{"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/how-much-context-does-my-attention-based-asr","title":"How Much Context Does My Attention-Based ASR System Need?","arxiv_id":"2310.15672","date":"2023-10-24","proceeding":null,"authors":["Robert Flynn","Anton Ragni"],"abstract":"For the task of speech recognition, the use of more than 30 seconds of acoustic context during training is uncommon and under-investigated in literature. In this work, we conduct an empirical study on the effect of scaling the sequence length used to train/evaluate (dense-attention-based) acoustic models on speech recognition performance. For these experiments, a dataset of roughly 100,000 pseudo-labelled Spotify podcasts is used, with context lengths of 5 seconds to 1 hour being explored. Zero-shot evaluations are presented on the long-format datasets: Earnings-22, Tedlium and Rev16. Results demonstrate a benefit from training with up to 21.8 minutes of acoustic context, showing up to a 14.5\\% relative improvement from a baseline trained with 10 seconds of context. We find that the model's width/depth, positional encoding scheme and number of attention heads impact its ability to use longer contexts.","url_abs":"https://arxiv.org/abs/2310.15672v2","url_pdf":"https://arxiv.org/pdf/2310.15672v2.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":"how-much-context-does-my-attention-based-asr","repo_url":"https://github.com/robflynnyh/long-context-asr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"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":null,"atlas_url":"https://app.syntology.ai/?focus=2310.15672","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}