{"ID":5937188,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-09T08:57:31.292890551Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04826","arxiv_id":"2607.04826","title":"Ranking the Impact of Contextual Specialization in Neural Speech Enhancement","abstract":"We systematically investigate neural speech enhancement systems, ranging from very small ($\\sim$10\\,k parameters) to medium-large ($\\sim$2-5\\,M parameters), which specialize to acoustic conditions using contextual information such as speaker identity, noise type, speaker gender, spoken language, and SNR. By fine-tuning generalist models on specific data subsets, we find that specializing to a speaker's identity consistently yields the largest gains in estimated speech intelligibility and quality. In contrast, specializing to SNR, noise type, or gender offers only marginal benefits. Crucially, we show that a small model specialized to both a specific speaker and a specific noise type can match or exceed the performance of a generalist model ten times its size. Further, cross-lingual tests reveal that models specialized to a target language outperform multilingual generalists, suggesting that language is a salient feature for specialization. These findings highlight the potential of small, adaptive models for resource-constrained applications like hearing aids, which specialize on-the-fly to contextual information.","short_abstract":"We systematically investigate neural speech enhancement systems, ranging from very small ($\\sim$10\\,k parameters) to medium-large ($\\sim$2-5\\,M parameters), which specialize to acoustic conditions using contextual information such as speaker identity, noise type, speaker gender, spoken language, and SNR. By fine-tuning...","url_abs":"https://arxiv.org/abs/2607.04826","url_pdf":"https://arxiv.org/pdf/2607.04826v1","authors":"[\"Peter Leer\",\"Svend Feldt\",\"Zheng-Hua Tan\",\"Jan Østergaard\",\"Jesper Jensen\"]","published":"2026-07-06T08:59:07Z","proceeding":"eess.AS","tasks":"[\"eess.AS\",\"cs.SD\"]","methods":"[]","has_code":false}