Earnings-22

· 논문 10편

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: 1. Corpus Description: - Earnings-22 consists of 125 audio files totaling 119 hours of English-language earnings calls. These calls were gathered from global companies. - Unlike many existing corpora, Earnings-22 focuses on speech in the wild, representing real-world scenarios where accents and environmental conditions vary. 2. Purpose and Significance: - ASR systems have achieved impressive performance on common corpora but often struggle with real-world speech. - Earnings-22 aims to bridge this gap by providing a free-to-use benchmark that includes accented audio. - Researchers and industry professionals can use Earnings-22 to evaluate and improve ASR models' robustness. 3. Comparison and Insights: - The benchmark involves four commercial ASR models, and their performance is compared. - By considering the country of origin, the study reveals variations in ASR accuracy. - Individual Word Error Rate (IWER) analysis highlights how certain accents impact model performance more than others. 4. Academic and Industrial Impact: - Earnings-22 serves as a valuable resource for both academic research and industrial applications. - It provides a realistic dataset for evaluating ASR systems' effectiveness in handling diverse accents. 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.