Saved in:
| Main Author: | |
|---|---|
| Format: | Artículo científico |
| Language: | pt |
| Published: |
Universidade Federal de Minas Gerais
2024
|
| Subjects: | |
| Online Access: | https://www.redalyc.org/articulo.oa?id=577176427016 https://www.redalyc.org/journal/5771/577176427016/ https://www.redalyc.org/journal/5771/577176427016/html/ https://www.redalyc.org/journal/5771/577176427016/577176427016.epub https://www.redalyc.org/journal/5771/577176427016/movil |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- Artificial intelligence-generated Arabic subtitles: insights from Veed.io’s automatic speech recognition system of Jordanian Arabic Wala’ Mohammad Akasheh Ahmad S. Haider Bassam Al-Saideen Yousef Sahari Multidisciplinarias (Ciencias, Ciencias Sociales, Artes y Humanidades) Legendas Linguística Árabe jordaniano Legendas geradas automaticamente Reconhecimento Automático de Fala This paper examines the errors that the automatic speech recognition (ASR) system of Veed.io produces when transcribing utterances spoken in Jordanian Arabic into subtitles. It attempts to propose a new classification for the subtitles that are built based on artificial intelligence technology. Through a combination of qualitative and quantitative analyses, the study examines the types of errors and their impact on comprehension. The errors observed in the generated subtitles based on linguistic and phonetic analysis are categorised into three main types: deletions, substitutions, and insertions. Furthermore, the quantitative analysis measures the word error rate (WER) and shows that the WER percentage is 38.857% revealing that deletions are the most common type of error, followed by substitutions and insertions. The study recommends conducting further research on ASR systems for Arabic language dialects and advises subtitlers to be aware of the limitations of these systems when using them, ensuring that they edit and supervise them appropriately. 2024 artículo científico 1983-3652 https://www.redalyc.org/articulo.oa?id=577176427016 https://www.redalyc.org/journal/5771/577176427016/ https://www.redalyc.org/journal/5771/577176427016/html/ https://www.redalyc.org/journal/5771/577176427016/577176427016.epub https://www.redalyc.org/journal/5771/577176427016/movil 10.1590/1983-3652.2024.46952 pt http://www.redalyc.org/revista.oa?id=5771 Texto Livre: Linguagem e Tecnologia application/pdf Universidade Federal de Minas Gerais Texto Livre: Linguagem e Tecnologia (Brasil) Vol.17