Target sound detection (TSD) aims to detect the target sound from mixture audio given the reference information. Previous works have shown that TSD models can be trained on fully-annotated (frame-level label) or weakly-annotated (clip-level label) data. However, there are some clear evidences show that the performance of the model trained on weakly-annotated data is worse than that trained on fully-annotated data. To fill this gap, we provide a mixed supervision perspective, in which learning novel categories (target domain) using weak annotations with the help of full annotations of existing base categories (source domain). To realize this, a mixed supervised learning framework is proposed, which contains two mutually-helping student models (\textit{f\_student} and \textit{w\_student}) that learn from fully-annotated and weakly-annotated data, respectively. The motivation is that \textit{f\_student} learned from fully-annotated data has a better ability to capture detailed information than \textit{w\_student}. Thus, we first let \textit{f\_student} guide \textit{w\_student} to learn the ability to capture details, so \textit{w\_student} can perform better in the target domain. Then we let \textit{w\_student} guide \textit{f\_student} to fine-tune on the target domain. The process can be repeated several times so that the two students perform very well in the target domain. To evaluate our method, we built three TSD datasets based on UrbanSound and Audioset. Experimental results show that our methods offer about 8\% improvement in event-based F-score as compared with a recent baseline.

翻译：目标声音检测 (TSD) 的目的是根据参考信息从混合物音频中检测目标声音。 先前的著作显示, TSD 模型可以在完全附加说明( 框架级标签) 或微弱附加说明( 剪贴标签) 数据上接受培训。 但是, 有一些清晰的证据表明, 以微弱附加说明数据 培训的模型的性能比以充分附加说明数据 培训的差。 为了填补这一空白, 我们提供了一种混合的监督视角, 借助现有基级类别( 源域) 的全面说明, 学习新的说明( 目标域) 。 为了实现这一点, 提议了一个混合的监管学习框架, 包含两个相互帮助的学生模型 (\ textit{ f\\ student} 和\ textitleitle{ w\ student} ), 分别从全部附加说明和微弱附加说明的数据中学习。 动机是, 从完全注{ f\\ studle tual} 数据中学习的详细信息比 text { w\\\\ text a littlegn rode rod rode rode} rode rode rode rode rode rous be swegs the rodud rous rost rodud rous rodud rodustelus legs