{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/rethinking-evaluation-in-asr-are-our-models","title":"Rethinking Evaluation in ASR: Are Our Models Robust Enough?","arxiv_id":"2010.11745","date":"2020-10-22","proceeding":null,"authors":["Tatiana Likhomanenko","Qiantong Xu","Vineel Pratap","Paden Tomasello","Jacob Kahn","Gilad Avidov","Ronan Collobert","Gabriel Synnaeve"],"abstract":"Is pushing numbers on a single benchmark valuable in automatic speech recognition? Research results in acoustic modeling are typically evaluated based on performance on a single dataset. While the research community has coalesced around various benchmarks, we set out to understand generalization performance in acoustic modeling across datasets - in particular, if models trained on a single dataset transfer to other (possibly out-of-domain) datasets. We show that, in general, reverberative and additive noise augmentation improves generalization performance across domains. Further, we demonstrate that when a large enough set of benchmarks is used, average word error rate (WER) performance over them provides a good proxy for performance on real-world noisy data. Finally, we show that training a single acoustic model on the most widely-used datasets - combined - reaches competitive performance on both research and real-world benchmarks.","url_abs":"https://arxiv.org/abs/2010.11745v3","url_pdf":"https://arxiv.org/pdf/2010.11745v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"rethinking-evaluation-in-asr-are-our-models","repo_url":"https://github.com/facebookresearch/wav2letter/tree/master/recipes/rasr","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2010.11745","atlas_url":"https://app.syntology.ai/?focus=2010.11745","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}