{"title":"研究生成式语音增强的训练目标","authors":"Julius Richter, Danilo de Oliveira, Timo Gerkmann","doi":"arxiv-2409.10753","DOIUrl":null,"url":null,"abstract":"Generative speech enhancement has recently shown promising advancements in\nimproving speech quality in noisy environments. Multiple diffusion-based\nframeworks exist, each employing distinct training objectives and learning\ntechniques. This paper aims at explaining the differences between these\nframeworks by focusing our investigation on score-based generative models and\nSchr\\\"odinger bridge. We conduct a series of comprehensive experiments to\ncompare their performance and highlight differing training behaviors.\nFurthermore, we propose a novel perceptual loss function tailored for the\nSchr\\\"odinger bridge framework, demonstrating enhanced performance and improved\nperceptual quality of the enhanced speech signals. All experimental code and\npre-trained models are publicly available to facilitate further research and\ndevelopment in this.","PeriodicalId":501284,"journal":{"name":"arXiv - EE - Audio and Speech Processing","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Investigating Training Objectives for Generative Speech Enhancement\",\"authors\":\"Julius Richter, Danilo de Oliveira, Timo Gerkmann\",\"doi\":\"arxiv-2409.10753\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Generative speech enhancement has recently shown promising advancements in\\nimproving speech quality in noisy environments. Multiple diffusion-based\\nframeworks exist, each employing distinct training objectives and learning\\ntechniques. This paper aims at explaining the differences between these\\nframeworks by focusing our investigation on score-based generative models and\\nSchr\\\\\\\"odinger bridge. We conduct a series of comprehensive experiments to\\ncompare their performance and highlight differing training behaviors.\\nFurthermore, we propose a novel perceptual loss function tailored for the\\nSchr\\\\\\\"odinger bridge framework, demonstrating enhanced performance and improved\\nperceptual quality of the enhanced speech signals. All experimental code and\\npre-trained models are publicly available to facilitate further research and\\ndevelopment in this.\",\"PeriodicalId\":501284,\"journal\":{\"name\":\"arXiv - EE - Audio and Speech Processing\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - EE - Audio and Speech Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.10753\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - EE - Audio and Speech Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.10753","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Investigating Training Objectives for Generative Speech Enhancement
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 at explaining the differences between these
frameworks by focusing our investigation on score-based generative models and
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.