sets are discussed. LIEPA speech corpus for training of Acoustic Model is used. The phonetic representation of corpus transcriptions is generated by grapheme-to-phoneme transformation rules. Rule based transformations for Lithuanian language is proposed. Recognition engine with CMU Pocketsphinx decoder is used. Experimental investigation with fixed size test corpus demonstrates that 36 (FZ1.3) phonemes set shows the bests result.

The phoneme set influence for lithuanian speech commands recognition accuracy

Artificial planar systems self-formation process supported by pattern recognition theory and methods are discussed. Concept possibilities to apply pattern recognition power for improving and control self-formation processes are presented.

Self-Formation Supported by Pattern Recognition

The problem of the parsing accuracy of simple sentences is solved. The case of the language with high inflexion is investigated. The task is addressed by the example of the Lithuanian language, which one root can give hundreds or even more than one thousand word forms. The method of estimation of the parsing accuracy of the simple sentences of such language is given, which is based on the usage of knowledge of language consistent patterns. It is taken note, that in the case of language with high inflection and small number of users the usage of the statistical data on language is strongly restricted. The method of the accuracy estimation of the parsing of simple sentences is presented. The algorithm of implementation of the software is described. The validity of the propositions is proved by experiments. The material of the Lithuanian corpus was used for the experiments. The recommendations are given for the increasing of the accuracy of the parsing of simple sentences for the languages with high inflection. DOI: http://dx.doi.org/10.5755/j01.itc.43.4.6700

/pdf/accuracy-of-the-parsing-of-lithuanian-simple-sentences-18jcd41za1.pdf

Accuracy of the Parsing of Lithuanian Simple Sentences

Specifics of hidden Markov model-based speech recognition are investigated. Influence of modeling simple and context-dependent phones, using simple Gaussian, two and three-component Gaussian mixture probability density functions for modeling feature distribution, and incorporating language model are discussed. Word recognition rates and model complexity criteria are used for evaluating suitability of these modifications for practical applications. Development of large vocabulary continuous speech recognition system using HTK toolkit and WSJCAM0 English speech corpus is described. Results of experimental investigations are presented.

/pdf/specifics-of-hidden-markov-model-modifications-for-large-558jvz5qrc.pdf

Specifics of Hidden Markov Model Modifications for Large Vocabulary Continuous Speech Recognition

The concept of audiovisual interface between human and stochastic process modeling and analysis software is investigated. Examples revealing the advantages of audiovisual interface over audio-only interface are given.

Laimutis Telksnys

Papers

The phoneme set influence for lithuanian speech commands recognition accuracy

Self-Formation Supported by Pattern Recognition

Accuracy of the Parsing of Lithuanian Simple Sentences

Specifics of Hidden Markov Model Modifications for Large Vocabulary Continuous Speech Recognition

Human-computer audiovisual interface