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

Transformer-based models have become the state of the art across multiple domains, from natural language processing to machine listening, thanks to the attention mechanisms. However, the attention layers require a large number of parameters…

Despite the rapid progress in speech enhancement (SE) research, enhancing the quality of desired speech in environments with strong noise and interfering speakers remains challenging. In this paper, we extend the application of the recently…

FullSubNet has shown its promising performance on speech enhancement by utilizing both fullband and subband information. However, the relationship between fullband and subband in FullSubNet is achieved by simply concatenating the output of…

This paper addresses the problem of microphone array generalization for deep-learning-based end-to-end multichannel speech enhancement. We aim to train a unique deep neural network (DNN) potentially performing well on unseen microphone…

Transformer models have revolutionized natural language processing with their unparalleled ability to grasp complex contextual relationships. However, the vast number of parameters in these models has raised concerns regarding computational…

The rapid expansion of Large Language Models (LLMs) has posed significant challenges regarding the computational resources required for fine-tuning and deployment. Recent advancements in low-rank adapters have demonstrated their efficacy in…

Modern compression algorithms are often the result of laborious domain-specific research; industry standards such as MP3, JPEG, and AMR-WB took years to develop and were largely hand-designed. We present a deep neural network model which…

The optimization of a wavelet-based algorithm to improve speech intelligibility along with the full data set and results are reported. The discrete-time speech signal is split into frequency sub-bands via a multi-level discrete wavelet…

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…

This paper proposes a deep speech enhancement method which exploits the high potential of residual connections in a wide neural network architecture, a topology known as Wide Residual Network. This is supported on single dimensional…

Recently, attention-based transformers have become a de facto standard in many deep learning applications including natural language processing, computer vision, signal processing, etc.. In this paper, we propose a transformer-based…

Compact neural network offers many benefits for real-world applications. However, it is usually challenging to train the compact neural networks with small parameter sizes and low computational costs to achieve the same or better model…

This paper describes our submission to the L3DAS22 Challenge Task 1, which consists of speech enhancement with 3D Ambisonic microphones. The core of our approach combines Deep Neural Network (DNN) driven complex spectral mapping with linear…

Deep pre-trained Transformer models have achieved state-of-the-art results over a variety of natural language processing (NLP) tasks. By learning rich language knowledge with millions of parameters, these models are usually…

We present a novel general speech restoration model, DBP-Net (dual-branch parallel network), designed to effectively handle complex real-world distortions including noise, reverberation, and bandwidth degradation. Unlike prior approaches…

Self-supervised speech representation learning has shown promising results in various speech processing tasks. However, the pre-trained models, e.g., HuBERT, are storage-intensive Transformers, limiting their scope of applications under…

This paper investigates a self-adaptation method for speech enhancement using auxiliary speaker-aware features; we extract a speaker representation used for adaptation directly from the test utterance. Conventional studies of deep neural…

Although the complex spectrum-based speech enhancement(SE) methods have achieved significant performance, coupling amplitude and phase can lead to a compensation effect, where amplitude information is sacrificed to compensate for the phase…

Speech enhancement promises higher efficiency in ad-hoc microphone arrays than in constrained microphone arrays thanks to the wide spatial coverage of the devices in the acoustic scene. However, speech enhancement in ad-hoc microphone…

We propose a multi-objective framework to learn both secondary targets not directly related to the intended task of speech enhancement (SE) and the primary target of the clean log-power spectra (LPS) features to be used directly for…