Publications
Article · December 7, 2020
Development of a personality recognition system by voice
Orken J. Mamyrbayev, Aizat Kydyrbekova, Дина Оралбекова, Багашар Жумажанов, Othman Mohamed
Abstract
Abstract— the paper discusses the development of a voice recognition system based on cepstral coefficients on the chalk scale (Mel-frequency Cepstral Coefficients, MFCC) and mixed Gaussian models (Gaussian Mixture Models, GMM). The aim of the research is to create a simple and convenient automatic speaker recognition system. The description of the created speech database for the Kazakh language is given. Experiments have shown quite good results of the system FAR 8.05%.
Speech Recognition and SynthesisSpeech and Audio ProcessingSpeech and dialogue systemsspeaker recognitionvoice recognitionMel-frequency cepstral coefficients
More by Orken Mamyrbayev
- A Knowledge-Augmented Multi-Agent AI System for Context-Aware Legal Reasoning and Case Outcome PredictionPreprints.org · 2026
- YOLO12 МОДЕЛІН ГЕОРАДАР КЕСКІНДЕРІНЕ ҚОЛДАНУNEWS OF THE NATIONAL ACADEMY OF SCIENCES OF THE REPUBLIC OF KAZAKHSTAN · 2026
- Developing a Kazakh Audio–Visual Multimodal Speech Recognition Model Based on Hierarchical and Cross-Modal AttentionInformation · 2026
- Exploring the influence of firm digital transformation on sustainable competitive advantage through organizational agility with moderation of knowledge sharingDiscover Sustainability · 2026