Talk · IEEE International Conference on Smart Information Systems and Technologies · April 28, 2021
Speaker Recognition from Spectrogram Images
Shirali Kadyrov, Cemil Turan, Altynbek Amirzhanov, Cemal Özdemir
Abstract
Speaker identification is used to identify the owner of the voice among many people based on the uniqueness of everyone's speech style. In this paper, we combine Convolutional Neural Network with Recurrent Neural Network using Long Short-Term Memory models for speaker recognition and implement the deep learning architecture on our dataset of spectrogram images for 77 different non-native speakers reading the same texts in Turkish. Usage of identical text reading eliminates the possible variations and diversities on spectrograms depending on vocabularies. Experiments show that the used method is very effective on recognition rate with satisfying performance and over 98% accuracy.
More by Shirali Kadyrov
- Bounded continued fractions and quadratic orders in $\Q(\sqrt{127})$arXiv · 2026
- Code and data for "Reinforcement learning-based PID for nonlinear temperature control with delayed feedback and measurement noise"Zenodo · 2026
- Life expectancy in Kazakhstan: an integrated analysis and forecastZenodo · 2026
- Data-driven homotopic reinforcement learning for adaptive tracking control of completely unknown Takagi–Sugeno fuzzy Markovian jump systemsCommunications in Nonlinear Science and Numerical Simulation · 2026