Underdetermined blind separation and tracking of moving sources based ONDOA-HMM

Abstract

This paper deals with the problem of the underdetermined blind separation and tracking of moving sources. In practical situations, sound sources such as human speakers can move freely and so blind separation algorithms must be designed to track the temporal changes of the impulse responses. We propose solving this problem through the posterior inference of the parameters in a generative model of an observed multichannel signal, formulated under the assumption of the sparsity of time-frequency components of speech and the continuity of speakers' movements. Specifically, we describe a generative model of mixture signals by incorporating a generative model of a time-varying frequency array response for each source, described using a path-restricted hidden Markov model (H-MM). Each hidden state of the present HMM represents the direction of arrival (DOA) of each source, and so we call it a "DOA-HMM." Through the posterior inference of the overall generative model, we can simultaneously track the DOAs of sources, separate source signals and perform permutation alignment. The experiment showed that the proposed algorithm provided a 6.20 dB improvement compared with the conventional method in terms of the signalto-interference ratio.

Separation of Moving Sound Sources Using Multichannel NMF and Acoustic Tracking

“…Alternatively, separation of moving sources can be achieved by tracking the spatial position or direction of arrival (DOA) of the sources and using spatial filtering (beamforming or separation mask) for extracting the signal originating from the estimated position or direction in each time instance. In [25] the problem of DOA tracking and separation mask estimation is formulated jointly, however in this paper we consider a two stage approach where the acoustic tracking is done first and the separation masks are estimated in a separate (offline) stage. Also the separation masks are binary in [25] which will lead to compromised subjective separation quality even if oracle masks are used.…”

“…In [25] the problem of DOA tracking and separation mask estimation is formulated jointly, however in this paper we consider a two stage approach where the acoustic tracking is done first and the separation masks are estimated in a separate (offline) stage. Also the separation masks are binary in [25] which will lead to compromised subjective separation quality even if oracle masks are used.…”

2-D DOA tracking using variational sparse Bayesian learning embedded with Kalman filter

“…This method mainly introduced a thresholding function to enforce sparsity. A model was proposed to describe a time-varying array response in the frequency domain for each source [23]. The key of this paper is that it utilizes a hidden Markov model to describe the moving signal and uses the posterior inference to estimate the signal positions.…”

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

“…al. [9,10,11], a framework addressing jointly the two problems seems overlooked in the literature; in [9,10] the active/inactive state of a source is independently modeled with a factorial HMM in a MASS framework. This independent modeling of the activity of a source with respect to the activity of the other sources may be unrealistic for multiparty conversations.…”

“…This independent modeling of the activity of a source with respect to the activity of the other sources may be unrealistic for multiparty conversations. In [10] the source activity detection is combined with a direction-of-arrival-dependent HMM for the propagation model. A variational expectation maximization (EM) is presented that infers the sources, their activity and the model parameters, although under the assumption of a single active source per time-frequency bin.…”