相关论文: GLD-Net: Improving Monaural Speech Enhancement by …

In this paper we investigate the GMM-derived (GMMD) features for adaptation of deep neural network (DNN) acoustic models. The adaptation of the DNN trained on GMMD features is done through the maximum a posteriori (MAP) adaptation of the…

Speech enhancement in hearing aids is a challenging task since the hardware limits the number of possible operations and the latency needs to be in the range of only a few milliseconds. We propose a deep-learning model compatible with these…

Convolutional Neural Networks (CNNs) have achieved outstanding performance on image processing challenges. Actually, CNNs imitate the typically developed human brain structures at the micro-level (Artificial neurons). At the same time, they…

This paper investigates the effects of limited speech data in the context of speaker verification using deep neural network (DNN) approach. Being able to reduce the length of required speech data is important to the development of speaker…

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…

In speaker verification, traditional models often emphasize modeling long-term contextual features to capture global speaker characteristics. However, this approach can neglect fine-grained voiceprint information, which contains highly…

Deep Convolutional Neural Networks (CNNs), such as Dense Convolutional Networks (DenseNet), have achieved great success for image representation by discovering deep hierarchical information. However, most existing networks simply stacks the…

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…

Deep neural networks (DNNs) represent the mainstream methodology for supervised speech enhancement, primarily due to their capability to model complex functions using hierarchical representations. However, a recent study revealed that DNNs…

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…

Online Speech Enhancement was mainly reserved for predictive models. A key advantage of these models is that for an incoming signal frame from a stream of data, the model is called only once for enhancement. In contrast, generative Speech…

In recent years, deep learning has achieved remarkable success in the field of image restoration. However, most convolutional neural network-based methods typically focus on a single scale, neglecting the incorporation of multi-scale…

Detecting abusive language in social media conversations poses significant challenges, as identifying abusiveness often depends on the conversational context, characterized by the content and topology of preceding comments. Traditional…

Time delay neural networks (TDNNs) are an effective acoustic model for large vocabulary speech recognition. The strength of the model can be attributed to its ability to effectively model long temporal contexts. However, current TDNN models…

Speech enhancement aims to improve speech quality and intelligibility, especially in noisy environments where background noise degrades speech signals. Currently, deep learning methods achieve great success in speech enhancement, e.g. the…

Recent advances in the Active Speaker Detection (ASD) problem build upon a two-stage process: feature extraction and spatio-temporal context aggregation. In this paper, we propose an end-to-end ASD workflow where feature learning and…

Recently, encoder-decoder neural networks have shown impressive performance on many sequence-related tasks. The architecture commonly uses an attentional mechanism which allows the model to learn alignments between the source and the target…

Speech enhancement involves the distinction of a target speech signal from an intrusive background. Although generative approaches using Variational Autoencoders or Generative Adversarial Networks (GANs) have increasingly been used in…

Convolutional neural networks (CNN) are one of the best-performing neural network architectures for environmental sound classification (ESC). Recently, temporal attention mechanisms have been used in CNN to capture the useful information…

Deep learning has the potential to enhance speech signals and increase their intelligibility for users of hearing aids. Deep models suited for real-world application should feature a low computational complexity and low processing delay of…