Related papers: Ultra Dual-Path Compression For Joint Echo Cancell…
Most data is automatically collected and only ever "seen" by algorithms. Yet, data compressors preserve perceptual fidelity rather than just the information needed by algorithms performing downstream tasks. In this paper, we characterize…
Dual-encoder-based neural retrieval models achieve appreciable performance and complement traditional lexical retrievers well due to their semantic matching capabilities, which makes them a common choice for hybrid IR systems. However,…
Deep Neural Networks are known to be very demanding in terms of computing and memory requirements. Due to the ever increasing use of embedded systems and mobile devices with a limited resource budget, designing low-complexity models without…
Deep neural networks have delivered remarkable performance and have been widely used in various visual tasks. However, their huge size causes significant inconvenience for transmission and storage. Many previous studies have explored model…
The rapid advancement of large-language models (LLMs) has driven extensive research into parameter compression after training has been completed, yet compression during the training phase remains largely unexplored. In this work, we…
Deep neural networks often have millions of parameters. This can hinder their deployment to low-end devices, not only due to high memory requirements but also because of increased latency at inference. We propose a novel model compression…
This paper investigates the optimization of Truncated Backpropagation Through Time (TBPTT) for training neural networks in digital audio effect modeling, with a focus on dynamic range compression. The study evaluates key TBPTT…
One of the main difficulties in echo cancellation is the fact that the learning rate needs to vary according to conditions such as double-talk and echo path change. Several methods have been proposed to vary the learning. In this paper we…
This paper introduces a dual-signal transformation LSTM network (DTLN) for real-time speech enhancement as part of the Deep Noise Suppression Challenge (DNS-Challenge). This approach combines a short-time Fourier transform (STFT) and a…
The rapid increase in networked systems and data transmission requires advanced data compression solutions to optimize bandwidth utilization and enhance network performance. This study introduces a novel byte-level predictive model using…
Optimizing distributed learning systems is an art of balancing between computation and communication. There have been two lines of research that try to deal with slower networks: {\em communication compression} for low bandwidth networks,…
To strike a balance between energy efficiency and data quality control, this paper proposes a sensor censoring scheme for distributed sparse signal recovery via compressive-sensing based wireless sensor networks. In the proposed approach,…
Full-duplex systems are expected to double the spectral efficiency compared to conventional half-duplex systems if the self-interference signal can be significantly mitigated. Digital cancellation is one of the lowest complexity…
Pruning is an efficient model compression technique to remove redundancy in the connectivity of deep neural networks (DNNs). Computations using sparse matrices obtained by pruning parameters, however, exhibit vastly different parallelism…
Deep neural networks are known to exhibit a `double descent' behavior as the number of parameters increases. Recently, it has also been shown that an `epochwise double descent' effect exists in which the generalization error initially…
Model compression techniques reduce the computational load and memory consumption of deep neural networks. After the compression operation, e.g. parameter pruning, the model is normally fine-tuned on the original training dataset to recover…
While large transformer-based models have exhibited remarkable performance in speaker-independent speech recognition, their large size and computational requirements make them expensive or impractical to use in resource-constrained…
Real-world multichannel time series prediction faces growing demands for efficiency across edge and cloud environments, making channel compression a timely and essential problem. Motivated by the success of Multiple-Input Multiple-Output…
A post-processing adjustment technique which aims for enhancement of dual-frequency SURF (Second order UltRasound Field) reverberation-noise suppression imaging in medical ultrasound is analyzed. Two variant methods are investigated through…
The topic of deep acoustic echo control (DAEC) has seen many approaches with various model topologies in recent years. Convolutional recurrent networks (CRNs), consisting of a convolutional encoder and decoder encompassing a recurrent…