Журнал «Современная Наука»

Russian (CIS)English (United Kingdom)
 MOSCOW +7(495)-142-86-81

MODERN APPROACHES TO AUTOMATIC FILTERING OF OBSCENE LEXICON IN MULTIMODAL DATA PROCESSING IN RUSSIAN LANGUAGE

Kapitanov A. I.  (National Research University "MIET" Associate Professor at the Department of Institute of Systems and Software Engineering and Information Technology )

Egorova D. A.  (National Research University "MIET" Applicant )

Zhuginskii I. A.  (National Research University "MIET" Applicant )

Shelamov A. A.  (National Research University "MIET" Applicant )

The article is devoted to the development of a technique and algorithm for automatic filtering of obscene lexicon in multimodal data. The relevance lies in the lack of effective solutions for automatic filtering of obscene lexicon in live broadcasting with Russian language support. The main attention is paid to modern methods of machine learning, which allow to effectively recognise and block unwanted lexicon in streaming data. The research examines the features of the functioning of algorithms using various language models, as well as aspects of content processing in real time. The stages of preprocessing the audio signal, formatting it, and subsequent cleaning are described.

Keywords:profanity, content filtering, audiovisual data, machine learning, language models, stream processing, real-time filtering
 

Read the full article …

Citation link:
Kapitanov A. I., Egorova D. A., Zhuginskii I. A., Shelamov A. A. MODERN APPROACHES TO AUTOMATIC FILTERING OF OBSCENE LEXICON IN MULTIMODAL DATA PROCESSING IN RUSSIAN LANGUAGE // Современная наука: актуальные проблемы теории и практики. Серия: Естественные и Технические Науки. -2024. -№11/2. -С. 95-97 DOI 10.37882/2223-2966.2024.11-2.14
LEGAL INFORMATION:
Reproduction of materials is permitted only for non-commercial purposes with reference to the original publication. Protected by the laws of the Russian Federation. Any violations of the law are prosecuted.
© ООО "Научные технологии"

Terms Publications

Issues of the journals (Archive)

ECONOMICS AND LAW
HUMANITIES
NATURAL AND TECHNICAL SCIENCES
COGNITION

Серия - Natural and Technical Sciences