Related papers: D2Former: A Fully Complex Dual-Path Dual-Decoder C…
In this paper, we propose a transformer-based architecture, called two-stage transformer neural network (TSTNN) for end-to-end speech denoising in the time domain. The proposed model is composed of an encoder, a two-stage transformer module…
Speech enhancement has benefited from the success of deep learning in terms of intelligibility and perceptual quality. Conventional time-frequency (TF) domain methods focus on predicting TF-masks or speech spectrum, via a naive convolution…
Recently, self-supervised learning (SSL) techniques have been introduced to solve the monaural speech enhancement problem. Due to the lack of using clean phase information, the enhancement performance is limited in most SSL methods.…
This paper describes a practical dual-process speech enhancement system that adapts environment-sensitive frame-online beamforming (front-end) with help from environment-free block-online source separation (back-end). To use minimum…
The popular frameworks for self-supervised learning of speech representations have largely focused on frame-level masked prediction of speech regions. While this has shown promising downstream task performance for speech recognition and…
Studies have shown that in noisy acoustic environments, providing binaural signals to the user of an assistive listening device may improve speech intelligibility and spatial awareness. This paper presents a binaural speech enhancement…
Most deep learning-based models for speech enhancement have mainly focused on estimating the magnitude of spectrogram while reusing the phase from noisy speech for reconstruction. This is due to the difficulty of estimating the phase of…
Deep complex U-Net structure and convolutional recurrent network (CRN) structure achieve state-of-the-art performance for monaural speech enhancement. Both deep complex U-Net and CRN are encoder and decoder structures with skip connections,…
The Dilated FAVOR Conformer (DF-Conformer) is an efficient variant of the Conformer architecture designed for speech enhancement (SE). It employs fast attention through positive orthogonal random features (FAVOR+) to mitigate the quadratic…
The objective of deep learning methods based on encoder-decoder architectures for music source separation is to approximate either ideal time-frequency masks or spectral representations of the target music source(s). The spectral…
Deep neural networks have shown promising potential for ultrasound-to-speech conversion task towards Silent Speech Interfaces. In this work, we applied two Conformer-based DNN architectures (Base and one with bi-LSTM) for this task.…
While deep neural networks have facilitated significant advancements in the field of speech enhancement, most existing methods are developed following either empirical or relatively blind criteria, lacking adequate guidelines in pipeline…
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.…
Deepfake speech detection presents a growing challenge as generative audio technologies continue to advance. We propose a hybrid training framework that advances detection performance through novel augmentation strategies. First, we…
In this paper, we present a scheme for extending deep neural network-based multiplicative maskers to deep subband filters for speech restoration in the time-frequency domain. The resulting method can be generically applied to any deep…
Recent high-performance transformer-based speech enhancement models demonstrate that time domain methods could achieve similar performance as time-frequency domain methods. However, time-domain speech enhancement systems typically receive…
Self-supervised learning has demonstrated impressive performance in speech tasks, yet there remains ample opportunity for advancement in the realm of speech enhancement research. In addressing speech tasks, confining the attention mechanism…
For the difficulty and large computational complexity of modeling more frequency bands, full-band speech enhancement based on deep neural networks is still challenging. Previous studies usually adopt compressed full-band speech features in…
Current multi-channel speech enhancement systems mainly adopt single-output architecture, which face significant challenges in preserving spatio-temporal signal integrity during multiple-input multiple-output (MIMO) processing. To address…
This paper proposes a model that integrates sub-band processing and deep filtering to fully exploit information from the target time-frequency (TF) bin and its surrounding TF bins for single-channel speech enhancement. The sub-band module…