Calum Heggan, S. Budgett, Timothy M. Hospedales, Mehrdad Yaghoobi
{"title":"MetaAudio:少量音频分类基准","authors":"Calum Heggan, S. Budgett, Timothy M. Hospedales, Mehrdad Yaghoobi","doi":"10.48550/arXiv.2204.02121","DOIUrl":null,"url":null,"abstract":"Currently available benchmarks for few-shot learning (machine learning with few training examples) are limited in the domains they cover, primarily focusing on image classification. This work aims to alleviate this reliance on image-based benchmarks by offering the first comprehensive, public and fully reproducible audio based alternative, covering a variety of sound domains and experimental settings. We compare the few-shot classification performance of a variety of techniques on seven audio datasets (spanning environmental sounds to human-speech). Extending this, we carry out in-depth analyses of joint training (where all datasets are used during training) and cross-dataset adaptation protocols, establishing the possibility of a generalised audio few-shot classification algorithm. Our experimentation shows gradient-based meta-learning methods such as MAML and Meta-Curvature consistently outperform both metric and baseline methods. We also demonstrate that the joint training routine helps overall generalisation for the environmental sound databases included, as well as being a somewhat-effective method of tackling the cross-dataset/domain setting.","PeriodicalId":93416,"journal":{"name":"Artificial neural networks, ICANN : international conference ... proceedings. International Conference on Artificial Neural Networks (European Neural Network Society)","volume":"41 1","pages":"219-230"},"PeriodicalIF":0.0000,"publicationDate":"2022-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":"{\"title\":\"MetaAudio: A Few-Shot Audio Classification Benchmark\",\"authors\":\"Calum Heggan, S. Budgett, Timothy M. Hospedales, Mehrdad Yaghoobi\",\"doi\":\"10.48550/arXiv.2204.02121\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Currently available benchmarks for few-shot learning (machine learning with few training examples) are limited in the domains they cover, primarily focusing on image classification. This work aims to alleviate this reliance on image-based benchmarks by offering the first comprehensive, public and fully reproducible audio based alternative, covering a variety of sound domains and experimental settings. We compare the few-shot classification performance of a variety of techniques on seven audio datasets (spanning environmental sounds to human-speech). Extending this, we carry out in-depth analyses of joint training (where all datasets are used during training) and cross-dataset adaptation protocols, establishing the possibility of a generalised audio few-shot classification algorithm. Our experimentation shows gradient-based meta-learning methods such as MAML and Meta-Curvature consistently outperform both metric and baseline methods. We also demonstrate that the joint training routine helps overall generalisation for the environmental sound databases included, as well as being a somewhat-effective method of tackling the cross-dataset/domain setting.\",\"PeriodicalId\":93416,\"journal\":{\"name\":\"Artificial neural networks, ICANN : international conference ... proceedings. International Conference on Artificial Neural Networks (European Neural Network Society)\",\"volume\":\"41 1\",\"pages\":\"219-230\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-04-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"11\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Artificial neural networks, ICANN : international conference ... proceedings. International Conference on Artificial Neural Networks (European Neural Network Society)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2204.02121\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Artificial neural networks, ICANN : international conference ... proceedings. International Conference on Artificial Neural Networks (European Neural Network Society)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2204.02121","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
MetaAudio: A Few-Shot Audio Classification Benchmark
Currently available benchmarks for few-shot learning (machine learning with few training examples) are limited in the domains they cover, primarily focusing on image classification. This work aims to alleviate this reliance on image-based benchmarks by offering the first comprehensive, public and fully reproducible audio based alternative, covering a variety of sound domains and experimental settings. We compare the few-shot classification performance of a variety of techniques on seven audio datasets (spanning environmental sounds to human-speech). Extending this, we carry out in-depth analyses of joint training (where all datasets are used during training) and cross-dataset adaptation protocols, establishing the possibility of a generalised audio few-shot classification algorithm. Our experimentation shows gradient-based meta-learning methods such as MAML and Meta-Curvature consistently outperform both metric and baseline methods. We also demonstrate that the joint training routine helps overall generalisation for the environmental sound databases included, as well as being a somewhat-effective method of tackling the cross-dataset/domain setting.