Related papers: A light-weight full-band speech enhancement model

While traditional statistical signal processing model-based methods can derive the optimal estimators relying on specific statistical assumptions, current learning-based methods further promote the performance upper bound via deep neural…

As more speech processing applications execute locally on edge devices, a set of resource constraints must be considered. In this work we address one of these constraints, namely over-the-network data budgets for transferring models from…

Recent speech enhancement methods based on convolutional neural networks (CNNs) and transformer have been demonstrated to efficaciously capture time-frequency (T-F) information on spectrogram. However, the correlation of each channels of…

Model compression has become an emerging need as the sizes of modern speech systems rapidly increase. In this paper, we study model weight quantization, which directly reduces the memory footprint to accommodate computationally…

Masked Language Modeling (MLM) is widely used to pretrain language models. The standard random masking strategy in MLM causes the pre-trained language models (PLMs) to be biased toward high-frequency tokens. Representation learning of rare…

Distant speech recognition is a challenge, particularly due to the corruption of speech signals by reverberation caused by large distances between the speaker and microphone. In order to cope with a wide range of reverberations in…

We present a hybrid framework that leverages the trade-off between temporal and frequency precision in audio representations to improve the performance of speech enhancement task. We first show that conventional approaches using specific…

Continued improvements in machine learning techniques offer exciting new opportunities through the use of larger models and larger training datasets. However, there is a growing need to offer these new capabilities on-board low-powered…

A mixed sample data augmentation strategy is proposed to enhance the performance of models on audio scene classification, sound event classification, and speech enhancement tasks. While there have been several augmentation methods shown to…

Language models have been successfully used to model natural signals, such as images, speech, and music. A key component of these models is a high quality neural compression model that can compress high-dimensional natural signals into…

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…

Recently, speech enhancement technologies that are based on deep learning have received considerable research attention. If the spatial information in microphone signals is exploited, microphone arrays can be advantageous under some adverse…

Federated learning is a distributed learning paradigm in which multiple mobile clients train a global model while keeping data local. These mobile clients can have various available memory and network bandwidth. However, to achieve the best…

Low power deep learning accelerators on the speech processing enable real-time applications on edge devices. However, most of the existing accelerators suffer from high power consumption and focus on image applications only. This paper…

We study the compressive diffusion strategies over distributed networks based on the diffusion implementation and adaptive extraction of the information from the compressed diffusion data. We demonstrate that one can achieve a comparable…

In this paper, we explore an improved framework to train a monoaural neural enhancement model for robust speech recognition. The designed training framework extends the existing mixture invariant training criterion to exploit both unpaired…

Deep learning algorithm are increasingly used for speech enhancement (SE). In supervised methods, global and local information is required for accurate spectral mapping. A key restriction is often poor capture of key contextual information.…

Universal speech enhancement aims at handling inputs with various speech distortions and recording conditions. In this work, we propose a novel hybrid architecture that synergizes the signal fidelity of discriminative modeling with the…

Speech bandwidth extension (BWE) has demonstrated promising performance in enhancing the perceptual speech quality in real communication systems. Most existing BWE researches primarily focus on fixed upsampling ratios, disregarding the fact…

The advent of hyper-scale and general-purpose pre-trained models is shifting the paradigm of building task-specific models for target tasks. In the field of audio research, task-agnostic pre-trained models with high transferability and…