Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: mel-cepstral coefficients

Sortuj według:

Ogranicz wyniki do:

Determination of Input Parameters of the Neural Network Model, Intended for Phoneme Recognition of a Voice Signal in the Systems of Distance Learning

Akhmetov B., Tereykovsky I., Doszhanova A., Tereykovskaya L.

International Journal of Electronics and Telecommunications

2018

Vol. 64, No. 4

425--432

The article is devoted to the problem of voice signals recognition means introduction in the system of distance learning. The results of the conducted research determine the prospects of neural network means of phoneme recognition. It is also shown that the main difficulties of creation of the neural network model, intended for recognition of phonemes in the system of distance learning, are connected with the uncertain duration of a phoneme-like element. Due to this reason for recognition of phonemes, it is impossible to use the most effective type of neural network model on the basis of a multilayered perceptron, at which the number of input parameters is a fixed value. To mitigate this shortcoming, the procedure, allowing to transform the non-stationary digitized voice signal to the fixed quantity of mel-cepstral coefficients, which are the basis for calculation of input parameters of the neural network model, is developed. In contrast to the known ones, the possibility of linear scaling of phoneme-like elements is available in the procedure. The number of computer experiments confirmed expediency of the fact that the use of the offered coding procedure of input parameters provides the acceptable accuracy of neural network recognition of phonemes under near-natural conditions of the distance learning system. Moreover, the prospects of further research in the field of development of neural network means of phoneme recognition of a voice signal in the system of distance learning is connected with an increase in admissible noise level. Besides, the adaptation of the offered procedure to various natural languages, as well as to other applied tasks, for instance, a problem of biometric authentication in the banking sector, is also of great interest.

Speaker identification based on Gaussian mixture model : experiments with Polish language utterances

Dąbrowska A., Drgas S., Cetnarowicz D., Chmielewska I.

Elektronika : konstrukcje, technologie, zastosowania

2008

Vol. 49, nr 4

29-33

In this paper results of experiments with the prototype speaker recognition system based on Gaussian mixture model (GMM) and mel-cepstral coefficients (MFCCs) are presented for Polish Corpora database [4]. The minimum amount of data to train a reliable model and the minimum length of a signal to recognize speakers have been determined. Furthermore, the speaker discriminative properties of Polish phonemes have been investigated. The phonemes with the best speaker discriminative properties have been determined.

Przedstawiono eksperymenty identyfikacji mówcy za pomocą prototypowego systemu rozpoznawania mowy na podstawie sumy rozkładów normalnych (GMM) i współczynników mel-cepstralnych, (MFCC), uzyskanych z wykorzystaniem polskojęzycznej bazy Corpora [4]. W eksperymentach zbadano minimalną ilość danych potrzebnych do wytrenowania wiarygodnego modelu oraz długość sygnału wymaganą do poprawnej klasyfikacji. Ponadto przebadano dyskryminacyjne właściwości polskich fonemów do identyfikacji mówcy. Wyodrębniono fonemy, które w największym stopniu przyczyniają się do poprawnego rozpoznawania.