In-Context Phone Posteriors as Complementary Features for Tandem ASR
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.
Probabilistic parameter estimation in model fitting runs the gamut from maximum likelihood or maximum a posteriori point estimates from optimization to Markov Chain Monte Carlo (MCMC) sampling. The latter, while more computationally intensive, generally pr ...
SPRINGER INTERNATIONAL PUBLISHING AG2019
State-of-the-art automatic speech recognition (ASR) and text-to-speech systems require a pronunciation lexicon that maps each word to a sequence of phones. Manual development of lexicons is costly as it needs linguistic knowledge and human expertise. To fa ...
EPFL2017
Speaker diarization is the task of identifying ``who spoke when'' in an audio stream containing multiple speakers. This is an unsupervised task as there is no a priori information about the speakers. Diagnostical studies on state-of-the-art diarization sys ...
We prove the special termination for log canonical pairs and its generalisation in the context of generalised pairs. ...
Somerville2023
The public program in the context of Bianca Baldi’s solo exhibition deals with perspectives on the colonial image archive and asks for the potential of a critical redesign. On November 5 and 6, the invited artists and scholars will introduce alternative na ...
2022
,
IRGC’s guidelines for the governance of systemic risks addresses the question of how to deal with systemic risks in the context of system transitions, i.e., in situations that require adaptation to new context conditions or transformation of an organisatio ...
International Risk Governance Center (IRGC)2018
,
Model-based approaches to Speaker Verification (SV), such as Joint Factor Analysis (JFA), i-vector and relevance Maximum-a-Posteriori (MAP), have shown to provide state-of-the-art performance for text-dependent systems with fixed phrases. The performance o ...
Ieee2017
, ,
One of the reasons sentiment lexicons do not reach human-level performance is that they lack the contexts that define the polarities of words. While obtaining this knowledge through machine learning would require huge amounts of data, context is commonsens ...
Springer-Verlag Berlin2014
With an ever-growing amount of data generated on the web, aggregating information from the crowd into meaningful knowledge has become crucial to companies in order to create a competitive edge. Not only companies, but also organizations and governments can ...
EPFL2014
, ,
Vision scientists have attempted to classify visual illusions according to certain aspects, such as brightness or spatial features. For example, Piaget proposed that visual illusion magnitudes either decrease or increase with age. Subsequently, it was sugg ...
