No abstract

This article discusses the classification algorithms for the problem of personality identification by voice using machine learning methods. We used the MFCC algorithm in the speech preprocessing process. To solve the problem, a comparative analysis of five classification algorithms was carried out. In the first experiment, the support vector method was determined-0.90 and multilayer perceptron-0.83, that showed the best results. In the second experiment, a multilayer perceptron with an accuracy of 0.93 was proposed using the Robust scaler method for personal identification. Therefore, to solve this problem, it is possible to use a multi-layer perceptron, taking into account the specifics of the speech signal.

Grapheme to phoneme conversion is one of the main subsystems of Text-to-Speech (TTS) systems. Converting sequence of written words to their corresponding phoneme sequences for the Persian language is more challenging than other languages; because in the standard orthography of this language the short vowels are omitted and the pronunciation of words depends on their positions in a sentence. Common approaches used in the Persian commercial TTS systems have several modules and complicated models for natural language processing and homograph disambiguation that make the implementation harder as well as reducing the overall precision of system. In this paper we define the grapheme-to-phoneme conversion as a sequential labeling problem; and use the modified Recurrent Neural Networks (RNN) to create a smart and integrated model for this purpose. The recurrent networks are modified to be bidirectional and equipped with Long-Short Term Memory (LSTM) blocks to acquire most of the past and future contextual information for decision making. The experiments conducted in this paper show that in addition to having a unified structure the bidirectional RNN-LSTM has a good performance in recognizing the pronunciation of the Persian sentences with the precision more than 98 percent.

This article describes the methods of creating a system of recognizing the continuous speech of Kazakh language. Studies on recognition of Kazakh speech in comparison with other languages began relatively recently, that is after obtaining independence of the country, and belongs to low resource languages. A large amount of data is required to create a reliable system and evaluate it accurately. A database has been created for the Kazakh language, consisting of a speech signal and corresponding transcriptions. The continuous speech has been composed of 200 speakers of different genders and ages, and the pronunciation vocabulary of the selected language. Traditional models and deep neural networks have been used to train the system. As a result, a word error rate (WER) of 30.01% has been obtained.

There are various methods of objects’ clusterization used in different areas of machine learning. Among the vast amount of clusterization methods, the K-means method is one of the most popular. Such a method has as pros as cons. Speaking about the advantages of this method, we can mention the rather high speed of objects clusterization. The main disadvantage is a necessity to know the number of clusters before the experiment. This paper describes the new way and the new method of clusterization, based on the K-means method. The method we suggest is also quite fast in terms of processing speed, however, it does not require the user to know in advance the exact number of clusters to be processed. The user only has to define the range within which the number of clusters is located. Besides, using suggested method there is a possibility to limit the radius of clusters, which would allow finding objects that express the criteria of one cluster in the most distinctive and accurate way, and it would also allow limiting the number of objects in each cluster within the certain range.