English
Related papers

Related papers: HARP-Net: Hyper-Autoencoded Reconstruction Propaga…

200 papers

Manifold learning aims to discover and represent low-dimensional structures underlying high-dimensional data while preserving critical topological and geometric properties. Existing methods often fail to capture local details with global…

Machine Learning · Computer Science 2025-05-08 Ren Wang , Pengcheng Zhou

Subcode-ensemble decoders improve iterative decoding by running multiple decoders in parallel over carefully chosen subcodes, increasing the likelihood that at least one decoder avoids the dominant trapping structures. Achieving strong…

Information Theory · Computer Science 2026-02-10 Yubeen Jo , Geon Choi , Chanho Park , Namyoon Lee

Many modern datasets mix points, edges, regions, groups, objects, events, hyperedges, and relations. Yet neural architectures often force such data into grids, graphs, or sequences, obscuring higher-order structure and making…

Interpreting the internal activations of neural networks can produce more faithful explanations of their behavior, but is difficult due to the complex structure of activation space. Existing approaches to scalable interpretability use…

Artificial Intelligence · Computer Science 2025-12-18 Vincent Huang , Dami Choi , Daniel D. Johnson , Sarah Schwettmann , Jacob Steinhardt

We propose the use of Non-Negative Autoencoders (NAEs) for sound deconstruction and user-guided manipulation of sounds for creative purposes. NAEs offer a versatile and scalable extension of traditional Non-Negative Matrix Factorization…

Sound · Computer Science 2025-10-13 Juan José Burred , Carmine-Emanuele Cella

While existing audio watermarking techniques have achieved strong robustness against traditional digital signal processing (DSP) attacks, they remain vulnerable to neural resynthesis. This occurs because modern neural audio codecs act as…

The Swapping Autoencoder achieved state-of-the-art performance in deep image manipulation and image-to-image translation. We improve this work by introducing a simple yet effective auxiliary module based on gradient reversal layers. The…

Computer Vision and Pattern Recognition · Computer Science 2022-08-25 Shima Shahfar , Charalambos Poullis

Although end-to-end (E2E) trainable automatic speech recognition (ASR) has shown great success by jointly learning acoustic and linguistic information, it still suffers from the effect of domain shifts, thus limiting potential applications.…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-28 Keqi Deng , Philip C. Woodland

This paper introduces a novel neural network (NN) structure referred to as an ``Auto-hybrid precoder'' (Auto-HP) and an unsupervised deep learning (DL) approach that jointly designs \ac{mmWave} probing beams and hybrid precoding matrix…

Networking and Internet Architecture · Computer Science 2025-03-12 Asmaa Abdallah , Abdulkadir Celik , Ahmed Alkhateeb , Ahmed M. Eltawil

This paper proposes a U-Net-based autoencoder framework for mitigating interference in communication signals corrupted by noise and diverse interference sources. The approach targets scenarios involving both signal-plus-noise and…

Signal Processing · Electrical Eng. & Systems 2025-12-17 Hiten Prakash Kothari , R. Michael Buehrer

Audio pretrained models are widely employed to solve various tasks in speech processing, sound event detection, or music information retrieval. However, the representations learned by these models are unclear, and their analysis mainly…

Distributed visual analysis applications, such as mobile visual search or Visual Sensor Networks (VSNs) require the transmission of visual content on a bandwidth-limited network, from a peripheral node to a processing unit. Traditionally, a…

Multimedia · Computer Science 2016-11-17 Luca Baroffio , Matteo Cesana , Alessandro Redondi , Marco Tagliasacchi , Stefano Tubaro

Semantic communication has witnessed a great progress with the development of natural language processing (NLP) and deep learning (DL). Although existing semantic communication technologies can effectively reduce errors in semantic…

Systems and Control · Electrical Eng. & Systems 2022-07-06 Qingyang Zhou , Rongpeng Li , Zhifeng Zhao , Yong Xiao , Honggang Zhang

Variational autoencoders learn unsupervised data representations, but these models frequently converge to minima that fail to preserve meaningful semantic information. For example, variational autoencoders with autoregressive decoders often…

Machine Learning · Computer Science 2019-05-21 Bryan Seybold , Emily Fertig , Alex Alemi , Ian Fischer

The topic of deep acoustic echo control (DAEC) has seen many approaches with various model topologies in recent years. Convolutional recurrent networks (CRNs), consisting of a convolutional encoder and decoder encompassing a recurrent…

Audio and Speech Processing · Electrical Eng. & Systems 2023-07-31 Ernst Seidel , Pejman Mowlaee , Tim Fingscheidt

Featured by a bottleneck structure, autoencoder (AE) and its variants have been largely applied in various medical image analysis tasks, such as segmentation, reconstruction and de-noising. Despite of their promising performances in…

Image and Video Processing · Electrical Eng. & Systems 2023-04-03 Weixun Luo , Xiaodan Xing , Guang Yang

We investigate applying audio manipulations using pretrained neural network-based autoencoders as an alternative to traditional signal processing methods, since the former may provide greater semantic or perceptual organization. To…

Audio and Speech Processing · Electrical Eng. & Systems 2023-04-11 Scott H. Hawley , Christian J. Steinmetz

Speech separation in realistic acoustic environments remains challenging because overlapping speakers, background noise, and reverberation must be resolved simultaneously. Although recent time-frequency (TF) domain models have shown strong…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-15 Ui-Hyeop Shin , Hyung-Min Park

Recent neural audio compression models often rely on residual vector quantization for high-fidelity coding, but using a fixed number of per-frame codebooks is suboptimal for the wide variability of audio content-especially for signals that…

Sound · Computer Science 2026-05-08 Xiangbo Wang , Wenbin Jiang , Jin Wang , Yubo You , Sheng Fang , Fei Wen

In speech separation, time-domain approaches have successfully replaced the time-frequency domain with latent sequence feature from a learnable encoder. Conventionally, the feature is separated into speaker-specific ones at the final stage…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-01 Ui-Hyeop Shin , Sangyoun Lee , Taehan Kim , Hyung-Min Park
‹ Prev 1 8 9 10 Next ›