0

MediaSpeech: Multilanguage ASR Benchmark and Dataset

Open-source NTR MediaSpeech dataset evaluates ASR systems across multiple languages using media content with manual transcriptions and provides benchmark results and baseline QuartzNet models.

Year
2021
Venue
arXiv 2021
Authors
8
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2103.16193ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

The performance of automated speech recognition (ASR) systems is well known to differ for varied application domains. At the same time, vendors and research groups typically report ASR quality results either for limited use simplistic domains (audiobooks, TED talks), or proprietary datasets. To fill this gap, we provide an open-source 10-hour ASR system evaluation dataset NTR MediaSpeech for 4 languages: Spanish, French, Turkish and Arabic. The dataset was collected from the official youtube channels of media in the respective languages, and manually transcribed. We estimate that the WER of the dataset is under 5%. We have benchmarked many ASR systems available both commercially and freely, and provide the benchmark results. We also open-source baseline QuartzNet models for each language.

Authors

8