ABSTRACT
MFCC is widely used in the field of voiceprint recognition, and has achieved remarkable effects. However, MFCC focuses on the short-term spectrum characteristics of speech, while ignoring the self-similarity of speech itself. Fractal has the self-similarity characteristic of non-integer dimension. It is often used to describe the evolution of nature, such as Brownian motion, coastline, rock strata and minerals. Based on MFCC, we try to introduce fractal dimension, which makes up for the lack of self-similarity of MFCC. The experimental results show that compared with MFCC, the fractal dimension modified MFCC (FDMFCC) has improved accuracy and stability.
- GAO Xiao-li, LI Jie, WAMG Wei, ZHAO Huo-jun, LUO Ming-wei. 2021. Individual Identification Method of Automobile Engine Voiceprint Based on CRNN. Fire Control & Command Control, 2021(3):150-154.Google Scholar
- OUYANG Cheng Tian, YUAN Jin. 2021. Voiceprint diagnosis method of air conditioning compressor based on learning vector quantization. Computer Engineering and Design, 2021(9):2634-2641.Google Scholar
- J. Yang, Z. Feng, J. Wu and Y. Fan, "Research on Voiceprint recognition method of buried drainage pipe based on MFCC and GMM-HMM," 2021 33rd Chinese Control and Decision Conference (CCDC), 2021, pp. 645-650, doi: 10.1109/CCDC52312.2021.9601645.Google Scholar
- A. Benba, A. Jilbab, A. Hammouch and S. Sandabad, "Voiceprints analysis using MFCC and SVM for detecting patients with Parkinson's disease," 2015 International Conference on Electrical and Information Technologies (ICEIT), 2015, pp. 300-304, doi: 10.1109/EITech.2015.7163000.Google Scholar
- S. Dasgupta, K. Harisudha and S. Masunda, "Voiceprint analysis for Parkinson's disease using MFCC, GMM, and instance based learning and multilayer perceptron," 2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI), 2017, pp. 1679-1682, doi: 10.1109/ICPCSI.2017.8391999.Google Scholar
- H. Zhang, A. Wang, D. Li and W. Xu, "DeepVoice: A voiceprint-based mobile health framework for Parkinson's disease identification," 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), 2018, pp. 214-217, doi: 10.1109/BHI.2018.8333407.Google Scholar
- Thomas Fang Zheng, Askar Rozi, Wang Renyu, Li Lantian. 2016. Journal of Information Security Research, 2016(1):12-16.Google Scholar
- Wang Xue-guang, ZHU Jun-wen, ZHANG Ai-xin. 2021. Identification Method of Voiceprint Identity Based on MFCC Feature. Computer Science, 2021(12):343-348.Google Scholar
- J. Zhang, "The Algorithm of Voiceprint Recognition Model based DNN-RELIANCE," 2020 International Conference on Computer Engineering and Application (ICCEA), 2020, pp. 250-253, doi: 10.1109/ICCEA50009.2020.00061.Google ScholarCross Ref
- Y. Gu, A. Shi and R. Ma, "Voiceprint Recognition Based on Big Data and Gaussian Mixture Model," 2021 6th International Conference on Smart Grid and Electrical Automation (ICSGEA), 2021, pp. 267-270, doi: 10.1109/ICSGEA53208.2021.00065.Google Scholar
- L. Min, Z. Huamao and Q. Annan, "Voiceprint Recognition of Transformer Fault Based on Blind Source Separation and Convolutional Neural Network," 2021 IEEE Electrical Insulation Conference (EIC), 2021, pp. 618-621, doi: 10.1109/EIC49891.2021.9612322.Google Scholar
- Y. Wu, L. Xu, Y. Chen and X. Zhang, "Research on voiceprint recognition based on weighted clustering recognition SVM algorithm," 2017 Chinese Automation Congress (CAC), 2017, pp. 1144-1148, doi: 10.1109/CAC.2017.8242938.Google Scholar
- G. Feng and X. Chang, "The Research of Forensic Voiceprint Identification Based on WMFCC," 2019 IEEE 5th International Conference on Computer and Communications (ICCC), 2019, pp. 1696-1700, doi: 10.1109/ICCC47050.2019.9064211.Google Scholar
- MFCC. 2013. Retrieved March 18, 2022 from https://blog.csdn.net/zouxy09/article/details/9156785Google Scholar
- Wen Zhiying, Fan Aihua. 1998. Fractal Geometry Theory and Its Applications. Zhejiang Science & Technology Publishing House, 1998:6-17.Google Scholar
Recommendations
Pitch adaptive MFCC features for improving children's mismatched ASR
A pitch normalization algorithm is proposed for addressing the pitch mismatch between adults' and children's speech for children's automatic speech recognition (ASR). Motivated by the appearance of pitch-dependent distortions in the smoothed mel ...
MFCC-GMM based accent recognition system for Telugu speech signals
Speech processing is very important research area where speaker recognition, speech synthesis, speech codec, speech noise reduction are some of the research areas. Many of the languages have different speaking styles called accents or dialects. ...
Comparative study of different classifiers based speaker recognition system using modified MFCC for noisy environment
ICGCIOT '15: Proceedings of the 2015 International Conference on Green Computing and Internet of Things (ICGCIoT)Speaker recognition has made great progress under the laboratory environment, but in real life the performance of speaker recognition system is affected by various factors including environmental noise. This paper studies the performance of speaker ...
Comments