Skip to Main content Skip to Navigation
Conference papers

Quantization-aware Parameter Estimation for Audio Upmixing

Christian Rohlfing 1 Antoine Liutkus 2 Julian Becker 1
2 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : Upmixing consists in extracting audio objects out of their downmix, given some parameters computed beforehand at a coding stage. It is an important task in audio processing with many applications in the entertainment industry. One particularly successful approach for this purpose is to compress the audio objects through nonnegative matrix factorization (NMF) parameters at the coder, to be used for separating the downmix at the decoder. In this paper, we focus on such NMF methods for audio compression, which operate at very low parameter bitrates. In existing methods, parameter estimation and quantization are conducted independently. Here, we propose two extensions: first, we jointly estimate and quantize the parameters at the coder to ensure good reconstruction at the decoder. Second, we propose a parameter refinement method operated at the decoder, that benefits from priors induced by quantization to yield better performance. We show that our contributions outperform existing baseline methods.
Document type :
Conference papers
Complete list of metadata

Cited literature [35 references]  Display  Hide  Download
Contributor : Antoine Liutkus Connect in order to contact the contributor
Submitted on : Friday, April 28, 2017 - 12:47:23 PM
Last modification on : Saturday, October 16, 2021 - 11:26:09 AM
Long-term archiving on: : Saturday, July 29, 2017 - 1:22:11 PM


Files produced by the author(s)


  • HAL Id : hal-01515955, version 1



Christian Rohlfing, Antoine Liutkus, Julian Becker. Quantization-aware Parameter Estimation for Audio Upmixing. 42nd International Conference on Acoustics, Speech and Signal Processing (ICASSP), Mar 2017, New Orleans, United States. ⟨hal-01515955⟩



Record views


Files downloads