Sound events in daily life carry rich information about the objective wo...
Most existing deep learning-based acoustic scene classification (ASC)
ap...
Audio tagging aims to assign predefined tags to audio clips to indicate ...
Previous works on scene classification are mainly based on audio or visu...
Models based on diverse attention mechanisms have recently shined in tas...
In real life, acoustic scenes and audio events are naturally correlated....
Sequential audio event tagging can provide not only the type information...
Many previous audio-visual voice-related works focus on speech, ignoring...
Detecting anchor's voice in live musical streams is an important
preproc...
Detecting singing-voice in polyphonic instrumental music is critical to ...
Sound event detection (SED) methods typically rely on either strongly
la...
Audio tagging aims to detect the types of sound events occurring in an a...
Audio tagging aims to predict one or several labels in an audio clip. Ma...