Change search
ReferencesLink to record
Permanent link

Direct link
Supervised and unsupervised speech enhancement using nonnegative matrix factorization
KTH, School of Electrical Engineering (EES), Communication Theory.
University of Illinois at Urbana-Champaign.
KTH, School of Electrical Engineering (EES), Communication Theory.
2013 (English)In: IEEE Transactions on Audio, Speech, and Language Processing, ISSN 1558-7916, Vol. 21, no 10, 2140-2151 p.Article in journal (Refereed) Published
Abstract [en]

Reducing the interference noise in a monaural noisy speech signal has been a challenging task for many years. Compared to traditional unsupervised speech enhancement methods, e. g., Wiener filtering, supervised approaches, such as algorithms based on hidden Markov models (HMM), lead to higher-quality enhanced speech signals. However, the main practical difficulty of these approaches is that for each noise type a model is required to be trained a priori. In this paper, we investigate a new class of supervised speech denoising algorithms using nonnegative matrix factorization (NMF). We propose a novel speech enhancement method that is based on a Bayesian formulation of NMF (BNMF). To circumvent the mismatch problem between the training and testing stages, we propose two solutions. First, we use an HMM in combination with BNMF (BNMF-HMM) to derive a minimum mean square error (MMSE) estimator for the speech signal with no information about the underlying noise type. Second, we suggest a scheme to learn the required noise BNMF model online, which is then used to develop an unsupervised speech enhancement system. Extensive experiments are carried out to investigate the performance of the proposed methods under different conditions. Moreover, we compare the performance of the developed algorithms with state-of-the-art speech enhancement schemes using various objective measures. Our simulations show that the proposed BNMF-based methods outperform the competing algorithms substantially.

Place, publisher, year, edition, pages
IEEE Signal Processing Society, 2013. Vol. 21, no 10, 2140-2151 p.
Keyword [en]
Nonnegative matrix factorization (NMF), speech enhancement, PLCA, HMM, Bayesian Inference
National Category
Engineering and Technology
URN: urn:nbn:se:kth:diva-124353DOI: 10.1109/TASL.2013.2270369ISI: 000322334900013ScopusID: 2-s2.0-84881053943OAI: diva2:634165

QC 20130905

Available from: 2013-06-28 Created: 2013-06-28 Last updated: 2013-09-18Bibliographically approved
In thesis
1. Speech Enhancement Using Nonnegative MatrixFactorization and Hidden Markov Models
Open this publication in new window or tab >>Speech Enhancement Using Nonnegative MatrixFactorization and Hidden Markov Models
2013 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Reducing interference noise in a noisy speech recording has been a challenging task for many years yet has a variety of applications, for example, in handsfree mobile communications, in speech recognition, and in hearing aids. Traditional single-channel noise reduction schemes, such as Wiener filtering, do not work satisfactorily in the presence of non-stationary background noise. Alternatively, supervised approaches, where the noise type is known in advance, lead to higher-quality enhanced speech signals. This dissertation proposes supervised and unsupervised single-channel noise reduction algorithms. We consider two classes of methods for this purpose: approaches based on nonnegative matrix factorization (NMF) and methods based on hidden Markov models (HMM).

 The contributions of this dissertation can be divided into three main (overlapping) parts. First, we propose NMF-based enhancement approaches that use temporal dependencies of the speech signals. In a standard NMF, the important temporal correlations between consecutive short-time frames are ignored. We propose both continuous and discrete state-space nonnegative dynamical models. These approaches are used to describe the dynamics of the NMF coefficients or activations. We derive optimal minimum mean squared error (MMSE) or linear MMSE estimates of the speech signal using the probabilistic formulations of NMF. Our experiments show that using temporal dynamics in the NMF-based denoising systems improves the performance greatly. Additionally, this dissertation proposes an approach to learn the noise basis matrix online from the noisy observations. This relaxes the assumption of an a-priori specified noise type and enables us to use the NMF-based denoising method in an unsupervised manner. Our experiments show that the proposed approach with online noise basis learning considerably outperforms state-of-the-art methods in different noise conditions.

 Second, this thesis proposes two methods for NMF-based separation of sources with similar dictionaries. We suggest a nonnegative HMM (NHMM) for babble noise that is derived from a speech HMM. In this approach, speech and babble signals share the same basis vectors, whereas the activation of the basis vectors are different for the two signals over time. We derive an MMSE estimator for the clean speech signal using the proposed NHMM. The objective evaluations and performed subjective listening test show that the proposed babble model and the final noise reduction algorithm outperform the conventional methods noticeably. Moreover, the dissertation proposes another solution to separate a desired source from a mixture with arbitrarily low artifacts.

 Third, an HMM-based algorithm to enhance the speech spectra using super-Gaussian priors is proposed. Our experiments show that speech discrete Fourier transform (DFT) coefficients have super-Gaussian rather than Gaussian distributions even if we limit the speech data to come from a specific phoneme. We derive a new MMSE estimator for the speech spectra that uses super-Gaussian priors. The results of our evaluations using the developed noise reduction algorithm support the super-Gaussianity hypothesis.

Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology, 2013. xiv, 52 p.
Trita-EE, ISSN 1653-5146 ; 2013:030
Speech enhancement, noise reduction, nonnegative matrix factorization, hidden Markov model, probabilistic latent component analysis, online dictionary learning, super-Gaussian distribution, MMSE estimator, temporal dependencies, dynamic NMF
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
urn:nbn:se:kth:diva-124642 (URN)978-91-7501-833-1 (ISBN)
Public defence
2013-10-18, Lecture Room F3, Lindstedtsvägen 26, KTH, Stockholm, 13:00 (English)

QC 20130916

Available from: 2013-09-16 Created: 2013-07-24 Last updated: 2013-10-09Bibliographically approved

Open Access in DiVA

fulltext(1412 kB)940 downloads
File information
File name FULLTEXT02.pdfFile size 1412 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopusIEEE Xplore

Search in DiVA

By author/editor
Mohammadiha, NasserArne, Leijon
By organisation
Communication Theory
In the same journal
IEEE Transactions on Audio, Speech, and Language Processing
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 952 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 228 hits
ReferencesLink to record
Permanent link

Direct link