Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

Fine-Tuning VGG19 with Mel Spectrograms for Amazigh Spoken Digit Recognition

Domaine:

natural language processing

Type de record:

paper
Créateur:
HosAbdMohJam
Éditeur:
EDP
Hôte:
This paper shows an improvement in speech recognition performance for the Amazigh language using the VGG19 model. We utilized a database of the first ten spoken Amazigh numbers, and we employed mel spectrograms as the visual representation of the audio. In the initial experiment, we froze the feature extraction layers of the VGG19, and trained only the custom classification layers, under the same training conditions as our previous work. This approach resulted in a recognition accuracy of 75.55%. Then, fine-tuning the entire model over 10 epochs improved the recognition accuracy to 89.33%.

Visit

doi.org

Tasks

automatic speech recognitionspeech processing

Languages

AmazighBerber

Licenses

https://creativecommons.org/licenses/by/4.0/

Similaires

Amazigh Spoken Digit Recognition using a Deep Learning Approach based on MFCCsykeb21/Fine-Tuning-OpenAI-Whisper-for-Amharic-Speech-RecognitionAmazigh CNN speech recognition system based on Mel spectrogram feature extraction methodSwahili Speech Dataset Development and Improved Pre-training Method for Spoken Digit RecognitionFine-Tuning SLAM-ASR for Low-Resource Language Speech Recognition with High-Resource AlignmentBi-directional Recurrent End-to-End Neural Network Classifier for Spoken Arab Digit Recognition

Amazigh Spoken Digit Recognition using a Deep Learning Approach based on MFCC

The field of speech recognition has made human-machine voice interaction more convenient. Recognizin

sykeb21/Fine-Tuning-OpenAI-Whisper-for-Amharic-Speech-Recognition

This repository contains a complete, memory-optimized pipeline for fine-tuning OpenAI’s Whisper auto

Amazigh CNN speech recognition system based on Mel spectrogram feature extraction method

Swahili Speech Dataset Development and Improved Pre-training Method for Spoken Digit Recognition

Speech dataset is an essential component in building commercial speech applications. However, low-re

Fine-Tuning SLAM-ASR for Low-Resource Language Speech Recognition with High-Resource Alignment

Large language models (LLMs) have demonstrated potential in handling spoken inputs for high-resource

Bi-directional Recurrent End-to-End Neural Network Classifier for Spoken Arab Digit Recognition

International audience —Automatic Speech Recognition can be considered as a transcrip