inria-00544199, version 1
First stereo audio source separation evaluation campaign: data, algorithms and results
Emmanuel Vincent
a, 1Hiroshi Sawada 2Pau Bofill 3Shoji Makino 2Justinian Rosca 4
7th Int. Conf. on Independent Component Analysis and Blind Source Separation (ICA) (2007) 552--559
Abstract: This article provides an overview of the first stereo audio source separation evaluation campaign, organized by the authors. Fifteen underdetermined stereo source separation algorithms have been applied to various audio data, including instantaneous, convolutive and real mixtures of speech or music sources. The data and the algorithms are presented and the estimated source signals are compared to reference signals using several objective performance criteria.
- a – INRIA
- 1: METISS (INRIA - IRISA)
- CNRS : UMR6074 – INRIA – INSA Rennes – Université de Rennes 1
- 2: NTT Communication Science Laboratories
- NTT Corporation
- 3: Department of Computer Architecture (DAC-UPC)
- Universitat Politécnica de Catalunya
- 4: Siemens Corporate Research
- Siemens
- Domain : Computer Science/Signal and Image Processing
Engineering Sciences/Signal and Image processing
- inria-00544199, version 1
- http://hal.inria.fr/inria-00544199
- oai:hal.inria.fr:inria-00544199
- From: Emmanuel Vincent
- Submitted on: Tuesday, 7 December 2010 14:51:35
- Updated on: Thursday, 9 December 2010 10:53:34
Associated documents
Export