MediaSpeech: Multilanguage ASR Benchmark and Dataset

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.

References in corpus (3)

• MLS: A Large-Scale Multilingual Dataset for Speech Research
• Self-Training for End-to-End Speech Recognition
• Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition

Cited by in corpus (4)

• Augmented Datasheets for Speech Datasets and Ethical Decision-Making
• Resources for Turkish Natural Language Processing: A critical survey
• BERSting at the Screams: A Benchmark for Distanced, Emotional and Shouted Speech Recognition
• From Black Box to Glass Box: Cross-Model ASR Disagreement to Prioto Review in Ambient AI Scribe Documentation