๐Ÿฟ๏ธ ScourBrowse
LoginSign Up
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
๐Ÿ‘‚ Psychoacoustic Coding

Perceptual Audio, Masking Models, Hearing Science, Lossy Compression

Comp-X: On Defining an Interactive Learned Image Compression Paradigm With Expert-driven LLM Agent
arxiv.orgยท1d
๐Ÿง Neural Compression
These Popular Noise-Canceling Headphones Are at Their Lowest Price Ever
lifehacker.comยท1d
๐Ÿ‘๏ธPerceptual Coding
Show HN: A short story on developing a long-context World-Model with no money
francesco215.github.ioยท14hยท
Discuss: Hacker News
๐Ÿง Learned Codecs
FFmpeg 8.0 Released
ffmpeg.orgยท5hยท
Discuss: Hacker News
๐ŸŽฌAV1 Encoding
A universal rhythm guides how we speak: Global analysis reveals 1.6-second 'intonation units'
phys.orgยท2d
๐Ÿ—ฃ๏ธCMU Pronouncing
Deep Dive: OpenAI's GPT-OSS
dev.toยท5hยท
Discuss: DEV
๐Ÿ“ŠQuantization
Powerful new book explores how noise has taken over the world
newscientist.comยท2d
๐ŸŽตMusic Universality
Voice Changing Sound Recorder
hackster.ioยท2d
๐Ÿ“ผTape Simulation
Denoising by neural network for muzzle blast detection
arxiv.orgยท1d
๐ŸŒŠDigital Signal Processing
Deep Equilibrium Convolutional Sparse Coding for Hyperspectral Image Denoising
arxiv.orgยท1d
๐Ÿง Neural Codecs
Shotcut is a free and open-source video editor, available for all major platforms
techspot.comยท13h
๐ŸŽฌVideo Codecs
I test audio kit for a living, and these earbuds' death-proof battery and regal design blew me away
techradar.comยท11m
๐Ÿ’ฟFLAC Archaeology
Cracking the Density Code: Why MAF Flows Where KDE Stalls
towardsdatascience.comยท16h
๐Ÿ”—Tailscale
Unplug and Play Language Models: Decomposing Experts in Language Models at Inference Time
arxiv.orgยท1d
๐Ÿง Intelligence Compression
BioSonix: Can Physics-Based Sonification Perceptualize Tissue Deformations From Tool Interactions?
arxiv.orgยท2d
๐Ÿ—ฃ๏ธCMU Pronouncing
Stabilization of Perturbed Loss Function: Differential Privacy without Gradient Noise
arxiv.orgยท1d
๐Ÿง Machine Learning
EmoSLLM: Parameter-Efficient Adaptation of LLMs for Speech Emotion Recognition
arxiv.orgยท2d
๐ŸŽตAudio ML
Compute Where It Counts: a trainable LLM sparsity enabling 4x CPU speed
crystalai.orgยท2dยท
Discuss: Hacker News
๐ŸŒŠStreaming Algorithms
A comparative study of some wavelet and sampling operators on various features of an image
arxiv.orgยท2d
๐ŸŒ€Fractal Compression
What Hugging Face reveals about the data economy of fine-tuning
research.portexai.comยท17hยท
Discuss: Hacker News
๐ŸŒ€Brotli Internals
Loading...Loading more...
AboutBlogChangelogRoadmap