WER We Stand: Benchmarking Urdu ASR Models

Samee Arif, Aamina Jamal Khan, Mustafa Abbas, Agha Ali Raza, Awais Athar
{"title":"WER We Stand: Benchmarking Urdu ASR Models","authors":"Samee Arif, Aamina Jamal Khan, Mustafa Abbas, Agha Ali Raza, Awais Athar","doi":"arxiv-2409.11252","DOIUrl":null,"url":null,"abstract":"This paper presents a comprehensive evaluation of Urdu Automatic Speech\nRecognition (ASR) models. We analyze the performance of three ASR model\nfamilies: Whisper, MMS, and Seamless-M4T using Word Error Rate (WER), along\nwith a detailed examination of the most frequent wrong words and error types\nincluding insertions, deletions, and substitutions. Our analysis is conducted\nusing two types of datasets, read speech and conversational speech. Notably, we\npresent the first conversational speech dataset designed for benchmarking Urdu\nASR models. We find that seamless-large outperforms other ASR models on the\nread speech dataset, while whisper-large performs best on the conversational\nspeech dataset. Furthermore, this evaluation highlights the complexities of\nassessing ASR models for low-resource languages like Urdu using quantitative\nmetrics alone and emphasizes the need for a robust Urdu text normalization\nsystem. Our findings contribute valuable insights for developing robust ASR\nsystems for low-resource languages like Urdu.","PeriodicalId":501284,"journal":{"name":"arXiv - EE - Audio and Speech Processing","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - EE - Audio and Speech Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11252","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

This paper presents a comprehensive evaluation of Urdu Automatic Speech Recognition (ASR) models. We analyze the performance of three ASR model families: Whisper, MMS, and Seamless-M4T using Word Error Rate (WER), along with a detailed examination of the most frequent wrong words and error types including insertions, deletions, and substitutions. Our analysis is conducted using two types of datasets, read speech and conversational speech. Notably, we present the first conversational speech dataset designed for benchmarking Urdu ASR models. We find that seamless-large outperforms other ASR models on the read speech dataset, while whisper-large performs best on the conversational speech dataset. Furthermore, this evaluation highlights the complexities of assessing ASR models for low-resource languages like Urdu using quantitative metrics alone and emphasizes the need for a robust Urdu text normalization system. Our findings contribute valuable insights for developing robust ASR systems for low-resource languages like Urdu.
我们的立场:乌尔都语 ASR 模型基准测试
本文全面评估了乌尔都语自动语音识别(ASR)模型。我们分析了三种 ASR 模式家族的性能:我们使用词错误率 (WER) 分析了三种 ASR 模式家族的性能:Whisper、MMS 和 Seamless-M4T,并详细分析了最常见的错词和错误类型,包括插入、删除和替换。我们使用阅读语音和对话语音两种数据集进行分析。值得注意的是,我们首次提出了用于对 UrduASR 模型进行基准测试的会话语音数据集。我们发现,seamless-large 在阅读语音数据集上的表现优于其他 ASR 模型,而 whisper-large 在对话语音数据集上的表现最好。此外,这项评估还凸显了仅使用定量指标对乌尔都语等低资源语言的 ASR 模型进行评估的复杂性,并强调了对强大的乌尔都语文本规范化系统的需求。我们的研究结果为开发适用于乌尔都语等低资源语言的强大 ASR 系统提供了宝贵的见解。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信