{"url":"/dataset/esb","name":"ESB","full_name":"End-to-End Speech Benchmark","description_markdown":"**ESB** is a benchmark for evaluating the performance of a single automatic speech recognition (ASR) system across a broad set of speech datasets. It comprises eight English speech recognition datasets, capturing a broad range of domains, acoustic conditions, speaker styles, and transcription requirements.\r\n\r\nSource: [ESB: A Benchmark For Multi-Domain End-to-End Speech Recognition](https://arxiv.org/pdf/2210.13352v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2210.13352v1.pdf](https://arxiv.org/pdf/2210.13352v1.pdf)","description_withheld":null,"homepage":"https://huggingface.co/esb","introduced_date":"2022-10-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/esb-a-benchmark-for-multi-domain-end-to-end","title":"ESB: A Benchmark For Multi-Domain End-to-End Speech Recognition","first_author":"Sanchit Gandhi","url":null},"license":null,"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"},{"name":"Automatic Speech Recognition (ASR)","url":"/task/automatic-speech-recognition","datasets_with_task":"/datasets/task/automatic-speech-recognition"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["ESB"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}