Diacritic Recognition Performance in Arabic ASR

Hanan Aldarmaki, Ahmad Ghannam

Research output: Contribution to journalConference articlepeer-review

1 Citation (Scopus)

Abstract

In Arabic text, most vowels are encoded in the form of diacritics that are often omitted, so most speech corpora and ASR models are undiacritized. Text-based diacritization has previously been used to preprocess the input or post-processs ASR hypotheses. It is generally believed that input diacritization degrades ASR quality, but no systematic evaluation of ASR diacritization performance has been conducted to date. We experimentally clarify whether input diacritiztation indeed degrades ASR quality and compare ASR diacritization with text-based diacritization. We fine-tune pre-trained ASR models on transcribed speech with different diacritization conditions: manual, automatic, and no diacritization. We isolate diacritic recognition performance from the overall ASR performance using coverage and precision metrics. We find that ASR diacritization significantly outperforms text-based diacritization, particularly when the ASR model is fine-tuned with manually diacritized transcripts.

Original languageEnglish
Pages (from-to)361-365
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume2023-August
DOIs
Publication statusPublished - 2023
Externally publishedYes
Event24th International Speech Communication Association, Interspeech 2023 - Dublin, Ireland
Duration: Aug 20 2023Aug 24 2023

Keywords

  • arabic speech recognition
  • automatic diacritization

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modelling and Simulation

Fingerprint

Dive into the research topics of 'Diacritic Recognition Performance in Arabic ASR'. Together they form a unique fingerprint.

Cite this