Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

A supervised learning approach to ambience extraction from mono recordings for blind upmixing

 
: Uhle, T.; Paul, C.

:
Fulltext (PDF; )

Aalto University, School of Science and Technology -TKK-, Espoo:
11th International Conference on Digital Audio Effects, DAFx-08. Proceedings : September 1-4, 2008, Espoo, Finland
Espoo, 2008
ISBN: 978-951-22-9517-3
pp.137-144
International Conference on Digital Audio Effects (DAFX) <11, 2008, Espoo>
English
Conference Paper, Electronic Publication
Fraunhofer IIS ()

Abstract
A supervised learning approach to ambience extraction from onechannel audio signals is presented. The extracted ambient signals are applied for the blind upmixing of musical audio recordings to surround sound formats. The input signal is processed by means of short-term spectral attenuation. The spectral weights are computed using a low-level feature extraction process and a neural network regression method. The multi-channel audio signal is generated by feeding the computed ambient signal into the rear channels of a surround sound system.

: http://publica.fraunhofer.de/documents/N-118012.html