Diacritic Recognition Performance in Arabic ASR

Hanan Aldarmaki, Ahmad Ghannam

MBZUAI

阿拉伯语 ASR 中的变音符号识别性能
要点：

1.分析了阿拉伯语自动语音识别 (ASR) 系统中的变音符号识别性能。 由于大多数现有的阿拉伯语语音语料库不包含所有变音符号，这些变音符号代表阿拉伯文字中的短元音和其他语音信息，因此当前最先进的 ASR 模型不会在其输出中产生完整的变音符号。 基于文本的自动变音以前被用作训练变音 ASR 的预处理步骤，或作为后处理步骤来变音生成的 ASR 假设。 人们普遍认为输入变音会降低 ASR 性能，但迄今为止还没有独立于 ASR 性能的对 ASR 变音性能的系统评估。

2.在本文中，试图通过实验阐明输入变音符号是否确实会降低 ASR 质量，并将变音符号识别性能与基于文本的变音符号作为后处理步骤进行比较。 我们从预训练的阿拉伯语 ASR 模型开始，并在具有不同变音条件的转录语音数据上对其进行微调：手动、自动和无变音。 我们使用覆盖率和精度指标将变音符号识别性能与整体 ASR 性能隔离开来。 我们发现 ASR 变音在后处理中明显优于基于文本的变音，特别是当 ASR 模型使用手动变音转录本进行微调时。[机器翻译+人工校对]

We present an analysis of diacritic recognition performance in Arabic Automatic Speech Recognition (ASR) systems. As most existing Arabic speech corpora do not contain all diacritical marks, which represent short vowels and other phonetic information in Arabic script, current state-of-the-art ASR models do not produce full diacritization in their output. Automatic text-based diacritization has previously been employed both as a pre-processing step to train diacritized ASR, or as a post-processing step to diacritize the resulting ASR hypotheses. It is generally believed that input diacritization degrades ASR performance, but no systematic evaluation of ASR diacritization performance, independent of ASR performance, has been conducted to date. In this paper, we attempt to experimentally clarify whether input diacritiztation indeed degrades ASR quality, and to compare the diacritic recognition performance against text-based diacritization as a post-processing step. We start with pre-trained Arabic ASR models and fine-tune them on transcribed speech data 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 in post-processing, particularly when the ASR model is fine-tuned with manually diacritized transcripts.

https://arxiv.org/ftp/arxiv/papers/2302/2302.14022.pdf

内容中包含的图片若涉及版权问题，请及时与我们联系删除