Related papers: Rethinking the Separation Layers in Speech Separat…
We present a novel approach that improves the performance of reverberant speech separation. Our approach is based on an accurate geometric acoustic simulator (GAS) which generates realistic room impulse responses (RIRs) by modeling both…
The substantial memory demands of pre-training and fine-tuning large language models (LLMs) require memory-efficient optimization algorithms. One promising approach is layer-wise optimization, which treats each transformer block as a single…
As an important component of multimedia analysis tasks, audio classification aims to discriminate between different audio signal types and has received intensive attention due to its wide applications. Generally speaking, the raw signal can…
Training speech separation models in the supervised setting raises a permutation problem: finding the best assignation between the model predictions and the ground truth separated signals. This inherently ambiguous task is customarily…
Previous work has attempted to boost Large Language Model (LLM) performance on planning and scheduling tasks through a variety of prompt engineering techniques. While these methods can work within the distributions tested, they are neither…
Multi-speaker speech recognition of unsegmented recordings has diverse applications such as meeting transcription and automatic subtitle generation. With technical advances in systems dealing with speech separation, speaker diarization, and…
Channel estimation is a critical task in multiple-input multiple-output (MIMO) digital communications that substantially effects end-to-end system performance. In this work, we introduce a novel approach for channel estimation using deep…
MIMO processing plays a central part towards the recent increase in spectral and energy efficiencies of wireless networks. MIMO has grown beyond the original point-to-point channel and nowadays refers to a diverse range of centralized and…
Spatial Modulation (SM) is a technique that can enhance the capacity of MIMO schemes by exploiting the index of transmit antenna to convey information bits. In this paper, we describe this technique, and present a new MIMO transmission…
The characteristics of a space-to-space multiple-input, multiple-output (MIMO) communication channel that distinguish it from terrestrial MIMO communication channels are summarized and discussed primarily from an information-theoretic…
Deep learning-based single-channel speaker separation has improved significantly in recent years largely due to the introduction of the transformer-based attention mechanism. However, these improvements come at the expense of intense…
Massive Multiple-Input Multiple-Output (MIMO) is foreseen to be one of the main technology components in next generation cellular communications (5G). In this paper, fundamental limits on the performance of downlink massive MIMO systems are…
Using Gaussian inputs and treating interference as noise at the receivers has recently been shown to be sum capacity achieving for the two-user single-input single-output (SISO) Gaussian interference channel in a low interference regime,…
This paper considers an interference network composed of K half-duplex single-antenna pairs of users who wish to establish bi-directional communication with the aid of a multi-input-multi-output (MIMO) half-duplex relay node. This channel…
In a recent work, a capacity-achieving scheme for the common-message two-user MIMO broadcast channel, based on single-stream coding and decoding, was described. This was obtained via a novel joint unitary triangularization which is applied…
Speech Enhancement (SE) systems typically operate on monaural input and are used for applications including voice communications and capture cleanup for user generated content. Recent advancements and changes in the devices used for these…
Multiple-input multiple-output (MIMO) techniques allow for multiplexing and/or diversity gain, and will be widely deployed in future wireless systems. In this paper, we propose a MIMO-assisted channel-based authentication scheme, exploiting…
In recent years, speech processing algorithms have seen tremendous progress primarily due to the deep learning renaissance. This is especially true for speech separation where the time-domain audio separation network (TasNet) has led to…
This dissertation covers a single-processor approach to the speech processing pipeline of bilateral Cochlear Implants (CIs). The use of only a single processor to provide binaural stimulation signals overcomes the synchronization problem,…
Despite the remarkable progress recently made in distant speech recognition, state-of-the-art technology still suffers from a lack of robustness, especially when adverse acoustic conditions characterized by non-stationary noises and…