Abstract
In this paper, the systems of speaker identification of a text-dependent and independent nature were considered. Feature extraction was performed using chalk-frequency cepstral coefficients (MFCC). The vector quantization method for the automatic identification of a person by voice has been investigated. Using the extracted features, the code book from each speaker was built by clustering the feature vectors. Speakers were modeled using vector quantization (VQ). Using the extracted features, the code book from each speaker was built by clustering the feature vectors. Codebooks of all announcers were collected in the database. From the results, it can be said that vector quantization using cepstral features produces good results for creating a voice recognition system.
Publisher
Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP
Subject
Electrical and Electronic Engineering,Mechanics of Materials,Civil and Structural Engineering,General Computer Science
Cited by
5 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. Approaches to Solving Problems of Markov Modeling Training in Speech Recognition;Lecture Notes in Networks and Systems;2024
2. Formation of a Speech Database in the Karakalpak Language for Speech Synthesis Systems;Lecture Notes in Networks and Systems;2024
3. Automatic Speech Recognition on the Neutral Network Based on Attention Mechanism;Intelligent Human Computer Interaction;2023
4. Methods for determining speech activity of uzbek speech in recognition systems;PROBLEMS IN THE TEXTILE AND LIGHT INDUSTRY IN THE CONTEXT OF INTEGRATION OF SCIENCE AND INDUSTRY AND WAYS TO SOLVE THEM: (PTLICISIWS-2022);2023
5. Construction of Language Models for Uzbek Language;2022 International Conference on Information Science and Communications Technologies (ICISCT);2022-09-28