Detection and Classification of Acoustic Scenes and Events II

Error message

The specified file temporary://fileQOMUt6 could not be copied, because the destination directory is not properly configured. This may be caused by a problem with file or directory permissions. More information is available in the system log.

The specified file temporary://filehMKWJQ could not be copied, because the destination directory is not properly configured. This may be caused by a problem with file or directory permissions. More information is available in the system log.

The specified file temporary://filesuN2HH could not be copied, because the destination directory is not properly configured. This may be caused by a problem with file or directory permissions. More information is available in the system log.

The specified file temporary://file76BhQe could not be copied, because the destination directory is not properly configured. This may be caused by a problem with file or directory permissions. More information is available in the system log.

The specified file temporary://fileWVus53 could not be copied, because the destination directory is not properly configured. This may be caused by a problem with file or directory permissions. More information is available in the system log.

The specified file temporary://file9sG2BD could not be copied, because the destination directory is not properly configured. This may be caused by a problem with file or directory permissions. More information is available in the system log.

The specified file temporary://filegPT9LG could not be copied, because the destination directory is not properly configured. This may be caused by a problem with file or directory permissions. More information is available in the system log.

The specified file temporary://fileL5iAt5 could not be copied, because the destination directory is not properly configured. This may be caused by a problem with file or directory permissions. More information is available in the system log.

ARTIFICIALLY SYNTHESISING DATA FOR AUDIO CLASSIFICATION AND SEGMENTATION TO IMPROVE SPEECH AND MUSIC DETECTION IN RADIO BROADCAST

Segmenting audio into homogeneous sections such as music and speech helps us understand the content of audio. It is useful as a pre-processing step to index, store, and modify audio recordings, radio broadcasts and TV programmes. Deep learning models for segmentation are generally trained on copyrighted material, which cannot be shared. Annotating these datasets is time-consuming and expensive and therefore, it significantly slows down research progress. In this study, we present a novel procedure that artificially synthesises data that resembles radio signals.

Venkatesh Slides and poster.pdf

Venkatesh Slides and poster.pdf (466)

Categories:: Content-Based Audio Processing
Audio Processing Systems

22 Views

ZERO-SHOT AUDIO CLASSIFICATION WITH FACTORED LINEAR AND NONLINEAR ACOUSTIC-SEMANTIC PROJECTIONS

In this paper, we study zero-shot learning in audio classification through factored linear and nonlinear acoustic-semantic projections between audio instances and sound classes. Zero-shot learning in audio classification refers to classification problems that aim at recognizing audio instances of sound classes, which have no available training data but only semantic side information. In this paper, we address zero-shot learning by employing factored linear and nonlinear acoustic-semantic projections.