Sound Event Detection

Sound Event Detection (SED) refers to the task of identifying sound events and their corresponding onset and offset times in audio recordings. In real-world scenarios, sound events often do not occur in isolation but overlap with each other, and recognizing these overlapping sound events is known as polyphonic SED. This task aims to enhance the understanding and analysis capabilities of complex soundscapes, which has significant application value in areas such as environmental monitoring, intelligent security, and human-computer interaction.