Joint Mixing Vector and Binaural Model Based Stereo Source Separation

Abstract

In this paper the mixing vector (MV) in the statistical mixing model is compared to the binaural cues represented by interaural level and phase differences (ILD and IPD). It is shown that the MV distributions are quite distinct while binaural models overlap when the sources are close to each other. On the other hand, the binaural cues are more robust to high reverberation than MV models. According to this complementary behavior we introduce a new robust algorithm for stereo speech separation which considers both additive and convolutive noise signals to model the MV and binaural cues in parallel and estimate probabilistic time-frequency masks. The contribution of each cue to the final decision is also adjusted by weighting the log-likelihoods of the cues empirically. Furthermore, the permutation problem of the frequency domain blind source separation (BSS) is addressed by initializing the MVs based on binaural cues. Experiments are performed systematically on determined and underdetermined speech mixtures in five rooms with various acoustic properties including anechoic, highly reverberant, and spatially-diffuse noise conditions. The results in terms of signal-to-distortion-ratio (SDR) confirm the benefits of integrating the MV and binaural cues, as compared with two state-of-the-art baseline algorithms which only use MV or the binaural cues

Predicting Binaural Speech Intelligibility from Signals Estimated by a Blind Source Separation Algorithm

“…For binaural recordings, the state-of-the-art blind source separation (BSS) methods [11,12,13] using interaural level difference (ILD) and interaural phase difference (IPD) have demonstrated good performance for two-channel source separation. These BSS methods can largely preserve binaural cues, as well as maintain the energy of each sound source, which is vital for speech intelligibility in noise.…”

“…1 illustrates the framework of the proposed system. A BSS algorithm [11,12,13] is applied to extract both the target and masker signals. To implement real-time source separation and intelligibility prediction, the separation model is trained offline.…”

Bootstrap Averaging for Model-Based Source Separation in Reverberant Conditions

“…Model-based blind source separation for exactly determined and underdetermined speech mixtures such as [1], [7], [8], [9], are more recent examples of applications in speech analysis involving frequency-specific GMMs. These methods have gained significant popularity due to their simple modelbased approach for integration of cues.…”

“…More generally, this is due to the absence of an explicit model for reverberation. In addition to this, the frequency domain GMM in these algorithms, [1], [7], [8], relies on the assumption of the cues being independent. As noted in [8, sec.…”

“…[19]. The latter approach integrates binaural cues following the model-based method of [8]. A multichannel source separation method is described in [20].…”