paper-with-me

Papers

HARP-Net: Hyper-Autoencoded Reconstruction Propagation for Scalable Neural Audio Coding

2021-07-22 · Darius Petermann, SeungKwon Beack, Minje Kim

An autoencoder-based codec employs quantization to turn its bottleneck layer activation into bitstrings, a process that hinders information flow between the encoder and decoder parts. To circumvent this issue, we employ additional skip connections between the corresponding pair of encoder-decoder layers. The assumption is that, in a mirrored autoencoder topology, a decoder layer reconstructs the intermediate feature representation of its corresponding encoder layer. Hence, any additional information directly propagated from the corresponding encoder layer helps the reconstruction. We implement this kind of skip connections in the form of additional autoencoders, each of which is a small codec that compresses the massive data transfer between the paired encoder-decoder layers. We empirically verify that the proposed hyper-autoencoded architecture improves perceptual audio quality compared to an ordinary autoencoder baseline.

📄 PDF Abstract BibTeX arXiv:2107.10843

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderQuantization

Similar Papers 제목 키워드 기반

Native Multi-Band Audio Coding within Hyper-Autoencoded Reconstruction Propagation Networks

2023-03-14 · Darius Petermann, Inseon Jang, Minje Kim

Spectral sub-bands do not portray the same perceptual relevance. In audio coding, it is therefore desirable to have independent control over each of the constituent bands so that bitrate assignment and signal reconstruct…

Bandwidth Extension

Autoencoded UMAP-Enhanced Clustering for Unsupervised Learning

2025-01-13 · Malihehsadat Chavooshi, Alexander V. Mamonov

We propose a novel approach to unsupervised learning by constructing a non-linear embedding of the data into a low-dimensional space followed by any conventional clustering algorithm. The embedding promotes clusterabilit…

Clustering

Convolutional Signal Propagation: A Simple Scalable Algorithm for Hypergraphs

2024-09-26 · Pavel Procházka, Marek Dědič, Lukáš Bajer

Last decade has seen the emergence of numerous methods for learning on graphs, particularly Graph Neural Networks (GNNs). These methods, however, are often not directly applicable to more complex structures like bipartit…

Node ClassificationRetrieval

Scalable low dimensional manifold model in the reconstruction of noisy and incomplete hyperspectral images

2016-05-18 · Wei Zhu, Zuoqiang Shi, Stanley Osher

We present a scalable low dimensional manifold model for the reconstruction of noisy and incomplete hyperspectral images. The model is based on the observation that the spatial-spectral blocks of a hyperspectral image ty…

HyperbolicDiffusion: Sharp & Scalable Tiled Generation on the Hyperbolic Plane

2026-08-04 · Hugo Caselles-Dupré arxiv

Planar tiled diffusion denoises overlapping windows of one rectangular canvas. The hyperbolic plane has no such canvas, and its area grows exponentially with radius. We introduce HyperbolicDiffusion, a training-free meth…