Automated definition of phonetically homogeneous sections of words in a natural language based on multiparameter optimization

An approach to the automated splitting of words into phonetically homogeneous parts is proposed under which the boundaries of the parts are defined as a result of solving a multiparameter optimization problem. The approach is assumed to ensure the maximum difference in the phonetic material between...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of computer & systems sciences international Ročník 55; číslo 4; s. 609 - 618
Hlavní autoři: Korsun, O. N., Poliev, A. V.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Moscow Pleiades Publishing 01.07.2016
Springer Nature B.V
Témata:
Algorithms
Analysis
Automation
Boundaries
Computer science
Control
Conversion
Engineering
Fourier transforms
Language
Mathematical models
Mathematical problems
Mechatronics
Natural language
Optimization
Pattern Recognition and Image Processing
Phonetics
Recording
Robotics
Similarity
Sound
Studies
ISSN:1064-2307, 1555-6530
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:An approach to the automated splitting of words into phonetically homogeneous parts is proposed under which the boundaries of the parts are defined as a result of solving a multiparameter optimization problem. The approach is assumed to ensure the maximum difference in the phonetic material between the adjacent parts and the maximum similarity within the parts. The accepted measure of similarity and difference is based on the correlation between the columns of the parametric portrait matrix of the word generated as a result of a time-spectral conversion of an audio recording of the word. To obtain a numerical solution of the problem, an algorithm is proposed which is a modification of a dynamic programming technique. The experimental results are presented with several words from the Russian language taken as examples to confirm the legitimacy of the assumptions made and viability of the algorithms proposed.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1064-2307
1555-6530
DOI:10.1134/S1064230716040080