AraSpot: Arabic Spoken Command Spotting

Mahmoud Salhab, Haidar Harmanani
3/29/2023
cs.CLcs.AI

No official code found. Best implementation: msalhab96/AraSpot (3 stars, MIT, last commit 2023-03-30).

Abstract

Spoken keyword spotting (KWS) is the task of identifying a keyword in an audio stream and is widely used in smart devices at the edge in order to activate voice assistants and perform hands-free tasks. The task is daunting as there is a need, on the one hand, to achieve high accuracy while at the same time ensuring that such systems continue to run efficiently on low power and possibly limited computational capabilities devices. This work presents AraSpot for Arabic keyword spotting trained on 40 Arabic keywords, using different online data augmentation, and introducing ConformerGRU model architecture. Finally, we further improve the performance of the model by training a text-to-speech model for synthetic data generation. AraSpot achieved a State-of-the-Art SOTA 99.59% result outperforming previous approaches.

View on arXivView PDF

Code Implementations(1)

msalhab96/AraSpotCommunity100%
MIT

The official implementation of the AraSpot research paper

30PythonNov 2, 20223 years agoMIT
nlpspeech-recognitionspeech-synthesis

Similar Papers

Keyword Spotting with Hyper-Matched Filters for Small Footprint Devices

86% match2025

Keyword spotting -- Detecting commands in speech using deep learning

85% match2023

Improving Small Footprint Few-shot Keyword Spotting with Supervision on Auxiliary Data

85% match2023

Enhancing Few-shot Keyword Spotting Performance through Pre-Trained Self-supervised Speech Models

85% match2025

Honk: A PyTorch Reimplementation of Convolutional Neural Networks for Keyword Spotting

84% match1 repo5272017

Utilizing TTS Synthesized Data for Efficient Development of Keyword Spotting Model

84% match2024

Cite this paper

@article{salhab2023araspot,
  title  = {AraSpot: Arabic Spoken Command Spotting},
  author = {Mahmoud Salhab and Haidar Harmanani},
  year   = {2023},
  eprint = {2303.16621},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2303.16621v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2303.16621.svg)](https://codeofpaper.com/paper/2303.16621)

Discussion