Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
January 1, 2022Procedia Computer ScienceOpen Access

Evaluation of the efficiency of state-of-the-art Speech Recognition engines

View Full Paper
Ask AI
Bookmark
Share

Authors

ATAsma TrabelsiSWSébastien WarichetYAYassine Aajaoun

Discussion

Loading...

Member takes

Overview

Evaluates speech recognition engines in terms of accuracy and inference time for accessibility, enhancing data sovereignty.

Key Points

  • The study aims to evaluate the efficiency of different speech recognition engines, focusing on accuracy and inference time.
  • Theoretically and experimentally compare DeepSpeech, Kaldi, Vosk, and LinTO.
  • Assess the engines based on their accuracy and inference time metrics.
  • Kaldi demonstrated superior accuracy compared to DeepSpeech in various test scenarios.
  • Inference time was significantly lower in Vosk compared to other engines, improving real-time processing capabilities.

Cite This Study

Trabelsi et al. (2022) studied this question.

synapsesocial.com/papers/6a1075e942b7486443ff01f6https://doi.org/10.1016/j.procs.2022.09.534
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Overview of Speech Recognition Algorithms and Their Applications2025
  2. 2Leveraging Artificial Neural Networks for Real-Time Speech Recognition in Voice-Activated Systems2025
  3. 3Dataset and Evaluation of Automatic Speech Recognition for Multi-lingual Intent Recognition on Social Robots2024
  4. 4Exploring the Horizons of Speaker Recognition: Contemporary Advancements and Prospective Trajectories in the Age of Deep Learning2024
  5. 5Towards inclusive and accessible automated speech audiometry using automatic speech recognition2025