Pith. sign in

REVIEW 3 cited by

MediaSpeech: Multilanguage ASR Benchmark and Dataset

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2103.16193 v1 pith:L4Y6ZTLR submitted 2021-03-30 eess.AS cs.SD

Rostislav Kolobov , Olga Okhapkina , Olga Omelchishina , Andrey Platunov , Roman Bedyakin , Vyacheslav Moshkin , Dmitry Menshikov , Nikolay Mikhaylovskiy This is my paper · ORCID
classification eess.AScs.SD
keywords datasetbenchmarkdomainslanguagesmediaspeechopen-sourceresultssystems
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Swivuriso: The South African Next Voices Multilingual Speech Dataset

    cs.CL 2025-12 conditional novelty 7.0 of 10

    Swivuriso provides a 3,000-hour, seven-language, scripted-and-unscripted South African speech corpus with domain coverage in agriculture, healthcare, and general topics.

  2. BERSting at the Screams: A Benchmark for Distanced, Emotional and Shouted Speech Recognition

    cs.CL 2025-04 conditional novelty 6.0 of 10

    BERSt is a new benchmark showing that state-of-the-art speech recognition degrades with distance and shouting, and emotion recognition performs poorly on such speech.

  3. Inclusivity of AI Speech in Healthcare: A Decade Look Back

    cs.CY 2025-05 conditional novelty 4.0 of 10

    A decade-long audit finds persistent inclusivity gaps in speech AI for healthcare: English-heavy datasets, little demographic metadata, no speech-impaired samples, and limited bias research.

Pith tools