Related papers: Sandglasset: A Light Multi-Granularity Self-attent…

Self-supervised speech representation learning has become essential for extracting meaningful features from untranscribed audio. Recent advances highlight the potential of deriving discrete symbols from the features correlated with…

Audio-visual multi-modal modeling has been demonstrated to be effective in many speech related tasks, such as speech recognition and speech enhancement. This paper introduces a new time-domain audio-visual architecture for target speaker…

Transformer has shown advanced performance in speech separation, benefiting from its ability to capture global features. However, capturing local features and channel information of audio sequences in speech separation is equally important.…

Speech enhancement in multichannel settings has been realized by utilizing the spatial information embedded in multiple microphone signals. Moreover, deep neural networks (DNNs) have been recently advanced in this field; however, studies on…

Semi-Supervised Semantic Segmentation (SSSS) aims to improve segmentation accuracy by leveraging a small set of labeled images alongside a larger pool of unlabeled data. Recent advances primarily focus on pseudo-labeling, consistency…

In medical images, various types of lesions often manifest significant differences in their shape and texture. Accurate medical image segmentation demands deep learning models with robust capabilities in multi-scale and boundary feature…

Transformer based models have provided significant performance improvements in monaural speech separation. However, there is still a performance gap compared to a recent proposed upper bound. The major limitation of the current dual-path…

This study presents UX-Net, a time-domain audio separation network (TasNet) based on a modified U-Net architecture. The proposed UX-Net works in real-time and handles either single or multi-microphone input. Inspired by the…

The end-to-end approach for single-channel speech separation has been studied recently and shown promising results. This paper extended the previous approach and proposed a new end-to-end model for multi-channel speech separation. The…

Recently, deep neural networks (DNNs) have been successfully used for speech enhancement, and DNN-based speech enhancement is becoming an attractive research area. While time-frequency masking based on the short-time Fourier transform…

Semantic segmentation with limited annotations, such as weakly supervised semantic segmentation (WSSS) and semi-supervised semantic segmentation (SSSS), is a challenging task that has attracted much attention recently. Most leading WSSS…

Previously proposed FullSubNet has achieved outstanding performance in Deep Noise Suppression (DNS) Challenge and attracted much attention. However, it still encounters issues such as input-output mismatch and coarse processing for…

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…

Closed-Set speaker identification aims to assign a speech utterance to one of a predefined set of enrolled speakers and requires robust modeling of speaker-specific characteristics across multiple temporal scales. While recent deep learning…

High quality speech capture has been widely studied for both voice communication and human computer interface reasons. To improve the capture performance, we can often find multi-microphone speech enhancement techniques deployed on various…

Time series segmentation (TSS) is one of the time series (TS) analysis techniques, that has received considerably less attention compared to other TS related tasks. In recent years, deep learning architectures have been introduced for TSS,…

Single-channel speech separation has recently made great progress thanks to learned filterbanks as used in ConvTasNet. In parallel, parameterized filterbanks have been proposed for speaker recognition where only center frequencies and…

Non-local operations are usually used to capture long-range dependencies via aggregating global context to each position recently. However, most of the methods cannot preserve object shapes since they only focus on feature similarity but…

Keyword spotting (KWS) on mobile devices generally requires a small memory footprint. However, most current models still maintain a large number of parameters in order to ensure good performance. In this paper, we propose a temporally…

Various neural network architectures have been proposed in recent years for the task of multi-channel speech separation. Among them, the filter-and-sum network (FaSNet) performs end-to-end time-domain filter-and-sum beamforming and has…