darlingwu Goto Github PK

2.5d-visual-sound

2.5D visual sound

adversarial

Code and hyperparameters for the paper "Generative Adversarial Networks"

apkit

Audio Processing Kit -- a python library

asteroid

The PyTorch-based audio source separation toolkit for researchers || Pretrained models available

attention-is-all-you-need-pytorch

A PyTorch implementation of the Transformer model in "Attention is All You Need".

audio_visual_speech_enhancement

Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments

autoencoder-speech-compression

Code for "End-to-End Optimized Speech Coding with Deep Neural Networks" (ICASSP 2018)

av3t

Impementation of "Multi-speaker tracking from an audio-visual sensing device" - IEEE Transactions on Multimedia,

bazel

a fast, scalable, multi-language and extensible build system

berkeley-stat-157

Homepage for STAT 157 at UC Berkeley

chrome-media-audio-papers

Audio samples from research projects done by the Chrome Media Audio group

codec2

Open source speech codec designed for communications quality speech between 450 and 3200 bit/s. The main application is low bandwidth HF/VHF digital radio.

communitydetection

Implements of community detection algorithms

conv-tasnet

conv-tasnet-1

Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation Pytorch's Implement

coursera-ml-andrewng-notes

吴恩达老师的机器学习课程个人笔记

cover-letter-latex

A cover letter template for a journal paper submission in Latex

deep-casa

Tensorflow implementation of deep CASA

deep-encoder-decoder-conv-tasnet

A PyTorch implementation of " AN EMPIRICAL STUDY OF CONV-TASNET "

deep_lip_reading

Code and models for evaluating a state-of-the-art lip reading network

deeplearning_wavelet-lstm

LSTM + Wavelet（长短期记忆神经网络+小波分析）：深度学习与数字信号处理的结合

deeplearningbook-chinese

Deep Learning Book Chinese Translation

deeplearningufldl

Exercises of deep learning tutorial from Stanford University

densenet

Densely Connected Convolutional Networks, In CVPR 2017 (Best Paper Award).

distil-whisper

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

easyaacencoder

开源项目：简单、高效、稳定的开源音频编码库，支持将各种音频数据(G.711A/PCMA、G.711U/PCMU、G726、PCM)转码成AAC(with adts)格式，其中aac编码部分采用的是业界公认的faac库，EasyAACEncoder支持Windows、Linux、ARM等多种平台，能够广泛应用于各种移动终端设备、嵌入式设备和流媒体转码服务器！

efficient_densenet_pytorch

A memory-efficient implementation of DenseNets

efficient_neural_audio_synthesis

A Tensorflow implementation of WaveRNN

espnet

End-to-End Speech Processing Toolkit

expressive-resume

A beautiful resume/cover letter LaTeX template pair that are extraordinarily easy to use.