jefflai108
Ph.D. Student at MIT. Interested in self-supervised learning, spoken language acquisition, and audio-visual learning.
Cambridge, MA
Pinned Repositories
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.
Contrastive-Predictive-Coding-PyTorch
Contrastive Predictive Coding for Automatic Speaker Verification
intro-machine-learning-paper
Paper I have read for understanding statistical machine learning and speaker recognition
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.
PARP-wav2vec-PyTorch
pytorch-kaldi-neural-speaker-embeddings
A light weight neural speaker embeddings extraction based on Kaldi and PyTorch.
scale
Some of my public work at https://hltcoe.jhu.edu/research/scale/scale-2017/
Semi-Supervsied-Spoken-Language-Understanding-PyTorch
Semi-supervised spoken language understanding (SLU) via self-supervised speech and language model pretraining
Unsupervised-TTS
jefflai108's Repositories
jefflai108/Contrastive-Predictive-Coding-PyTorch
Contrastive Predictive Coding for Automatic Speaker Verification
jefflai108/pytorch-kaldi-neural-speaker-embeddings
A light weight neural speaker embeddings extraction based on Kaldi and PyTorch.
jefflai108/ASSERT
JHU's system submission to the ASVspoof 2019 Challenge: Anti-Spoofing with Squeeze-Excitation and Residual neTworks (ASSERT).
jefflai108/Attentive-Filtering-Network
University of Edinbrugh-Johns Hopkins University's system for ASVspoof 2017 Version 2.0 dataset.
jefflai108/Unsupervised-TTS
jefflai108/Semi-Supervsied-Spoken-Language-Understanding-PyTorch
Semi-supervised spoken language understanding (SLU) via self-supervised speech and language model pretraining
jefflai108/PARP-wav2vec-PyTorch
jefflai108/lexicon-learner
jefflai108/TTS-Pruning-Pytorch
jefflai108/VGNSL
[ACL 2019] Visually Grounded Neural Syntax Acquisition
jefflai108/6.864-final
jefflai108/AV-NSL
jefflai108/axlearn
jefflai108/DIM
Deep InfoMax (DIM), or "Learning Deep Representations by Mutual Information Estimation and Maximization"
jefflai108/espnet
End-to-End Speech Processing Toolkit
jefflai108/fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
jefflai108/fairseq-ust
jefflai108/jefflai108.github.io
jefflai108/joint-segmentation
jefflai108/OpenNMT-py
Open Source Neural Machine Translation in PyTorch
jefflai108/PPLM
Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.
jefflai108/pytorch_GAN_zoo
A mix of GAN implementations including progressive growing
jefflai108/PytorchWaveNetVocoder
WaveNet-Vocoder implementation with pytorch
jefflai108/self-attention-tacotron
An implementation of "Investigation of enhanced Tacotron text-to-speech synthesis systems with self-attention for pitch accent language" https://arxiv.org/abs/1810.11960
jefflai108/Self-Supervised-Speech-Pretraining-and-Representation-Learning
The S3PRL speech toolkit: self-supervised pre-training and representation learning of Mockingjay, TERA, A-ALBERT, APC, and more to come. With easy-to-use standard downstream evaluation scripts including phone classification, speaker recognition, and ASR. (All in Pytorch!)
jefflai108/speeech-instruction-following
jefflai108/tacotron2
An implementation of Tacotron and Tacotron2
jefflai108/tf-kaldi-speaker
Neural speaker recognition/verification system based on Kaldi and Tensorflow
jefflai108/unit_info_align
jefflai108/word-codebook-learning