chochobo's repositories
Wavenet-demo
A TensorFlow implementation for Chinese speech recognition based on DeepMind's WaveNet
amazfit-bip-kr
Amazfit Bip Korean Firmware and tools for making it
capsule_networks
This is the code for "Capsule Networks: An Improvement to Convolutional Networks" by Siraj Raval on Youtube
ConvolutionaNeuralNetworksToEnhanceCodedSpeech
In this work we propose two postprocessing approaches applying convolutional neural networks (CNNs) either in the time domain or the cepstral domain to enhance the coded speech without any modification of the codecs. The time domain approach follows an end-to-end fashion, while the cepstral domain approach uses analysis-synthesis with cepstral domain features. The proposed postprocessors in both domains are evaluated for various narrowband and wideband speech codecs in a wide range of conditions. The proposed postprocessor improves speech quality (PESQ) by up to 0.25 MOS-LQO points for G.711, 0.30 points for G.726, 0.82 points for G.722, and 0.26 points for adaptive multirate wideband codec (AMR-WB). In a subjective CCR listening test, the proposed postprocessor on G.711-coded speech exceeds the speech quality of an ITU-T-standardized postfilter by 0.36 CMOS points, and obtains a clear preference of 1.77 CMOS points compared to G.711, even en par with uncoded speech.
dc_tts
A TensorFlow Implementation of DC-TTS: yet another text-to-speech model
dctts-pytorch
The pytorch implementation of DC-TTS
deep-learning-model-convertor
The convertor/conversion of deep learning models for different deep learning frameworks/softwares.
deep-painterly-harmonization
Code and data for paper "Deep Painterly Harmonization": https://arxiv.org/abs/1804.03189
deep-voice-conversion
Deep neural networks for voice conversion (voice style transfer) in Tensorflow
FastPhotoStyle
Style transfer, deep learning, feature transform
handson-ml
A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in python using Scikit-Learn and TensorFlow.
hwplib
hwp library for java
koshort
:cat: koshort is a Python package for Korean internet spoken language crawling and processing... or maybe Korean domestic cat.
machine-learning-tone-generation
Using a GAN to synthesize the sounds of instruments, initially only clarinet
nv-wavenet
Reference implementation of real-time autoregressive wavenet inference
object_detector_app
Real-Time Object Recognition App with Tensorflow and OpenCV
postfilt_gan
This is an implementation of "Generative adversarial network-based postfilter for statistical parametric speech synthesis"
PyTorch-FastCampus
PyTorch로 시작하는 딥러닝 입문 CAMP (2017.7~2017.12) 강의자료
PytorchWaveNetVocoder
WaveNet-Vocoder implementation with pytorch
set-egpu
Display-agnostic acceleration of macOS applications using external GPUs.
SpeechSynthesis
음성합성 관련 자료 모음
SpeechSynthesisSSMLParser
Implement SSML parsing for Web Speech API
Super-SlowMo
An attempt at a PyTorch implimentation of "Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation"
tacotron2
pytorch tacotron2 https://arxiv.org/pdf/1712.05884.pdf
tacotron2-1
Tacotron 2 - PyTorch implementation with faster-than-realtime inference
Voice_Converter_CycleGAN
Voice Converter Using CycleGAN and Non-Parallel Data