{"ID":2865025,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.21867","arxiv_id":"2509.21867","title":"FastEnhancer: Speed-Optimized Streaming Neural Speech Enhancement","abstract":"Streaming speech enhancement is a crucial task for real-time applications such as online meetings, smart home appliances, and hearing aids. Deep neural network-based approaches achieve exceptional performance while demanding substantial computational resources. Although recent neural speech enhancement models have succeeded in reducing the number of parameters and multiply-accumulate operations, their sophisticated architectures often introduce significant processing latency on common hardware. In this work, we propose FastEnhancer, a streaming neural speech enhancement model designed explicitly to minimize real-world latency. It features a simple encoder-decoder structure with efficient RNNFormer blocks. Evaluations on various objective metrics show that FastEnhancer achieves state-of-the-art speech quality and intelligibility while simultaneously demonstrating the fastest processing speed on a single CPU thread. Code and pre-trained weights are publicly available (https://github.com/aask1357/fastenhancer).","short_abstract":"Streaming speech enhancement is a crucial task for real-time applications such as online meetings, smart home appliances, and hearing aids. Deep neural network-based approaches achieve exceptional performance while demanding substantial computational resources. Although recent neural speech enhancement models have succ...","url_abs":"https://arxiv.org/abs/2509.21867","url_pdf":"https://arxiv.org/pdf/2509.21867v1","authors":"[\"Sunghwan Ahn\",\"Jinmo Han\",\"Beom Jun Woo\",\"Nam Soo Kim\"]","published":"2025-09-26T04:45:04Z","proceeding":"eess.AS","tasks":"[\"eess.AS\"]","methods":"[]","has_code":false,"code_links":[{"ID":609232,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2865025,"paper_url":"https://arxiv.org/abs/2509.21867","paper_title":"FastEnhancer: Speed-Optimized Streaming Neural Speech Enhancement","repo_url":"https://github.com/aask1357/fastenhancer","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}