Improved Speaker Recognition with Convolutional Neural Networks and MFCC Feature Extraction
- 1 August 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
This paper explores the application of deep learning (DL) techniques, specifically Convolutional Neural Networks (CNN), for speaker recognition using Mel-Frequency Cepstral Coefficients (MFCC) as the feature extraction method. The speaker recognition, which relies on unique vocal characteristics, faces challenges such as speech variability, background noise, and microphone differences. These factors complicate the creation of stable speech templates, making accurate recognition systems difficult to implement. To address these challenges, the study employs MFCC for feature extraction along with a novel CNN1D model for recognition tasks. This suggested method is evaluated using various datasets, including 50-speaker audio data, the DARPA TIMIT dataset with 454 speakers across 8 dialect regions, and other sample sets. Experimental results demonstrate the effectiveness of the MFCC + CNN approach, achieving an accuracy of 93% for 2462 speech samples and up to 98.01% for 750 samples. The study highlights the significant impact of dataset size on model performance, with larger datasets yielding higher accuracy. Despite the promising results, challenges related to speech variability and environmental factors remain. Future work will explore the use of CNN2D with spectrogram images as input, potentially enhancing performance further. This research contributes to the ongoing development of robust speaker recognition systems built on DL(deep learning) techniques.Keywords
This publication has 11 references indexed in Scilit:
- Mel Frequency Cepstral Coefficient and its Applications: A ReviewIEEE Access, 2022
- PF-Net: Personalized Filter for Speaker Recognition from Raw Waveform2022
- Text-independent speaker recognition based on adaptive course learning loss and deep residual networkEURASIP Journal on Advances in Signal Processing, 2021
- Deep Speaker Recognition: Process, Progress, and ChallengesIEEE Access, 2021
- Speaker Recognition with ResNet and VGG Networks2021
- Automatic Speaker Recognition using Transfer Learning Approach of Deep Learning Models2021
- Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs2020
- AutoSpeech: Neural Architecture Search for Speaker Recognition2020
- Convolutional Neural Network for Automatic Speech Recognition of Filipino LanguageInternational Journal of Advanced Trends in Computer Science and Engineering, 2020
- Speaker Recognition from Raw Waveform with SincNet2018