This task is a variant of the Target Sound Extraction task, with the constraint of causal streaming inference. Aiming for an algorithmic latency of less than 20 ms, at each time step, streaming audio models operate on an input audio chunk of length less than 20 ms. The causal constraint means that the model only has the knowledge of past chunks and no future chunks.
데이터셋
출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.
A synthetic sound mixture specification dataset for the Target Sound Extraction (TSE) task. Dataset samples consist of a .jams file specifying the mixture components, and a metadata file with target labels. Mixtures are 6 seconds long and contain 3-5 unique foreground sounds over a 6 second long background sound. Each sample is provided with 3 target labels, and sounds corresponding to all target labels are guaranteed to be present in the mixture. FSDKaggle2018 is used as the source for foreground sounds and TAU Urban Acoustic Scenes 2019 is used as the source for background sounds. ##### Split Train: 50K Val: 5K Test: 10K