Cheng-I Jeff Lai

Contrastive-Predictive-Coding-PyTorch. Contrastive Predictive Coding for Automatic Speaker Verification

pytorch-kaldi-neural-speaker-embeddings. A light weight neural speaker embeddings extraction based on Kaldi and PyTorch.

ASSERT. JHU's system submission to the ASVspoof 2019 Challenge: Anti-Spoofing with Squeeze-Excitation and Residual neTworks (ASSERT).

Attentive-Filtering-Network. University of Edinbrugh-Johns Hopkins University's system for ASVspoof 2017 Version 2.0 dataset.

Unsupervised-TTS. Python

Semi-Supervsied-Spoken-Language-Understanding-PyTorch. Semi-supervised spoken language understanding (SLU) via self-supervised speech and language model pretraining

PARP-wav2vec-PyTorch. Python

LSTM. Voice activity detection of noisy speech files with LSTM. LSTM is implemented with Keras. Data processing is done with Python, MATLAB, and Bash. Experiments are done on Johns Hopkins CLSP GPUs.

scale. Some of my public work at https://hltcoe.jhu.edu/research/scale/scale-2017/

mfcc. Steps to extract mfcc features from audios

intro-machine-learning-paper. Paper I have read for understanding statistical machine learning and speaker recognition

noise_cancellation. Noise cancellation system for speech files with different kinds of noise.

Intro_Mechatronics. Introduction to Mechatronics (EN.520.240) is an introductory robotic course I took in Fall 2016 at Johns Hopkins University. The course consists of 7 labs and a final project, and each one builds up to the next one. The codes are written for Arduino, and each subfile corresponds to a lab.

LDA. An implementation of Linear Discriminant Analysis on multi-class speaker recognition.

VGNSL. [ACL 2019] Visually Grounded Neural Syntax Acquisition

lexicon-learner. Python

TTS-Pruning-Pytorch. Python