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

The end-to-end approaches for single-channel target speech extraction have attracted widespread attention. However, the studies for end-to-end multi-channel target speech extraction are still relatively limited. In this work, we propose two methods for exploiting the multi-channel spatial information to extract the target speech. The first one is using a target speech adaptation layer in a parallel encoder architecture. The second one is designing a channel decorrelation mechanism to extract the inter-channel differential information to enhance the multi-channel encoder representation.

We consider globally optimal precoder design for rate splitting multiple access in Gaussian multiple-input single-output downlink channels with respect to weighted sum rate and energy efficiency maximization. The proposed algorithm solves an instance of the joint multicast and unicast beamforming problem and includes multicast- and unicast-only beamforming as special cases. Numerical results show that it outperforms state-of-the-art algorithms in terms of numerical stability and converges almost twice as fast.

In this paper, we propose a residual echo suppression method using a UNet neural network that directly maps the outputs of a linear acoustic echo canceler to the desired signal in the spectral domain. This system embeds a design parameter that allows a tunable tradeoff between the desired-signal distortion and residual echo suppression in double-talk scenarios. The system employs 136 thousand parameters, and requires 1.6 Giga floating-point operations per second and 10 Mega-bytes of memory.

Turing computability deals with the question of what is theoretically computable on a digital computer, and hence is relevant whenever digital hardware is used. In this paper we study different possibilities to define computable bandlimited signals and systems. We consider a definition that uses finite Shannon sampling series as approximating functions and another that employs computable continuous functions together with an effectively computable time concentration. We discuss the advantages and drawbacks of both definitions and analyze the connections and differences.

Multi-frame algorithms for single-microphone speech enhancement, e.g., the multi-frame minimum variance distortionless response (MFMVDR) filter, are able to exploit speech correlation across adjacent time frames in the short-time Fourier transform (STFT) domain. Provided that accurate estimates of the required speech interframe correlation vector and the noise correlation matrix are available, it has been shown that the MFMVDR filter yields a substantial noise reduction while hardly introducing any speech distortion.

Multi-frame algorithms for single-microphone speech enhancement, e.g., the multi-frame minimum variance distortionless response (MFMVDR) filter, are able to exploit speech correlation across adjacent time frames in the short-time Fourier transform (STFT) domain. Provided that accurate estimates of the required speech interframe correlation vector and the noise correlation matrix are available, it has been shown that the MFMVDR filter yields a substantial noise reduction while hardly introducing any speech distortion.

When approaching graph signal processing tasks, graphs are usually assumed to be perfectly known. However, in many practical applications, the observed (inferred) network is prone to perturbations which, if ignored, will hinder performance. Tailored to those setups, this paper presents a robust formulation for the problem of graph-filter identification from input-output observations. Different from existing works, our approach consists in addressing the robust identification by formulating a joint graph denoising and graph-filter identification problem.