Trending Research
I Learn to Diffuse, or Data Alchemy 101: a Mnemonic Manifesto
In this manifesto, we put forward the idea of data alchemy as a narrative device to discuss storytelling and transdisciplinarity in visualization.
Human-Computer Interaction
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
Several recent end-to-end text-to-speech (TTS) models enabling single-stage training and parallel sampling have been proposed, but their sample quality does not match that of two-stage TTS systems.
Sound Audio and Speech Processing
Million.js: A Fast, Compiler-Augmented Virtual DOM for Performant JavaScript UI Libraries
The need for developing and delivering interactive web applications has grown rapidly.
Human-Computer Interaction
Simple deterministic O(n log n) algorithm finding a solution of Erdős-Ginzburg-Ziv theorem
Erd\H{o}s-Ginzburg-Ziv theorem is a famous theorem in additive number theory, which states any sequence of $2n-1$ integers contains a subsequence of $n$ elements, with their sum being a multiple of $n$.
Data Structures and Algorithms Combinatorics
Pulsar: Efficient Sphere-based Neural Rendering
facebookresearch/pytorch3d
•
•
CVPR 2021
To alleviate these problems, Pulsar employs: 1) a sphere-based scene representation, 2) an efficient differentiable rendering engine, and 3) neural shading.
Graphics
Daft-Exprt: Cross-Speaker Prosody Transfer on Any Text for Expressive Speech Synthesis
ubisoft/ubisoft-laforge-daft-exprt
•
•
This paper presents Daft-Exprt, a multi-speaker acoustic model advancing the state-of-the-art for cross-speaker prosody transfer on any text.
Sound Audio and Speech Processing
Augmenting Decompiler Output with Learned Variable Names and Types
CMUSTRUDEL/DIRTY
•
•
A common tool used by security professionals for reverse-engineering binaries found in the wild is the decompiler.
Software Engineering Programming Languages
Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speech
PaddlePaddle/PaddleSpeech
•
•
Interspeech2020 2020
In this paper, we propose multi-band MelGAN, a much faster waveform generation model targeting to high-quality text-to-speech.
Sound Audio and Speech Processing
DDSP-based Singing Vocoders: A New Subtractive-based Synthesizer and A Comprehensive Evaluation
yatingmusic/ddsp-singing-vocoders
•
•
A vocoder is a conditional audio generation model that converts acoustic features such as mel-spectrograms into waveforms.
Sound Audio and Speech Processing
AirGuard -- Protecting Android Users From Stalking Attacks By Apple Find My Devices
Finder networks in general, and Apple's Find My network in particular, can pose a grave threat to users' privacy and even health if these networks are abused for stalking.
Cryptography and Security Computers and Society
