Publications related to On matching data and model in LF-MMI-based dysarthric speech recognition

Model Adaptation for Sentence Unit Segmentation from Speech

The sentence segmentation task is a classification task that aims at inserting sentence boundaries in a sequence of words. One of the applications of sentence segmentation is to detect the sentence boundaries in the sequence of words that is output by an a ...

IDIAP2006

Using auxiliary sources of knowledge for automatic speech recognition

Mathew Magimai Doss

Standard hidden Markov model (HMM) based automatic speech recognition (ASR) systems usually use cepstral features as acoustic observation and phonemes as subword units. Speech signal exhibits wide range of variability such as, due to environmental variatio ...

EPFL2005

Using Auxiliary Sources of Knowledge for Automatic Speech Recognition

Standard hidden Markov model (HMM) based automatic speech recognition (ASR) systems usually use cepstral features as acoustic observation and phonemes as subword units. Speech signal exhibits wide range of variability such as, due to environmental variatio ...

École Polytechnique Fédérale de Lausanne, Computer Science Department2005

Using Auxiliary Sources of Knowledge for Automatic Speech Recognition

Standard hidden Markov model (HMM) based automatic speech recognition (ASR) systems usually use cepstral features as acoustic observation and phonemes as subword units. Speech signal exhibits wide range of variability such as, due to environmental variatio ...

IDIAP2005

Efficient integration of automated speech recognition in the framework of dialogue-based vocal systems

In this work, we propose different strategies for efficiently integrating an automated speech recognition module in the framework of a dialogue-based vocal system. The aim is the study of different ways leading to the improvement of the quality and robustn ...

EPFL2005

Pseudo-Syntactic Language Modeling for Disfluent Speech Recognition

Language models for speech recognition are generally trained on text corpora. Since these corpora do not contain the disfluencies found in natural speech, there is a train/test mismatch when these models are applied to conversational speech. In this work w ...

IDIAP2004

Pseudo-Syntactic Language Modeling for Disfluent Speech Recognition

Language models for speech recognition are generally trained on text corpora. Since these corpora do not contain the disfluencies found in natural speech, there is a train/test mismatch when these models are applied to conversational speech. In this work w ...

2004

An Online Audio Indexing System

Hervé Bourlard, Jitendra Ajmera

This paper presents overview of an online audio indexing system, which creates a searchable index of speech content embedded in digitized audio files. This system is based on our recently proposed offline audio segmentation techniques. As the data arrives ...

2004

HMM mixtures (HMM2) for robust speech recognition

Katrin Weber

State-of-the-art automatic speech recognition (ASR) techniques are typically based on hidden Markov models (HMMs) for the modeling of temporal sequences of feature vectors extracted from the speech signal. At the level of each HMM state, Gaussian mixture m ...

EPFL2003

HMM Mixtures (HMM2) for Robust Speech Recognition

Katrin Weber

State-of-the-art automatic speech recognition (ASR) techniques are typically based on hidden Markov models (HMMs) for the modeling of temporal sequences of feature vectors extracted from the speech signal. At the level of each HMM state, Gaussian mixture m ...

Ecole Polytechnique Federale de Lausanne2003

On matching data and model in LF-MMI-based dysarthric speech recognition

Graph Chatbot

Chat with Graph Search

Model Adaptation for Sentence Unit Segmentation from Speech

Using auxiliary sources of knowledge for automatic speech recognition

Using Auxiliary Sources of Knowledge for Automatic Speech Recognition

Using Auxiliary Sources of Knowledge for Automatic Speech Recognition

Efficient integration of automated speech recognition in the framework of dialogue-based vocal systems

Pseudo-Syntactic Language Modeling for Disfluent Speech Recognition

Pseudo-Syntactic Language Modeling for Disfluent Speech Recognition

An Online Audio Indexing System

HMM mixtures (HMM2) for robust speech recognition

HMM Mixtures (HMM2) for Robust Speech Recognition

HMM Mixtures (HMM2) for Robust Speech Recognition

Using Auxiliary Sources of Knowledge for Automatic Speech Recognition

Using Auxiliary Sources of Knowledge for Automatic Speech Recognition

Using auxiliary sources of knowledge for automatic speech recognition

Model Adaptation for Sentence Unit Segmentation from Speech

Efficient integration of automated speech recognition in the framework of dialogue-based vocal systems

Pseudo-Syntactic Language Modeling for Disfluent Speech Recognition

An Online Audio Indexing System

HMM mixtures (HMM2) for robust speech recognition

Pseudo-Syntactic Language Modeling for Disfluent Speech Recognition