shun60s Goto Github PK

followers: 10.0 following: 0.0 repos: 61.0 gists: 0.0

Name: ISI SHUN

Type: User

Bio: Python, Deep learning, and signal processing

Location: Japan

Blog: https://shun60s.github.io/

ISI SHUN's Projects

read-apache-log

Apache のログファイルを読み込んで、指定した特定のURLアドレスだけの情報を、csvファイルに書き出す。

rpi-i2c-readwrite

A primitive C source code to read/write multibyte data by I2C for Raspberry Pi 1

rt-wdf_renderer-sample-study

Wave Digital Filterを使った真空管回路のシュミレーションの勉強用。

shun60s.github.io

ディープラーニングと、オーディオや音声の信号処理のページ。

softmax-index-weighted

Chainerを使った自作の損失関数の実装

spectral-subtraction

This is a simple python code of spectral subtraction.

spectrogram2

This is an example of multiple sound sources spectrogram and clarity deteriorated one via sound path.

spectrogram_autoencoder

メル尺度のスぺクトログラムの作成、オートエンコーダによる事前学習、などの学習練習用。

time-difference-webapp

Web App, load a wav file and estimate L signal and R signal difference time of the wav file

tube-model-gui

A GUI to control three tube resonance model via tkinter.

vocal-tube-estimation

A trial estimation of vocal tract as simple tube model

vocal-tube-estimation2

Estimation of vocal tract tube resonance model from peak frequency, two three four and five tube.

vocal-tube-estimation3

Estimation vocal tract four tube resonance model length and area about japanese vowels.

vocal-tube-i-model

generate vowel /i/ sound by two tubes model and noise source

vocal-tube-model

a very simple vocal tract model, few tube model. generate vowel sound by it

vocal-tube-model2

Python Class to calculate frequecny response and process reflection transmission upto vocal tract 5 tube resonance model.

vocal-tube-n-model

generate nasal voice /na/ /ma/ sound by two tubes model and nasal effect source

vocal-tube-noise-k-model

generate plosive voice /ga/ /ka/ sound by pseudo blast impulse, noise source, and two tubes model

vocal-tube-noise-s-model

generate fricative voice /sa/ sound by two tubes model and noise source

vocal-tube-t

This is an experiment of 3-way junction model, T Three Tube Mode.

voice-bpf-bank

Band Pass Filter bank and its application to voice sound analysis

wave-dnn

音声認識エンジンJuliusのディクテーションキットに含まれるDNNを利用するための特徴量FBANK_D_A_Zを計算するpython

wave-dnn-likelihood

音声認識エンジンJuliusのディクテーションキットに含まれるDNN-HMMモデルを利用して対数尤度を計算するpython

wavegan-clone

Cloned from chrisdonahue/wavegan, try to learn GAN synthesize.

wavelet-noise-reduction

A simple example of wav signal noise reduction using Wavelet (Daubechies) transform

world-models-clone

Cloned from ctallec/world-models (pytorch implementation) and change to run on windows.

yolo-spectrogram-darknet-clone

Cloned from AlexeyAB/darknet, try to a spectrogram detector.

shun60s Goto Github PK

ISI SHUN's Projects

Recommend Projects

Recommend Topics

Recommend Org