wnhsu

FactorizedHierarchicalVAE

This repository contains the code to reproduce the core results from the paper "Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data"

ScalableFHVAE

This repository contains the code to reproduce the core results from the paper "Scalable Factorized Hierarchical Variational Autoencoders"

SpeechVAE

This repository contains the code to reproduce the core results from the paper "Learning Latent Representations for Speech Generation and Transformation".

ResDAVEnet-VQ

Official codes for the paper "Learning Hierarchical Discrete Linguistic Units from Visually-Grounded Speech"

ReVISE

ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement

PGLSTM_ASR

This repo contains codes to reproduce the core results of "A Prioritized Grid Long Short-Term Memory RNN for Speech Recognition"

semi-supervised-pytorch

Implementations of different VAE-based semi-supervised and generative models in PyTorch

tensorflow-wavenet

A TensorFlow implementation of DeepMind's WaveNet paper

tacotron2_dev

wavenet_vocoder

WaveNet vocoder

ZeroSpeech2019_RLE_eval

ZeroSpeech 2019 evaluation with run-length encoding (RLE), metrics reported in ResDAVEnet-VQ.

a-PyTorch-Tutorial-to-Image-Captioning

Show, Attend, and Tell | a PyTorch Tutorial to Image Captioning

ABXpy

ABX discrimination task in python

CNTK

Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit

einops

Deep learning operations reinvented (for pytorch, tensorflow, jax and others)

espnet_tts_frontend

Text frontend for ESPnet tts recipes

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

image-to-speech-demo

kaldi

kaldi-asr/kaldi is the official location of the Kaldi project.

show-attend-and-tell

TensorFlow Implementation of "Show, Attend and Tell"

wav2letter

Facebook AI Research's Automatic Speech Recognition Toolkit

wnhsu.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes