syfengcuhk
Postdoc Delft University of Technology, Ph.D. Chinese University of Hong kong, Automatic speech recognition researcher
Delft, The Netherlands
Pinned Repositories
abkhazia
ABX and kaldi experiments on speech corpora made easy
abnet
ABNet is a "same/different"-based loss trained neural net.
ABXpy
ABX discrimination task in python
Autoregressive-Predictive-Coding
Autoregressive Predictive Coding: An unsupervised autoregressive model for speech representation learning
beer
Bayesian spEEch Recognizer
CPC_audio
An implementation of the Contrast Predictive Coding (CPC) method to train audio features in an unsupervised fashion.
espnet
End-to-End Speech Processing Toolkit
jasmin
Jasmin corpus is a spoken Dutch corpus containing children, elderly and non-native Dutch speakers. In this repo we benchmark a standard Dutch ASR system (on CGN) in various types of speech in Jasmin
kaldi
This is now the official location of the Kaldi project.
mboshi
syfengcuhk's Repositories
syfengcuhk/zerospeech2017_surprise
Zero Speech Challenge 2017 Surprise Dataset and Evaluation
syfengcuhk/zerospeech2017
All you need to get started for the Zero Speech Challenge 2017
syfengcuhk/siyuan
syfengcuhk/recipe_swbd_wordembeds
syfengcuhk/speech_correspondence
Correspondence and autoencoder neural network training for speech using Pylearn2.
syfengcuhk/ZRTools
Zero-Resource Speech Discovery, Search, and Evaluation Tools
syfengcuhk/abnet
ABNet is a "same/different"-based loss trained neural net.