Publication

Joint Decoding for Phoneme-Grapheme Continuous Speech Recognition

Publications associées (44)

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

Enhanced Phone Posteriors for Improving Speech Recognition Systems

Hervé Bourlard, Hamed Ketabdar

Using phone posterior probabilities has been increasingly explored for improving automatic speech recognition (ASR) systems. In this paper, we propose two approaches for hierarchically enhancing these phone posteriors, by integrating long acoustic context, ...

2010

Approaches to automatic lexicon learning with limited training examples

Pinar Akyazi, Samuel Thomas

Preparation of a lexicon for speech recognition systems can be a significant effort in languages where the written form is not exactly phonetic. On the other hand, in languages where the written form is quite phonetic, some common words are often mispronou ...

IEEE2010

A Kernel Wrapper for Phoneme Sequence Recognition

We describe a kernel wrapper, a Mercer kernel for the task of phoneme sequence recognition which is based on operations with the Gaussian kernel, and suitable for any sequence kernel classifier. We start by presenting a kernel-based algorithm for phoneme s ...

John Wiley and Sons2009

On Joint Modelling of Grapheme and Phoneme Information using KL-HMM for ASR

Hervé Bourlard, Guillermo Aradilla

In this paper, we propose a simple approach to jointly model both grapheme and phoneme information using Kullback-Leibler divergence based HMM (KL-HMM) system. More specifically, graphemes are used as subword units and phoneme posterior probabilities estim ...

Idiap2009

A Proposal for a Kernel-based Algorithm for Large Vocabulary Continuous Speech Recognition

We present a proposal of a kernel-based model for large vocabulary continuous speech recognizer. The continuous speech recognition is described as a problem of finding the best phoneme sequence and its best time span, where the phonemes are generated from ...

John Wiley and Sons2009

Enhancing posterior based speech recognition systems

Hamed Ketabdar

The use of local phoneme posterior probabilities has been increasingly explored for improving speech recognition systems. Hybrid hidden Markov model / artificial neural network (HMM/ANN) and Tandem are the most successful examples of such systems. In this ...

EPFL2008

Enhancing posterior based speech recognition systems

Hamed Ketabdar

Ecole Polytechnique Fédérale de Lausanne2008

Fast Approximate Spoken Term Detection from Sequence of Phonemes

Hynek Hermansky, Joel Praveen Pinto

We investigate the detection of spoken terms in conversational speech using phoneme recognition with the objective of achieving smaller index size as well as faster search speed. Speech is processed and indexed as a sequence of one best phoneme sequence. W ...

2008

Fast Approximate Spoken Term Detection from Sequence of Phonemes

Hynek Hermansky, Joel Praveen Pinto

IDIAP2008

On Confusions in a Phoneme Recognizer

Hynek Hermansky, Joel Praveen Pinto

In this paper, we analyze the confusions patterns at three places in the hybrid phoneme recognition system. The confusions are analyzed at the pronunciation, the posterior probability, and the phoneme recognizer levels. The confusions show significant stru ...

2007