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:
Unlike many existing corpora, Earnings-22 focuses on speech in the wild, representing real-world scenarios where accents and environmental conditions vary.
Purpose and Significance:
Researchers and industry professionals can use Earnings-22 to evaluate and improve ASR models' robustness.
Comparison and Insights:
Individual Word Error Rate (IWER) analysis highlights how certain accents impact model performance more than others.
Academic and Industrial Impact:
Source: Conversation with Bing, 3/16/2024 (1) Earnings-22: A Practical Benchmark for Accents in the Wild. https://arxiv.org/abs/2203.15591. (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. (3) arXiv:2203.15591v1 [cs.CL] 29 Mar 2022. https://arxiv.org/pdf/2203.15591.pdf. (4) undefined. https://doi.org/10.48550/arXiv.2203.15591.
Paper | Code | Results | Date | Stars |
---|