相关论文: Exploring Deep Hybrid Tensor-to-Vector Network Arc…

A new type of End-to-End system for text-dependent speaker verification is presented in this paper. Previously, using the phonetically discriminative/speaker discriminative DNNs as feature extractors for speaker verification has shown…

Deep Neural Networks (DNNs) have shown unparalleled achievements in numerous applications, reflecting their proficiency in managing vast data sets. Yet, their static structure limits their adaptability in ever-changing environments. This…

In speech enhancement, complex neural network has shown promising performance due to their effectiveness in processing complex-valued spectrum. Most of the recent speech enhancement approaches mainly focus on wide-band signal with a…

Audio-visual speech enhancement system is regarded to be one of promising solutions for isolating and enhancing speech of desired speaker. Conventional methods focus on predicting clean speech spectrum via a naive convolution neural network…

Convolutional neural networks (CNNs) are one of the most widely used neural network architectures, showcasing state-of-the-art performance in computer vision tasks. Although larger CNNs generally exhibit higher accuracy, their size can be…

Ensuring intelligible speech communication for hearing assistive devices in low-latency scenarios presents significant challenges in terms of speech enhancement, coding and transmission. In this paper, we propose novel solutions for…

Neural Network designs are quite diverse, from VGG-style to ResNet-style, and from Convolutional Neural Networks to Transformers. Towards the design of efficient accelerators, many works have adopted a dataflow-based, inter-layer pipelined…

The present paper describes a singing voice synthesis based on convolutional neural networks (CNNs). Singing voice synthesis systems based on deep neural networks (DNNs) are currently being proposed and are improving the naturalness of…

To extract accurate speaker information for text-independent speaker verification, temporal dynamic CNNs (TDY-CNNs) adapting kernels to each time bin was proposed. However, model size of TDY-CNN is too large and the adaptive kernel's degree…

Most current speech technology systems are designed to operate well even in the presence of multiple active speakers. However, most solutions assume that the number of co-current speakers is known. Unfortunately, this information might not…

This paper presents a new hybrid architecture for voice activity detection (VAD) incorporating both convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) layers trained in an end-to-end manner. In addition, we…

In this paper, we propose hybrid real- and complex-valued neural networks for speech enhancement. Real- or complex-valued models are either inefficient or present high complexity. We devise a straightforward design method for extending a…

Sentence compression is a Natural Language Processing (NLP) task aimed at shortening original sentences and preserving their key information. Its applications can benefit many fields e.g. one can build tools for language education. However,…

A novel speech feature fusion algorithm with independent vector analysis (IVA) and parallel convolutional neural network (PCNN) is proposed for text-independent speaker recognition. Firstly, some different feature types, such as the time…

Deep neural networks (DNNs) have achieved outstanding performance in a wide range of applications, e.g., image classification, natural language processing, etc. Despite the good performance, the huge number of parameters in DNNs brings…

This paper introduces a tensor neural network (TNN) to address nonparametric regression problems, leveraging its distinct sub-network structure to effectively facilitate variable separation and enhance the approximation of complex,…

This article surveys convolution-based models including convolutional neural networks (CNNs), Conformers, ResNets, and CRNNs-as speech signal processing models and provide their statistical backgrounds and speech recognition, speaker…

Tensor-valued data arise naturally in neuroimaging, genomics, climate science, and spatiotemporal networks, where multilinear dependencies across modes carry information that is destroyed under vectorization. Existing approaches either…

The fundamental frequency (F0) contour of speech is a key aspect to represent speech prosody that finds use in speech and spoken language analysis such as voice conversion and speech synthesis as well as speaker and language identification.…

Recent years, the approaches based on neural networks have shown remarkable potential for sentence modeling. There are two main neural network structures: recurrent neural network (RNN) and convolution neural network (CNN). RNN can capture…