SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model, Accepted to IEEE SLT 2022
-
Updated
Nov 25, 2022 - Python
#
visually-grounded-speech
Here are 6 public repositories matching this topic...
SpeechCLIP+: Self-supervised multi-task representation learning for speech via CLIP and speech-image data. Accepted to ICASSP 2024, Self-supervision in Audio, Speech, and Beyond (SASB) workshop.
-
Updated
Apr 9, 2024 - Python
Baselines for the Zero-Resources Speech Challenge using VisuallyGrounded Models of Spoken Language, 2021 edition
challenge deep-neural-networks pytorch representation-learning speech-processing weakly-supervised-learning multimodal-learning librispeech visually-grounded-speech spokencoco
-
Updated
Jun 1, 2021 - Python
Library for training visually-grounded models of spoken language understanding.
deep-neural-networks pytorch speech-processing weakly-supervised-learning multimodal-learning spoken-language-understanding multi-tasking visually-grounded-speech flickr8k spokencoco
-
Updated
Apr 13, 2022 - Python
Code for the paper "Textual supervision for visually grounded spoken language understanding".
-
Updated
Oct 12, 2021 - Python
Code used in my Master's thesis
-
Updated
May 28, 2020 - Python
Add this topic to your repo
To associate your repository with the visually-grounded-speech topic, visit your repo's landing page and select "manage topics."