• Home
  • Search
  • A Deep Neural Network Model for Speaker Identification
  • Open Access IconOpen Access
  • Cite Icon120
  • https://doi.org/10.3390/app11083603Copy DOI Icon

A Deep Neural Network Model for Speaker Identification

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Speaker identification is a classification task which aims to identify a subject from a given time-series sequential data. Since the speech signal is a continuous one-dimensional time series, most of the current research methods are based on convolutional neural network (CNN) or recurrent neural network (RNN). Indeed, these methods perform well in many tasks, but there is no attempt to combine these two network models to study the speaker identification task. Due to the spectrogram that a speech signal contains, the spatial features of voiceprint (which corresponds to the voice spectrum) and CNN are effective for spatial feature extraction (which corresponds to modeling spectral correlations in acoustic features). At the same time, the speech signal is in a time series, and deep RNN can better represent long utterances than shallow networks. Considering the advantage of gated recurrent unit (GRU) (compared with traditional RNN) in the segmentation of sequence data, we decide to use stacked GRU layers in our model for frame-level feature extraction. In this paper, we propose a deep neural network (DNN) model based on a two-dimensional convolutional neural network (2-D CNN) and gated recurrent unit (GRU) for speaker identification. In the network model design, the convolutional layer is used for voiceprint feature extraction and reduces dimensionality in both the time and frequency domains, allowing for faster GRU layer computation. In addition, the stacked GRU recurrent network layers can learn a speaker’s acoustic features. During this research, we tried to use various neural network structures, including 2-D CNN, deep RNN, and deep LSTM. The above network models were evaluated on the Aishell-1 speech dataset. The experimental results showed that our proposed DNN model, which we call deep GRU, achieved a high recognition accuracy of 98.96%. At the same time, the results also demonstrate the effectiveness of the proposed deep GRU network model versus other models for speaker identification. Through further optimization, this method could be applied to other research similar to the study of speaker identification.

Loading PDF

Similar Papers
  • Conference Article
  • Citations2

First-Break Picking Classification Models Using Recurrent Neural Network

  • Dec 15, 2021
  • Mohammed Ayub +1
  • Research Article
  • Citations31

Text recognition in document images obtained by a smartphone based on deep convolutional and recurrent neural network

  • Jun 11, 2019
  • Multimedia Tools and Applications
  • Hassan El Bahi +1
  • PDF
  • Research Article
  • Citations304

A Deep Bidirectional GRU Network Model for Biometric Electrocardiogram Classification Based on Recurrent Neural Networks

  • Jan 01, 2019
  • IEEE Access
  • Htet Myet Lynn +2
  • Conference Article
  • Citations12

GRU-MF: A Novel Appliance Classification Method for Non-Intrusive Load Monitoring Data

  • Nov 03, 2022
  • Aji Gautama Putrada +3
  • Research Article
  • Citations111

Tunnel boring machine vibration-based deep learning for the ground identification of working faces

  • Dec 01, 2021
  • Journal of Rock Mechanics and Geotechnical Engineering
  • Mengbo Liu +5
  • Conference Article
  • Citations1

An Investigation into the Detection of Human Scratching Activity Based on Deep Learning Models

  • Apr 28, 2023
  • Kevin Wang
  • Research Article
  • Citations81

Assessing the imperative of conditioning factor grading in machine learning-based landslide susceptibility modeling: A critical inquiry

  • Dec 07, 2023
  • CATENA
  • Taorui Zeng +6
  • PDF
  • Research Article
  • Citations82

Time series-based groundwater level forecasting using gated recurrent unit deep neural networks

  • Aug 16, 2022
  • Engineering Applications of Computational Fluid Mechanics
  • Haiping Lin +6
  • Research Article
  • Citations8

Performance Evaluation of Recurrent Neural Networks Applied to Indoor Camera Localization

  • Aug 02, 2022
  • International Journal of Emerging Technology and Advanced Engineering
  • Muhammad S Alam +2
  • Research Article

A Comparative Study of Recurrent Neural Network (RNN) with Gray Relational Analysis for Temporal Data

  • Dec 06, 2025
  • Computer Science, Engineering and Technology
  • Research Article

Speaker identification under noisy conditions using hybrid convolutional neural network and gated recurrent unit

  • Mar 01, 2024
  • IAES International Journal of Artificial Intelligence
  • Wondimu Lambamo Anito +3
  • Research Article
  • Citations8

Extraction of entity relations from Chinese medical literature based on multi-scale CRNN.

  • May 01, 2022
  • Annals of Translational Medicine
  • Tingyin Chen +4
  • PDF
  • Research Article
  • Citations217

Water Level Prediction Model Based on GRU and CNN

  • Jan 01, 2020
  • IEEE Access
  • Mingyang Pan +6
  • Conference Article
  • Citations5

ASSESSING RECURRENT AND CONVOLUTIONAL NEURAL NETWORKS FOR TROPOSPHERIC OZONE FORECASTING IN THE REGION OF VITÓRIA, BRAZIL

  • Jul 27, 2020
  • WIT transactions on ecology and the environment
  • Amilton S R Junior +2
  • Conference Article
  • Citations12

Breast Cancer Prediction Using Deep Learning Technique RNN and GRU

  • Sep 08, 2022
  • Nalinikanta Routray +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.