Themos Stafylakis's repositories
Lipreading-ResNet
Torch code for using Residual Networks with LSTMs for Lipreading
Speaker-Embeddings-Correlation-Pooling
Original implementation of the pooling method introduced in "Speaker embeddings by modeling channel-wise correlations"
s3prl_correlation
Self-Supervised Speech Pre-training and Representation Learning Toolkit.
A-Simple-Baseline-For-Knowledge-Based-VQA
Repo for the EMNLP 2023 paper "A Simple Knowledge-Based Visual Question Answering"
Language:Python000
Language:PythonApache-2.0000
deep-clustering
A tensorflow implementation for Deep clustering: Discriminative embeddings for segmentation and separation
Language:Python000
end-to-end-lipreading
Pytorch code for End-to-End Audiovisual Speech Recognition
Language:Python000
GHR
Capturing Conversational Interaction for Question Answering via Global History Reasoning (Qian et al., NAACL findings 2022)
Language:PythonMIT000