相关论文: Time-Graph Frequency Representation with Singular …

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…

We propose a new algorithm for time stretching music signals based on the theory of nonstationary Gabor frames (NSGFs). The algorithm extends the techniques of the classical phase vocoder (PV) by incorporating adaptive time-frequency (TF)…

While Graph Neural Networks (GNNs) excel on graph-structured data, their performance is fundamentally limited by the quality of the observed graph, which often contains noise, missing links, or structural properties misaligned with GNNs'…

This study proposes a trainable adaptive window switching (AWS) method and apply it to a deep-neural-network (DNN) for speech enhancement in the modified discrete cosine transform domain. Time-frequency (T-F) mask processing in the…

In this paper, we propose a simple yet effective graph neural network for directed graphs (digraph) based on the classic Singular Value Decomposition (SVD), named SVD-GCN. The new graph neural network is built upon the graph SVD-framelet to…

Deep learning has dramatically improved the performance of speech recognition systems through learning hierarchies of features optimized for the task at hand. However, true end-to-end learning, where features are learned directly from…

We propose TF-GridNet for speech separation. The model is a novel deep neural network (DNN) integrating full- and sub-band modeling in the time-frequency (T-F) domain. It stacks several blocks, each consisting of an intra-frame full-band…

The performance of speaker verification degrades significantly in adverse acoustic environments with strong reverberation and noise. To address this issue, this paper proposes a spatial-temporal graph convolutional network (GCN) method for…

Deep learning based speech enhancement in the short-time Fourier transform (STFT) domain typically uses a large window length such as 32 ms. A larger window can lead to higher frequency resolution and potentially better enhancement. This…

Recent research has shown that Deep Neural Networks (DNNs) are highly vulnerable to adversarial samples, which are highly transferable and can be used to attack other unknown black-box models. To improve the transferability of adversarial…

Graph-based temporal classification (GTC), a generalized form of the connectionist temporal classification loss, was recently proposed to improve automatic speech recognition (ASR) systems using graph-based supervision. For example, GTC was…

The key problem in multivariate time series (MTS) analysis and forecasting aims to disclose the underlying couplings between variables that drive the co-movements. Considerable recent successful MTS methods are built with graph neural…

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…

Graph Neural Networks (GNNs) have shown excellent performance on graphs that exhibit strong homophily with respect to the node labels i.e. connected nodes have same labels. However, they perform poorly on heterophilic graphs. Recent…

Speech enhancement concerns the processes required to remove unwanted background sounds from the target speech to improve its quality and intelligibility. In this paper, a novel approach for single-channel speech enhancement is presented,…

Forecasting outcomes in mixed-motive negotiations requires integrating explicit linguistic cues with latent strategic constraints, such as budgets and alternatives. Existing computational models often fail to adapt to varying task…

Two-stage pipeline is popular in speech enhancement tasks due to its superiority over traditional single-stage methods. The current two-stage approaches usually enhance the magnitude spectrum in the first stage, and further modify the…

Conventional time-delay neural networks (TDNNs) struggle to handle long-range context, their ability to represent speaker information is therefore limited in long utterances. Existing solutions either depend on increasing model complexity…

In this work, we propose a novel consistency-preserving loss function for recovering the phase information in the context of phase reconstruction (PR) and speech enhancement (SE). Different from conventional techniques that directly…

This paper investigates different trade-offs between the number of model parameters and enhanced speech qualities by employing several deep tensor-to-vector regression models for speech enhancement. We find that a hybrid architecture,…