Sorry, you need to enable JavaScript to visit this website.

The problems of speech separation and enhancement concern the extraction of the speech emitted by a target speaker when placed in a scenario where multiple interfering speakers or noise are present, respectively. A plethora of practical applications such as home assistants and teleconferencing require some sort of speech separation and enhancement pre-processing before applying Automatic Speech Recognition (ASR) systems. In the recent years, most techniques have focused on the application of deep learning to either time-frequency or time-domain representations of the input audio signals.

The problems of speech separation and enhancement concern the extraction of the speech emitted by a target speaker when placed in a scenario where multiple interfering speakers or noise are present, respectively. A plethora of practical applications such as home assistants and teleconferencing require some sort of speech separation and enhancement pre-processing before applying Automatic Speech Recognition (ASR) systems. In the recent years, most techniques have focused on the application of deep learning to either time-frequency or time-domain representations of the input audio signals.

In this study, we propose a dense frequency-time attentive network (DeFT-AN) for multichannel speech enhancement. DeFT-AN is a mask estimation network that predicts a complex spectral masking pattern for suppressing the noise and reverberation embedded in the short-time Fourier transform (STFT) of an input signal. The proposed mask estimation network incorporates three different types of blocks for aggregating information in the spatial, spectral, and temporal dimensions.

Mutual learning, the related idea to knowledge distillation, is a group of untrained lightweight networks, which simultaneously learn and share knowledge to perform tasks together during training. In this paper, we propose a novel mutual learning approach, namely selective mutual learning. This is the simple yet effective approach to boost the performance of the networks for speech separation. There are two networks in the selective mutual learning method, they are like a pair of friends learning and sharing knowledge with each other.

With the aim of addressing audio signal restoration as a sequential inference problem, we build upon Gabor regression to propose a state-space model for audio time series. Exploiting the structure of our model, we devise a sequential Markov chain Monte Carlo algorithm to explore the sequence of filtering distributions of the synthesis coefficients. The algorithm is then tested on a series of denoising examples.

This paper describes a blind source separation method for multichannel audio signals, called NF-FastMNMF, based on the integration of the normalizing flow (NF) into the multichannel nonnegative matrix factorization with jointly-diagonalizable spatial covariance matrices, a.k.a. FastMNMF.

Continuous speech separation for meeting pre-processing has recently become a focused research topic. Compared to the data in utterance-level speech separation, the meeting-style audio stream lasts longer, has an uncertain number of speakers. We adopt the time-domain speech separation method and the recently proposed Graph-PIT to build a super low-latency online speech separation model, which is very important for the real application. The low-latency time-domain encoder with a small stride leads to an extremely long feature sequence.

Full-rank spatial covariance analysis (FCA) is a blind source separation (BSS) method, and can be applied to underdetermined cases where the sources outnumber the microphones. This paper proposes a new extension of FCA, aiming to improve BSS performance for mixtures in which the length of reverberation exceeds the analysis frame. There has already been proposed a model that considers delayed source components as the exceeded parts. In contrast, our new extension models multiple time frames with multivariate Gaussian distributions of larger dimensionality than the existing FCA models.

We investigate which loss functions provide better separations via
benchmarking an extensive set of those for music source separation.
To that end, we first survey the most representative audio source
separation losses we identified, to later consistently benchmark them
in a controlled experimental setup. We also explore using such losses
as evaluation metrics, via cross-correlating them with the results of
a subjective test. Based on the observation that the standard signal-
to-distortion ratio metric can be misleading in some scenarios, we