{"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/investigating-training-objectives-for","title":"Investigating Training Objectives for Generative Speech Enhancement","arxiv_id":"2409.10753","date":"2024-09-16","proceeding":null,"authors":["Julius Richter","Danilo de Oliveira","Timo Gerkmann"],"abstract":"Generative speech enhancement has recently shown promising advancements in improving speech quality in noisy environments. Multiple diffusion-based frameworks exist, each employing distinct training objectives and learning techniques. This paper aims to explain the differences between these frameworks by focusing our investigation on score-based generative models and the Schr\\\"odinger bridge. We conduct a series of comprehensive experiments to compare their performance and highlight differing training behaviors. Furthermore, we propose a novel perceptual loss function tailored for the Schr\\\"odinger bridge framework, demonstrating enhanced performance and improved perceptual quality of the enhanced speech signals. All experimental code and pre-trained models are publicly available to facilitate further research and development in this domain.","url_abs":"https://arxiv.org/abs/2409.10753v2","url_pdf":"https://arxiv.org/pdf/2409.10753v2.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":"investigating-training-objectives-for","repo_url":"https://github.com/sp-uhh/sgmse","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"speech-enhancement","task_name":"Speech Enhancement"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-enhancement-on-ears-wham","task":"Speech Enhancement","dataset":"EARS-WHAM","model":"Schrödinger Bridge (PESQ loss)","rank_in_archive_order":1,"of":6,"metrics":{"DNSMOS":"3.72","ESTOI":"0.73","PESQ-WB":"3.09","POLQA":"3.71","SI-SDR":"16.29","SIGMOS":"3.18"},"uses_additional_data":false},{"leaderboard":"/sota/speech-enhancement-on-demand","task":"Speech Enhancement","dataset":"VoiceBank + DEMAND","model":"Schrödinger bridge (PESQ loss)","rank_in_archive_order":4,"of":42,"metrics":{"PESQ (wb)":"3.70"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.10753","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}