Pinned Repositories
bajibabu.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
basic
CSTR-Edinburgh.github.io
CSTR-Edinburgh blog
CycleGAN-VC
dash-devdev.github.io
dnn-speech
This ist the repository for the term project Speech Recognition using Deep Neural Networks for the course ELEC-E5510-Speech Recognition
g2p
This folder contains the scripts to train g2p models for Telugu language.
GlottGAN
This repository contains the files used for our Interspeech 2017 paper.
make_full_labels
how to generate the full-contextual labels from un-seen text for the application of HMM-based speech synthesis (HTS)
postfilt_gan
This is an implementation of "Generative adversarial network-based postfilter for statistical parametric speech synthesis"
bajibabu's Repositories
bajibabu/GlottGAN
This repository contains the files used for our Interspeech 2017 paper.
bajibabu/postfilt_gan
This is an implementation of "Generative adversarial network-based postfilter for statistical parametric speech synthesis"
bajibabu/make_full_labels
how to generate the full-contextual labels from un-seen text for the application of HMM-based speech synthesis (HTS)
bajibabu/CycleGAN-VC
bajibabu/bajibabu.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
bajibabu/basic
bajibabu/CSTR-Edinburgh.github.io
CSTR-Edinburgh blog
bajibabu/dash-devdev.github.io
bajibabu/dnn-speech
This ist the repository for the term project Speech Recognition using Deep Neural Networks for the course ELEC-E5510-Speech Recognition
bajibabu/g2p
This folder contains the scripts to train g2p models for Telugu language.
bajibabu/keras-wavenet
Keras implementation of deepmind's wavenet paper
bajibabu/Learn_ML
bajibabu/merlin
This is not the official location of the Merlin project.
bajibabu/PytorchWaveNetVocoder
WaveNet-Vocoder implementation with pytorch
bajibabu/sr_presentation
Speaker recognition using DNNs. This is a course project.
bajibabu/SummerProject2014
This is a web application which makes it easier for the deaf people. This is done under the guidance of Prof. Jonas Beskow in KTH (Centre for Speech Technology)
bajibabu/tacotron
A TensorFlow Implementation of Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model
bajibabu/TTS
Deep learning for Text to Speech
bajibabu/tutorials
bajibabu/Voice_Analysis_Toolkit
A set of Matlab functions for carrying glottal source and voice quality analysis.
bajibabu/wavenet_vocoder
WaveNet vocoder