Informed Source Separation from compressed mixtures using spatial wiener filter and quantization noise estimation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

Informed Source Separation from compressed mixtures using spatial wiener filter and quantization noise estimation

Résumé

In a previous work, we proposed an Informed Source Separation sys- tem based on Wiener filtering for active listening of music from un- compressed (16-bit PCM) multichannel mix signals. In the present work, the system is improved to work with (MPEG-2 AAC) com- pressed mix signals: quantization noise is estimated from the AAC bitstream at the decoder and explicitly taken into account in the source separation process. Also a direct MDCT-to-STFT transform is used to optimize the computational efficiency of the process in the STFT domain from AAC-decoded MDCT coefficients.
Fichier principal
Vignette du fichier
SZ_LG_AL_icassp-2013.pdf (390.91 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00940328 , version 1 (31-01-2014)

Identifiants

Citer

Shuhua Zhang, Laurent Girin, Antoine Liutkus. Informed Source Separation from compressed mixtures using spatial wiener filter and quantization noise estimation. ICASSP 2013 - 38th IEEE International Conference on Acoustics, Speech and Signal Processing, May 2013, Vancouver, Canada. pp.61-65, ⟨10.1109/ICASSP.2013.6637609⟩. ⟨hal-00940328⟩
296 Consultations
167 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More