Non-negative Hidden Markov Modeling of Audio with Application to Source Separation

Mysore, Gautham J.; Smaragdis, Paris; Raj, Bhiksha

doi:10.1007/978-3-642-15995-4_18

Cited by 83 publications

(92 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The sequential modeling of bases is conducted with convolutive NMF [7] and hidden Markov models [8], [9]. Shifted NMF [10], [11] identifies the bases that correspond to the notes played by an identical instrument.…”

Section: Introductionmentioning

confidence: 99%

Multichannel Extensions of Non-Negative Matrix Factorization With Complex-Valued Data

Sawada

Kameoka

Araki

et al. 2013

IEEE Trans. Audio Speech Lang. Process.

237

239

View full text Add to dashboard Cite

Abstract-This paper presents new formulations and algorithms for multichannel extensions of non-negative matrix factorization (NMF). The formulations employ Hermitian positive semidefinite matrices to represent a multichannel version of non-negative elements. Multichannel Euclidean distance and multichannel Itakura-Saito (IS) divergence are defined based on appropriate statistical models utilizing multivariate complex Gaussian distributions. To minimize this distance/divergence, efficient optimization algorithms in the form of multiplicative updates are derived by using properly designed auxiliary functions. Two methods are proposed for clustering NMF bases according to the estimated spatial property. Convolutive blind source separation (BSS) is performed by the multichannel extensions of NMF with the clustering mechanism. Experimental results show that 1) the derived multiplicative update rules exhibited good convergence behavior, and 2) BSS tasks for several music sources with two microphones and three instrumental parts were evaluated successfully.

show abstract

Section: Introductionmentioning

confidence: 99%

Multichannel Extensions of Non-Negative Matrix Factorization With Complex-Valued Data

Sawada

Kameoka

Araki

et al. 2013

IEEE Trans. Audio Speech Lang. Process.

237

239

View full text Add to dashboard Cite

show abstract

“…We will benchmark the performance of alternative source models, e.g. [24], when bundled with a diarisation scheme. We will explore realistic initialization schemes, so to create a fully blind joint MASS and diarisation method.…”

Section: Discussionmentioning

confidence: 99%

An EM algorithm for joint source separation and diarisation of multichannel convolutive speech mixtures

Kounades-Bastian

Girin

Alameda-Pineda

et al. 2017

2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

We present a probabilistic model for joint source separation and diarisation of multichannel convolutive speech mixtures. We build upon the framework of local Gaussian model (LGM) with non-negative matrix factorization (NMF). The diarisation is introduced as a temporal labeling of each source in the mix as active or inactive at the short-term frame level. We devise an EM algorithm in which the source separation process is aided by the diarisation state, since the latter indicates the sources actually present in the mixture. The diarisation state is tracked with a Hidden Markov Model (HMM) with emission probabilities calculated from the estimated source signals. The proposed EM has separation performance comparable with a state-of-the-art LGM NMF method, while outperforming a state-of-the-art speaker diarisation pipeline.

show abstract

“…One possible reason the CNMF does not outperform our unsupervised method is that it does not model the temporal dynamics between sets of convolutive bases. In [21], a hidden Markov model (HMM) is incorporated to model this temporal structure.…”

Section: Comparisonmentioning

confidence: 99%

An Unsupervised Approach to Cochannel Speech Separation

Wang

2013

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Abstract-Cochannel (two-talker) speech separation is predominantly addressed using pretrained speaker dependent models. In this paper, we propose an unsupervised approach to separating cochannel speech. Our approach follows the two main stages of computational auditory scene analysis: segmentation and grouping. For voiced speech segregation, the proposed system utilizes a tandem algorithm for simultaneous grouping and then unsupervised clustering for sequential grouping. The clustering is performed by a search to maximize the ratio of between-and within-group speaker distances while penalizing within-group concurrent pitches. To segregate unvoiced speech, we first produce unvoiced speech segments based on onset/offset analysis. The segments are grouped using the complementary binary masks of segregated voiced speech. Despite its simplicity, our approach produces significant SNR improvements across a range of input SNR. The proposed system yields competitive performance in comparison to other speaker-independent and model-based methods.

show abstract

Non-negative Hidden Markov Modeling of Audio with Application to Source Separation

Cited by 83 publications

References 8 publications

Multichannel Extensions of Non-Negative Matrix Factorization With Complex-Valued Data

Multichannel Extensions of Non-Negative Matrix Factorization With Complex-Valued Data

An EM algorithm for joint source separation and diarisation of multichannel convolutive speech mixtures

An Unsupervised Approach to Cochannel Speech Separation

Contact Info

Product

Resources

About