Related papers: Scalable and Efficient Neural Speech Coding: A Hyb…
Efficiently representing audio signals in a compressed latent space is critical for latent generative modelling. However, existing autoencoders often force a choice between continuous embeddings and discrete tokens. Furthermore, achieving…
Unsupervised representation learning of speech has been of keen interest in recent years, which is for example evident in the wide interest of the ZeroSpeech challenges. This work presents a new method for learning frame level…
While recent neural audio codecs deliver superior speech quality at ultralow bitrates over traditional methods, their practical adoption is hindered by obstacles related to low-resource operation and robustness to acoustic distortions. Edge…
We propose a novel decentralized feature extraction approach in federated learning to address privacy-preservation issues for speech recognition. It is built upon a quantum convolutional neural network (QCNN) composed of a quantum circuit…
This paper presents a novel convolutional neural network (CNN) based image compression framework via scalable auto-encoder (SAE). Specifically, our SAE based deep image codec consists of hierarchical coding layers, each of which is an…
Modern speech enhancement algorithms achieve remarkable noise suppression by means of large recurrent neural networks (RNNs). However, large RNNs limit practical deployment in hearing aid hardware (HW) form-factors, which are battery…
Speech super-resolution (SR) is a task to increase speech sampling rate by generating high-frequency components. Existing speech SR methods are trained in constrained experimental settings, such as a fixed upsampling ratio. These strong…
In this paper, we design a deep learning-based convolutional autoencoder for channel coding and modulation. The objective is to develop an adaptive scheme capable of operating at various signal-to-noise ratios (SNR)s without the need for…
In this work, we analyze the capabilities and practical limitations of neural networks (NNs) for sequence-based signal processing which can be seen as an omnipresent property in almost any modern communication systems. In particular, we…
Humans interpret and perceive the world by integrating sensory information from multiple modalities, such as vision and hearing. Spiking Neural Networks (SNNs), as brain-inspired computational models, exhibit unique advantages in emulating…
Recently end-to-end neural audio/speech coding has shown its great potential to outperform traditional signal analysis based audio codecs. This is mostly achieved by following the VQ-VAE paradigm where blind features are learned,…
Wireless networked control system (WNCS) connecting sensors, controllers, and actuators via wireless communications is a key enabling technology for highly scalable and low-cost deployment of control systems in the Industry 4.0 era. Despite…
We introduce a practical real-time neural video codec (NVC) designed to deliver high compression ratio, low latency and broad versatility. In practice, the coding speed of NVCs depends on 1) computational costs, and 2) non-computational…
This work presents our ongoing research of unsupervised pretraining in neural machine translation (NMT). In our method, we initialize the weights of the encoder and decoder with two language models that are trained with monolingual data and…
Neural video compression has recently demonstrated significant potential to compete with conventional video codecs in terms of rate-quality performance. These learned video codecs are however associated with various issues related to…
Coding schemes for discrete memoryless multicast networks (DM-MN) with rate-limited feedback from the receivers and relays to the transmitter are proposed. The schemes improve over the noisy network coding proposed by Lim et al.. For the…
Deep complex convolution recurrent network (DCCRN), which extends CRN with complex structure, has achieved superior performance in MOS evaluation in Interspeech 2020 deep noise suppression challenge (DNS2020). This paper further extends…
Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference, especially when deploying to edge or IoT devices with limited computation capacity and power consumption budget. The uniform bit…
We introduce CrossNet, a complex spectral mapping approach to speaker separation and enhancement in reverberant and noisy conditions. The proposed architecture comprises an encoder layer, a global multi-head self-attention module, a…
Large-scale mobile communication systems tend to contain legacy transmission channels with narrowband bottlenecks, resulting in characteristic "telephone-quality" audio. While higher quality codecs exist, due to the scale and heterogeneity…