bingo-todd Goto Github PK

ams

amplitude modulation spectrum

auditory_segmentation

awesome-english-ebooks

经济学人(含音频)、纽约客、卫报、连线、大西洋月刊等英语杂志免费下载,支持epub、mobi、pdf格式, 每周更新

basictools

collections of basic tools

bi-lstm-crf-ner-tf2.0

Named Entity Recognition (NER) task using Bi-LSTM-CRF model implemented in Tensorflow 2.0(tensorflow2.0 +)

bianural-cues

python code for binaural cues(ITD,ILD) calculation

binaurallocalizationcnn

Code to create networks that localize sounds sources in 3D environments

bingo-todd.github.io

pages

blindestrt

blindrt

Blind Estimation of Reveberation Time from speech and music

conv-tasnet-for-speech-enchancement-and-seperation

The state-of-art time domain network for speech separation, and it performs well on speech enhancement and music separation

dnn_binaural_localization

binaural sound localization, DNN model with feature of GCC-PHAT

gammatone-filters

Python implementation of Gammatone filter

gcc-phat_dnn_loc

DNN based binaural sound localization model, using GCC-PHAT as features

gmm_localize

gmms

Gaussian Mixture Mode written in Python

icassp-latex-template

ICASSP latex template (2021)

jekyll-theme-prologue

A Jekyll version of the "Prologue" theme by HTML5 UP

loctools

magenta

Magenta: Music and Art Generation with Machine Intelligence

mvdr-beamformer

MVDR beamformer written in python

preprint-template.tex

A template for two-column scientific preprints

pysofa

Python API for SOFA (Spatially Oriented Format for Acoustics)

rasta-plp

Relative Spectral Transform-Perceptual Linear Prediction

rir_simulator_python

Room impulse response simulator using python

roomsim_campbell

Roomsim_Campbell

roomsimulator

sparse-nmf

svoice

We provide a PyTorch implementation of the paper Voice Separation with an Unknown Number of Multiple Speakers In which, we present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for every number of possible speakers, and the model with the largest number of speakers is employed to select the actual number of speakers in a given sample. Our method greatly outperforms the current state of the art, which, as we show, is not competitive for more than two speakers.

tasnet

Time-domain Audio Separation Network (IN PYTORCH)