yusunnny
Follow
Stars
Implementation of Band Split Roformer, SOTA Attention network for music source separation out of ByteDance AI Labs
Ambiscaper: a tool for automatic dataset generation and annotation of reverberant Ambisonics audio. Originally forked from http:https://github.com/justinsalamon/scaper
Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch
Generic PyTorch dataset implementation to load and augment VIDEOS for deep learning training loops.
Unsupervised domain adaptation for conversational speech enhancement using RemixIT
Code for the paper: "Unsupervised Deep Clustering for Source Separation: Direct Learning from Mixtures using Spatial Information"
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
AD-YOLO: You Look Only Once in Training Multiple Sound Event Localization and Detection, ICASSP 2023
This is an official implementation of CvT: Introducing Convolutions to Vision Transformers.
CMT: Convolutional Neural Networks Meet Vision Transformers
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
Reformer, the efficient Transformer, in Pytorch
Implementation of the paper "Attentive Statistics Pooling for Deep Speaker Embedding" in Pytorch
Datasets, Transforms and Models specific to Computer Vision
This is the public repository for eigenvector-based SALSA features for polyphonic sound event localization and detection.
My system for the DCASE 2022 Task 3 Sound Event Localizaiton and Detection.
Example MATLAB/Octave scripts to perform ambisonic encoding of microphone array signals
Pytorch implemenation of "Learning Filter Basis for Convolutional Neural Network Compression" ICCV2019
A Repository of Room Responses and 360 Videos of a Variable Acoustics Lab
PyTorch implementations of several SOTA backbone deep neural networks (such as ResNet, ResNeXt, RegNet) on one-dimensional (1D) signal/time-series data.