no code implementations • 5 Jun 2022 • Jouni Paulus, Matteo Torcoli
A geometrically-motivated method for primary-ambient decomposition is proposed and evaluated in an up-mixing application.
no code implementations • 5 Jun 2022 • Jouni Paulus, Matteo Torcoli
The models are trained with audio sampled at 8 kHz.
no code implementations • 17 Dec 2021 • Matteo Torcoli, Christian Simon, Jouni Paulus, Davide Straninger, Alfred Riedel, Volker Koch, Stefan Wits, Daniela Rieger, Harald Fuchs, Christian Uhle, Stefan Meltzer, Adrian Murtaza
To address this, Fraunhofer IIS has developed a deep-learning solution called Dialog+, capable of enabling speech level personalization also for content with only the final audio tracks available.
no code implementations • 22 Jul 2021 • Christian Uhle, Matteo Torcoli, Jouni Paulus
Speech enhancement attenuates interfering sounds in speech signals but may introduce artifacts that perceivably deteriorate the output signal.
no code implementations • 21 Jul 2021 • Matteo Torcoli, Jouni Paulus, Thorsten Kastner, Christian Uhle
The 2f-model requires the reference target source as an input, but this is not available in many applications.
no code implementations • 16 Jun 2021 • Martin Strauss, Jouni Paulus, Matteo Torcoli, Bernd Edler
The music separation models are selected as they share the number of channels (2) and sampling rate (44. 1 kHz or higher) with the considered broadcast content, and vocals separation in music is considered as a parallel for dialog separation in the target application domain.