Auditory-inspired sparse representation of audio signals

This article deals with the generation of auditory-inspired spectro-temporal features aimed at audio coding. To do so, we first generate sparse audio representations we call spikegrams, using projections on gammatone/gammachirp kernels that generate neural spikes. Unlike Fourier-based representations, these representations are powerful at identifying auditory events, such as onsets, offsets,

• Type: Journal
• Year: 2011
• Where: SPEECH
• Authors: Ramin Pichevar, Hossein Najaf-Zadeh, Louis Thibault, Hassan Lahdili
• Keywords: Auditory-inspired Spectro-temporal Features, Security Privacy, Sparse Audio Representations, SPEECH 2011, first Generate