Search Results for author:
Found 11 papers, 6 papers with code
Improved Visually Prompted Keyword Localisation in Real Low-Resource Settings
On English, this results in only a small drop in performance.
Visually Grounded Speech Models for Low-resource Languages and Cognitive Modelling
This dissertation examines visually grounded speech (VGS) models that learn from unlabelled speech paired with images.
Visually Grounded Speech Models have a Mutual Exclusivity Bias
To simulate prior acoustic and visual knowledge, we experiment with several initialisation strategies using pretrained speech and vision networks.
Visually grounded few-shot word learning in low-resource settings
We propose an approach that can work on natural word-image pairs but with less examples, i. e. fewer shots, and then illustrate how this approach can be applied for multimodal few-shot learning in a real low-resource language, Yor\`ub\'a.
Visually grounded few-shot word acquisition with fewer shots
Our approach involves using the given word-image example pairs to mine new unsupervised word-image training pairs from large collections of unlabelled speech and images.
Towards visually prompted keyword localisation for zero-resource spoken languages
We formalise this task and call it visually prompted keyword localisation (VPKL): given an image of a keyword, detect and predict where in an utterance the keyword occurs.
Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing
In this paper, we first show that the per-utterance mean of CPC features captures speaker information to a large extent.
Direct multimodal few-shot learning of speech and images
We propose direct multimodal few-shot models that learn a shared embedding space of spoken words and images from only a few paired examples.
Unsupervised vs. transfer learning for multimodal one-shot matching of speech and images
Here we compare transfer learning to unsupervised models trained on unlabelled in-domain data.
Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challenge
The idea is to learn a representation of speech by predicting future acoustic units.
Ranked #1 on
Voice Conversion
on ZeroSpeech 2019 English
(using extra training data)
Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks
For our submission to the ZeroSpeech 2019 challenge, we apply discrete latent-variable neural networks to unlabelled speech and use the discovered units for speech synthesis.
