Variational Bayesian Inference for Source Separation and Robust Feature Extraction

Kamil Adiloğlu 1 Emmanuel Vincent 2
2 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : We consider the task of separating and classifying individual sound sources mixed together. The main challenge is to achieve robust classification despite residual distortion of the separated source signals. A promising paradigm is to estimate the uncertainty about the separated source signals and to propagate it through the subsequent feature extraction and classification stages. We argue that variational Bayesian (VB) inference offers a mathematically rigorous way of deriving uncertainty estimators, which contrasts with state-of-the-art estimators based on heuristics or on maximum likelihood (ML) estimation. We propose a general VB source separation algorithm, which makes it possible to jointly exploit spatial and spectral models of the sources. This algorithm achieves 6% and 5% relative error reduction compared to ML uncertainty estimation on the CHiME noise-robust speaker identification and speech recognition benchmarks, respectively, and it opens the way for more complex VB approximations of uncertainty.
Complete list of metadatas

Cited literature [61 references]  Display  Hide  Download

https://hal.inria.fr/hal-00726146
Contributor : Kamil Adiloglu <>
Submitted on : Friday, July 8, 2016 - 9:15:56 AM
Last modification on : Tuesday, June 25, 2019 - 1:27:18 AM

File

double.pdf
Files produced by the author(s)

Identifiers

Citation

Kamil Adiloğlu, Emmanuel Vincent. Variational Bayesian Inference for Source Separation and Robust Feature Extraction. IEEE Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2016, ⟨10.1109/TASLP.2016.2583794⟩. ⟨hal-00726146v2⟩

Share

Metrics

Record views

726

Files downloads

934