Coding-Based Informed Source Separation: Nonnegative Tensor Factorization Approach
Reads0
Chats0
TLDR
Coding-based ISS is introduced and Nonnegative Tensor Factorization is introduced as a very efficient model for CISS and report rate-distortion results that strongly outperform the state of the art.Abstract:
Informed source separation (ISS) aims at reliably recovering sources from a mixture. To this purpose, it relies on the assumption that the original sources are available during an encoding stage. Given both sources and mixture, a side-information may be computed and transmitted along with the mixture, whereas the original sources are not available any longer. During a decoding stage, both mixture and side-information are processed to recover the sources. ISS is motivated by a number of specific applications including active listening and remixing of music, karaoke, audio gaming, etc. Most ISS techniques proposed so far rely on a source separation strategy and cannot achieve better results than oracle estimators. In this study, we introduce Coding-based ISS (CISS) and draw the connection between ISS and source coding. CISS amounts to encode the sources using not only a model as in source coding but also the observation of the mixture. This strategy has several advantages over conventional ISS methods. First, it can reach any quality, provided sufficient bandwidth is available as in source coding. Second, it makes use of the mixture in order to reduce the bitrate required to transmit the sources, as in classical ISS. Furthermore, we introduce Nonnegative Tensor Factorization as a very efficient model for CISS and report rate-distortion results that strongly outperform the state of the art.read more
Citations
More filters
Proceedings ArticleDOI
Scalable audio separation with light Kernel Additive Modelling
TL;DR: It is shown how KAM can be combined with a fast compression algorithm of its parameters to address the scalability issue, thus enabling its use on small platforms or mobile devices.
Proceedings ArticleDOI
Student's T nonnegative matrix factorization and positive semidefinite tensor factorization for single-channel audio source separation
TL;DR: T-NMF is proposed as a unified extension of Gaussian NMF and Cauchy NMF for source separation of single-channel audio signals and the corresponding variant of positive semidefinite tensor factorization based on multivariate complex t distributions (t-PSDTF) is proposed.
Journal ArticleDOI
Model-Based STFT Phase Recovery for Audio Source Separation
TL;DR: A novel iterative source separation procedure is proposed that outperforms the state-of-the-art consistent Wiener filter in minimizing the mixing error by means of the auxiliary function method.
Proceedings ArticleDOI
Audio declipping via nonnegative matrix factorization
TL;DR: This paper proposes a new algorithm that makes use of a low rank NMF model to perform audio inpainting and declipping and introduces a novel way to enforce additional constraints on the signal magnitude in order to improve the performance in declipping applications.
Proceedings ArticleDOI
Student's t multichannel nonnegative matrix factorization for blind source separation
TL;DR: A robust generalization of multichannel nonnegative matrix factorization (MNMF) for blind source separation of mixture audio signals recorded by a microphone array is presented, based on the complex Student's t likelihood.
References
More filters
Journal ArticleDOI
Performance measurement in blind audio source separation
TL;DR: This paper considers four different sets of allowed distortions in blind audio source separation algorithms, from time-invariant gains to time-varying filters, and derives a global performance measure using an energy ratio, plus a separate performance measure for each error term.
Journal ArticleDOI
Context-based adaptive binary arithmetic coding in the H.264/AVC video compression standard
TL;DR: Context-based adaptive binary arithmetic coding (CABAC) as a normative part of the new ITU-T/ISO/IEC standard H.264/AVC for video compression is presented, and significantly outperforms the baseline entropy coding method of H.265.
Book
Handbook of Blind Source Separation: Independent Component Analysis and Applications
Pierre Comon,Christian Jutten +1 more
TL;DR: This handbook provides the definitive reference on Blind Source Separation, giving a broad and comprehensive description of all the core principles and methods, numerical algorithms and major applications in the fields of telecommunications, biomedical engineering and audio, acoustic and speech processing.
Journal ArticleDOI
Nonnegative matrix factorization with the itakura-saito divergence: With application to music analysis
TL;DR: Results indicate that IS-NMF correctly captures the semantics of audio and is better suited to the representation of music signals than NMF with the usual Euclidean and KL costs.
Journal ArticleDOI
Speech coding based upon vector quantization
TL;DR: The vector quantizing approach is shown to be a mathematically and computationally tractable method which builds upon knowledge obtained in linear prediction analysis studies and is introduced in a nonrigorous form.