Using more informative posterior probabilities for speech recognition
Publications associées (32)
Graph Chatbot
Chattez avec Graph Search
Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.
AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.
Information collected through sensor measurements has the potential to improve knowledge of complex-system behavior, leading to better decisions related to system management. In this situation, and particularly when using digital twins, the quality of sens ...
Natural language processing has experienced significant improvements with the development of Transformer-based models, which employ self-attention mechanism and pre-training strategies. However, these models still present several obstacles. A notable issue ...
Natural language processing and other artificial intelligence fields have witnessed impressive progress over the past decade. Although some of this progress is due to algorithmic advances in deep learning, the majority has arguably been enabled by scaling ...
In certain cases of astronomical data analysis, the meaningful physical quantity to extract is the ratio R between two data sets. Examples include the lensing ratio, the interloper rate in spectroscopic redshift samples, and the decay rate of gravitational ...
In light of steady progress in machine learning, automatic speech recognition (ASR) is entering more and more areas of our daily life, but people with dysarthria and other speech pathologies are left behind. Their voices are underrepresented in the trainin ...
In this dissertation, we propose multiple methods to improve transfer learning for pretrained language models (PLMs). Broadly, transfer learning is a powerful technique in natural language processing, where a language model is first pre-trained on a data-r ...
Dense image-based prediction methods have advanced tremendously in recent years. Their remarkable development has been possible due to the ample availability of real-world imagery. While these methods work well on photographs, their abilities do not genera ...
Self-supervised learning (SSL) models use only the intrinsic structure of a given signal, independent of its acoustic domain, to extract essential information from the input to an embedding space. This implies that the utility of such representations is no ...
Biological motor control is versatile, efficient, and depends on proprioceptive feedback. Muscles are flexible and undergo continuous changes, requiring distributed adaptive control mechanisms that continuously account for the body's state. The canonical r ...
This thesis focuses on two selected learning problems: 1) statistical inference on graphs models, and, 2) gradient descent on neural networks, with the common objective of defining and analysing the measures that characterize the fundamental limits.In the ...