Svarah: Evaluating English ASR Systems on Indian Accents

被引：1

作者：

Javed, Tahir ^{[1
,2
]}

Joshi, Sakshi ^{[2
]}

Nagarajan, Vignesh ^{[2
]}

Sundaresan, Sai ^{[2
]}

Nawale, Janki ^{[2
]}

Raman, Abhigyan ^{[2
]}

Bhogale, Kaushal ^{[2
]}

Kumar, Pratyush ^{[2
,3
]}

Khapra, Mitesh M. ^{[2
]}

机构：

[1] Indian Inst Technol Madras, Chennai, India

[2] AI4Bharat, Chennai, India

[3] Microsoft, Redmond, WA USA

来源：

INTERSPEECH 2023 | 2023年

关键词：

non-native speech recognition; Indian accents; diversity; and inclusion;

D O I：

10.21437/Interspeech.2023-2588

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

India is the second largest English-speaking country in the world with a speaker base of roughly 130 million. Thus, it is imperative that automatic speech recognition (ASR) systems for English should be evaluated on Indian accents. Unfortunately, Indian speakers find a very poor representation in existing English ASR benchmarks such as LibriSpeech, Switchboard, Speech Accent Archive, etc. In this work, we address this gap by creating Svarah, a benchmark that contains 9.6 hours of transcribed English audio from 117 speakers across 65 geographic locations throughout India, resulting in a diverse range of accents. Svarah comprises both read speech and spontaneous conversational data, covering various domains, such as history, culture, tourism, etc., ensuring a diverse vocabulary. We evaluate 6 open source ASR models and 2 commercial ASR systems on Svarah and show that there is clear scope for improvement on Indian accents.

引用

页码：5087 / 5091

页数：5