Single-Label Target Sound Extraction

Single-Label Target Sound Extraction is the task of extracting sounds of a specific category from an audio mixture. This task aims to separate the target sound by inputting sound category labels, such as strings, integers, or one-hot encodings, from mixed audio containing background noise, to achieve high-precision sound recognition and processing. Its application value lies in enhancing the clarity and intelligibility of audio signals, widely applicable in areas such as speech enhancement, music production, and environmental sound monitoring.