{"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/efficient-speech-enhancement-via-embeddings","title":"Efficient Speech Enhancement via Embeddings from Pre-trained Generative Audioencoders","arxiv_id":"2506.11514","date":"2025-06-13","proceeding":null,"authors":["Xingwei Sun","Heinrich Dinkel","Yadong Niu","Linzhang Wang","Junbo Zhang","Jian Luan"],"abstract":"Recent research has delved into speech enhancement (SE) approaches that leverage audio embeddings from pre-trained models, diverging from time-frequency masking or signal prediction techniques. This paper introduces an efficient and extensible SE method. Our approach involves initially extracting audio embeddings from noisy speech using a pre-trained audioencoder, which are then denoised by a compact encoder network. Subsequently, a vocoder synthesizes the clean speech from denoised embeddings. An ablation study substantiates the parameter efficiency of the denoise encoder with a pre-trained audioencoder and vocoder. Experimental results on both speech enhancement and speaker fidelity demonstrate that our generative audioencoder-based SE system outperforms models utilizing discriminative audioencoders. Furthermore, subjective listening tests validate that our proposed system surpasses an existing state-of-the-art SE model in terms of perceptual quality.","url_abs":"https://arxiv.org/abs/2506.11514v1","url_pdf":"https://arxiv.org/pdf/2506.11514v1.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":"efficient-speech-enhancement-via-embeddings","repo_url":"https://github.com/xiaomi-research/dasheng-denoiser","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"speech-enhancement","task_name":"Speech Enhancement"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}