AUDIO SIGNAL CLASSIFICATION
Hariharan Subramanian, Preeti Rao, Debaditya Roy · 2004
Audio signal classification system analyzes the input audio signal and creates a label that describes the signal at the output. These are used to characterize both music and speech signals. The categorization can be done on the basis of pitch, music content, music tempo and rhythm. The signal classifier analyzes the content of the audio format thereby extracting information about the content from the audio data. This is also called audio content analysis, which extends to retrieval of content information from signals. In this report the implementation of the audio signal classification is presented. A number of features such as pitch, timbral, rhythmic features have been discussed with reference to their ability to distinguish the different audio formats. The selection of the important features as well as the common techniques used for classification has been explained. Finally an approach called the confusion matrix has been studied in order to evaluate performance of the classification system.