Publication

A Generalized Dynamic Composition Algorithm of Weighted Finite State Transducers for Large Vocabulary Speech Recognition

Publications associées (21)

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.

Connectez-vous pour utiliser Chat avec Graph Search

TFHE: Fast Fully Homomorphic Encryption Over the Torus

This work describes a fast fully homomorphic encryption scheme over the torus (TFHE) that revisits, generalizes and improves the fully homomorphic encryption (FHE) based on GSW and its ring variants. The simplest FHE schemes consist in bootstrapped binary ...

SPRINGER2020

Measuring and Synthesizing Systems in Probabilistic Environments

Barbara Jobstmann, Rishabh Singh

The traditional synthesis question given a specification asks for the automatic construction of a system that satisfies the specification, whereas often there exists a preference order among the different systems that satisfy the given specification. Under ...

Assoc Computing Machinery2015

The Kaldi Speech Recognition Toolkit

Petr Motlicek

We describe the design of Kaldi, a free, open-source toolkit for speech recognition research. Kaldi provides a speech recognition system based on finite-state automata (using the freely available OpenFst), together with detailed documentation and a compreh ...

Idiap2012

Conversion of Recurrent Neural Network Language Models to Weighted Finite State Transducers for Automatic Speech Recognition

Petr Motlicek

Recurrent neural network language models (RNNLMs) have recently shown to outperform the venerable n-gram language models (LMs). However, in automatic speech recognition (ASR), RNNLMs were not yet used to directly decode a speech signal. Instead, RNNLMs are ...

2012

Conversion of Recurrent Neural Network Language Models to Weighted Finite State Transducers for Automatic Speech Recognition

Petr Motlicek

Idiap2012

Control design for specifications on stochastic hybrid systems

Maryam Kamgarpour

We synthesize controllers for discrete-time stochastic hybrid systems such that the probability of satisfying a given specification on the system is maximized. The specifications are defined with finite state automata. It is shown that automata satisfactio ...

2012

The Kaldi Speech Recognition Toolkit

Petr Motlicek

We describe the design of Kaldi, a free, open-source toolkit for speech recognition research. Kaldi provides a speech recognition system based on finite-state transducers (using the freely available OpenFst), together with detailed documentation and script ...

IEEE Signal Processing Society2011

Quantitative Languages

Laurent Doyen

Quantitative generalizations of classical languages, which assign to each word a real number instead of a Boolean value, have applications in modeling resource-constrained computation. We use weighted automata (finite automata with transition weights) to d ...

2010

Expressiveness And Closure Properties For Quantitative Languages

Laurent Doyen

Weighted automata are nondeterministic automata with numerical weights on transitions. They can define quantitative languages L that assign to each word w a real number L(w). In the case of infinite words, the value of a run is naturally computed as the ma ...

2010