Related papers: Hybrid noise shaping for audio coding using perfec…
Inspired by the mammal's auditory localization pathway, in this paper we propose a pure spiking neural network (SNN) based computational model for precise sound localization in the noisy real-world environment, and implement this algorithm…
Convolutional neural networks (CNNs) have achieved exciting performance in joint segmentation of optic disc and optic cup on single-institution datasets. However, their clinical translation is hindered by two major challenges: limited…
Window decoding, first proposed to reduce decoding complexity for real-time decoding, is an essential component to realize scalable, universal-fault tolerant computation. Prior work has focused on improving throughput through…
We design an online end-to-end speech recognition system based on Time-Depth Separable (TDS) convolutions and Connectionist Temporal Classification (CTC). We improve the core TDS architecture in order to limit the future context and hence…
Learning with noisy labels has become imperative in the Big Data era, which saves expensive human labors on accurate annotations. Previous noise-transition-based methods have achieved theoretically-grounded performance under the…
We show how the iterative decoding threshold of tailbiting spatially coupled (SC) low-density parity-check (LDPC) code ensembles can be improved over the binary input additive white Gaussian noise channel by allowing the use of different…
In recent years, speech enhancement (SE) has achieved impressive progress with the success of deep neural networks (DNNs). However, the DNN approach usually fails to generalize well to unseen environmental noise that is not included in the…
Multivariate time series (MTS) analysis prevails in real-world applications such as finance, climate science and healthcare. The various self-attention mechanisms, the backbone of the state-of-the-art Transformer-based models, efficiently…
In decentralized active noise control (ANC) systems, crosstalk between multichannel secondary sources and error microphones significantly degrades control accuracy. Moreover, prefiltering reference signals in filtered-x (Fx) type algorithms…
Medical image segmentation traditionally relies on fully supervised 3D architectures that demand a large amount of dense, voxel-level annotations from clinical experts which is a prohibitively expensive process. Vision Language Models…
For neural video codec, it is critical, yet challenging, to design an efficient entropy model which can accurately predict the probability distribution of the quantized latent representation. However, most existing video codecs directly use…
High-mobility scenarios in next-generation wireless networks, such as those involving vehicular communications, require ultra-reliable and low-latency communications (URLLC). However, rapidly time-varying channels pose significant…
We propose Text-Aligned Speech Tokens with Multiple Layer-Aggregation (TASLA), which is a text-aligned speech tokenization framework that aims to address the problem that under a low-frame-rate and text-aligned regime, single-source speech…
Unsupervised domain adaptation for medical image segmentation remains a significant challenge due to substantial domain shifts across imaging modalities, such as CT and MRI. While recent vision-language representation learning methods have…
This paper proposes a novel framework for lung sound event detection, segmenting continuous lung sound recordings into discrete events and performing recognition on each event. Exploiting the lightweight nature of Temporal Convolution…
Text-to-speech (TTS) synthesis has seen renewed progress under the discrete modeling paradigm. Existing autoregressive approaches often rely on single-codebook representations, which suffer from significant information loss. Even with…
Transformers have drawn attention in the MIR field for their remarkable performance shown in natural language processing and computer vision. However, prior works in the audio processing domain mostly use Transformer as a temporal feature…
The Dynamic Communication Network (DCN) describes the interactions over time among various communication nodes, and it is widely used in Big-data applications as a data source. As the number of communication nodes increases and temporal…
There are a number of studies about extraction of bottleneck (BN) features from deep neural networks (DNNs)trained to discriminate speakers, pass-phrases and triphone states for improving the performance of text-dependent speaker…
Cooperative perception significantly enhances scene understanding by integrating complementary information from diverse agents. However, existing research often overlooks critical challenges inherent in real-world multi-source data…