{"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/a-streaming-multi-channel-end-to-end-speech","title":"CUSIDE-array: A Streaming Multi-Channel End-to-End Speech Recognition System with Realistic Evaluations","arxiv_id":"2407.09807","date":"2024-07-13","proceeding":null,"authors":["Xiangzhu Kong","Tianqi Ning","Hao Huang","Zhijian Ou"],"abstract":"Recently multi-channel end-to-end (ME2E) ASR systems have emerged. While streaming single-channel end-to-end ASR has been extensively studied, streaming ME2E ASR is limited in exploration. Additionally, recent studies call attention to the gap between in-distribution (ID) and out-of-distribution (OOD) tests and doing realistic evaluations. This paper focuses on two research problems: realizing streaming ME2E ASR and improving OOD generalization. We propose the CUSIDE-array method, which integrates the recent CUSIDE methodology (Chunking, Simulating Future Context and Decoding) into the neural beamformer approach of ME2E ASR. It enables streaming processing of both front-end and back-end with a total latency of 402ms. The CUSIDE-array ME2E models are shown to achieve superior streaming results in both ID and OOD tests. Realistic evaluations confirm the advantage of CUSIDE-array in its capability to consume single-channel data to improve OOD generalization via back-end pre-training and ME2E fine-tuning.","url_abs":"https://arxiv.org/abs/2407.09807v2","url_pdf":"https://arxiv.org/pdf/2407.09807v2.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":"a-streaming-multi-channel-end-to-end-speech","repo_url":"https://github.com/thu-spmi/cat","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"chunking","task_name":"Chunking"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}