{"url":"/dataset/earnings-22","name":"Earnings-22","full_name":null,"description_markdown":"**Earnings-22** is a practical benchmark designed to evaluate **automatic speech recognition (ASR)** systems' performance on real-world, accented audio. Let me provide you with more details:\r\n\r\n1. **Corpus Description**:\r\n   - Earnings-22 consists of **125 audio files** totaling **119 hours** of English-language **earnings calls**. These calls were gathered from **global companies**.\r\n   - Unlike many existing corpora, Earnings-22 focuses on **speech in the wild**, representing real-world scenarios where accents and environmental conditions vary.\r\n\r\n2. **Purpose and Significance**:\r\n   - ASR systems have achieved impressive performance on common corpora but often struggle with real-world speech.\r\n   - Earnings-22 aims to bridge this gap by providing a **free-to-use benchmark** that includes **accented audio**.\r\n   - Researchers and industry professionals can use Earnings-22 to evaluate and improve ASR models' robustness.\r\n\r\n3. **Comparison and Insights**:\r\n   - The benchmark involves **four commercial ASR models**, and their performance is compared.\r\n   - By considering the **country of origin**, the study reveals variations in ASR accuracy.\r\n   - **Individual Word Error Rate (IWER)** analysis highlights how certain accents impact model performance more than others.\r\n\r\n4. **Academic and Industrial Impact**:\r\n   - Earnings-22 serves as a valuable resource for both **academic research** and **industrial applications**.\r\n   - It provides a realistic dataset for evaluating ASR systems' effectiveness in handling diverse accents.\r\n\r\nSource: Conversation with Bing, 3/16/2024\r\n(1) Earnings-22: A Practical Benchmark for Accents in the Wild. https://arxiv.org/abs/2203.15591.\r\n(2) Earnings-22: A Practical Benchmark for Accents in the Wild. https://deepai.org/publication/earnings-22-a-practical-benchmark-for-accents-in-the-wild.\r\n(3) arXiv:2203.15591v1 [cs.CL] 29 Mar 2022. https://arxiv.org/pdf/2203.15591.pdf.\r\n(4) undefined. https://doi.org/10.48550/arXiv.2203.15591.","description_withheld":null,"homepage":"","introduced_date":"2022-03-29","introduced_date_note":null,"introduced_by":{"paper":"/paper/earnings-22-a-practical-benchmark-for-accents","title":"Earnings-22: A Practical Benchmark for Accents in the Wild","first_author":"Miguel Del Rio","url":null},"license":null,"modalities":[],"tasks":[{"name":"Automatic Speech Recognition","url":"/task/automatic-speech-recognition-2","datasets_with_task":"/datasets/task/automatic-speech-recognition-2"}],"languages":[],"variants":["Earnings-22"],"data_loaders":[],"num_papers_in_archive":10,"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."}