suldier Goto Github PK

asr_syllable

采用音节建模构建语音识别声学模型

asr_word

采用端到端方法构建声学模型，以字为建模单元，采用DCNN-CTC网络结构。

asrt_speechrecognition

A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统

athena

an open-source implementation of sequence-to-sequence based speech processing engine

audiotsm

A python library for real-time audio time-scale modification procedures

biaxial-rnn-music-composition

A recurrent neural network designed to generate classical music.

caffe-cvprw15

:heart::coffee: Deep Learning of Binary Hash Codes for Fast Image Retrieval (CVPRW15)

chord-recognition

Automatic chord recognition with PCP/EPCP

codingmath

Tech

coursera-ml-andrewng-notes

dc_tts

A TensorFlow Implementation of DC-TTS: yet another text-to-speech model

deepspeech

A TensorFlow implementation of Baidu's DeepSpeech architecture

dtw

DTW (Dynamic Time Warping) python module

dualsc

eesen

The official repository of the Eesen project

eesen-for-thchs30

ASR for Chinese Mandarin

expressive_tacotron

Tensorflow Implementation of Expressive Tacotron

fast-wavenet

Speedy Wavenet generation using dynamic programming :zap:

fastdtw

A Python implementation of FastDTW

faust

Functional programming language for signal processing and sound synthesis

flowavenet

A Pytorch implementation of "FloWaveNet: A Generative Flow for Raw Audio"

gantts

PyTorch implementation of GAN-based text-to-speech synthesis and voice conversion (VC)

gcot

Graph Convolutional Optimal Transport for Hyperspectral Image Spectral Clustering

graph-based-nn

Graph Convolutional Networks (GCNs)

improved_wgan_training

Code for reproducing experiments in "Improved Training of Wasserstein GANs"

intro2musictech

公众号“无痛入门音乐科技”开源代码

kaldi

This is now the official location of the Kaldi project.

kaldi-python

Python wrappers for Kaldi data

laplacian_segmentation

graph laplacian song segmentation

librosa

Python library for audio and music analysis