# MediaSpeech: Multilanguage ASR Benchmark and Dataset

arXiv: https://arxiv.org/abs/2103.16193 · HTML: https://mlsanity.com/paper/2103.16193/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Mar 2021.

## Built on by (most cited first, 17 of 17)

- [CL-MASR: A Continual Learning Benchmark for Multilingual ASR](https://mlsanity.com/paper/2310.16931/) (2023)
- [MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages](https://mlsanity.com/paper/2410.01036/) (2024)
- [Resources for Turkish Natural Language Processing: A critical survey](https://mlsanity.com/paper/2204.05042/) (2022)
- [BERSting at the Screams: A Benchmark for Distanced, Emotional and Shouted Speech Recognition](https://mlsanity.com/paper/2505.00059/) (2025)
- [Arab Voices: Mapping Standard and Dialectal Arabic Speech Technology](https://mlsanity.com/paper/2601.13319/) (2026)
- [Swivuriso: The South African Next Voices Multilingual Speech Dataset](https://mlsanity.com/paper/2512.02201/) (2025)
- [A New Benchmark for Evaluating Automatic Speech Recognition in the Arabic Call Domain](https://mlsanity.com/paper/2403.04280/) (2024)
- [Inclusivity of AI Speech in Healthcare: A Decade Look Back](https://mlsanity.com/paper/2505.10596/) (2025)
- [Ara-Best-RQ: Multi Dialectal Arabic SSL](https://mlsanity.com/paper/2603.21900/) (2026)
- [Modernizing Open-Set Speech Language Identification](https://mlsanity.com/paper/2205.10397/) (2022)
- [Open Automatic Speech Recognition Models for Classical and Modern Standard Arabic](https://mlsanity.com/paper/2507.13977/) (2025)
- [Efficient ASR for Low-Resource Languages: Leveraging Cross-Lingual Unlabeled Data](https://mlsanity.com/paper/2512.07277/) (2025)
- [Automatic Spoken Language Identification using a Time-Delay Neural Network](https://mlsanity.com/paper/2205.09564/) (2022)
- [Robust Open-Set Spoken Language Identification and the CU MultiLang Dataset](https://mlsanity.com/paper/2308.14951/) (2023)
- [From Black Box to Glass Box: Cross-Model ASR Disagreement to Prioto Review in Ambient AI Scribe Documentation](https://mlsanity.com/paper/2604.14152/) (2026)
- [Evaluating Bias in Phoneme-Based Automatic Speech Recognition Systems: An Analysis of IPA Transcription Models](https://mlsanity.com/paper/2606.11639/) (2026)
- [Benchmarking Automatic Speech Recognition Tools for Iberian Languages](https://mlsanity.com/paper/2609.36920/) (2026)

## Abstract (arXiv)

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.