Publications associées à Supervised and unsupervised Web-based language model domain adaptation

Emulating Temporal Receptive Fields of Auditory Mid-Brain Neurons for Automatic Speech Recognition

This paper proposes modifications to the Multi-resolution RASTA (MRASTA) feature extraction technique for the automatic speech recognition (ASR). By emulating asymmetries of the temporal receptive field (TRF) profiles of auditory mid-brain neurons, we obta ...

2008

Emulating Temporal Receptive Fields of Auditory Mid-Brain Neurons for Automatic Speech Recognition

Hynek Hermansky

This paper proposes modifications to the Multi-resolution RASTA (MRASTA) feature extraction technique for the automatic speech recognition (ASR). By emulating asymmetries of the temporal receptive field (TRF) profiles of auditory mid-brain neurons, we obta ...

IDIAP2008

Emulating Temporal Receptive Fields of Higher Level Auditory Neurons for ASR

Hynek Hermansky

This paper proposes modifications to the Multi-resolution RASTA (MRASTA) feature extraction technique for the automatic speech recognition (ASR). By emulating asymmetries of the temporal receptive field (TRF) profiles of higher level auditory neurons, we o ...

Springer-Verlag New York, Ms Ingrid Cunningham, 175 Fifth Ave, New York, Ny 10010 Usa2008

Front-end for Far-field Speech Recognition based on Frequency Domain Linear Prediction

Hynek Hermansky, Sriram Ganapathy, Samuel Thomas

Automatic Speech Recognition (ASR) systems usually fail when they encounter speech from far-field microphone in reverberant environments. This is due to the application of short-term feature extraction techniques which do not compensate for the artifacts i ...

2008

Front-end for Far-field Speech Recognition based on Frequency Domain Linear Prediction

Hynek Hermansky, Sriram Ganapathy, Samuel Thomas

Automatic Speech Recognition (ASR) systems usually fail when they encounter speech from far-field microphone in reverberant environments. This is due to the application of short-term feature extraction techniques which do not compensate for the artifacts i ...

IDIAP2008

Ensembles for sequence learning

Christos Dimitrakakis

This thesis explores the application of ensemble methods to sequential learning tasks. The focus is on the development and the critical examination of new methods or novel applications of existing methods, with emphasis on supervised and reinforcement lear ...

EPFL2007

Ensembles for Sequence Learning

Christos Dimitrakakis

This thesis explores the application of ensemble methods to sequential learning tasks. The focus is on the development and the critical examination of new methods or novel applications of existing methods, with emphasis on supervised and reinforcement lear ...

École Polytechnique Fédérale de Lausanne2006

Semi-supervised Adapted HMMs for Unusual Event Detection

Daniel Gatica-Perez, Samy Bengio, Dong Zhang

We address the problem of temporal unusual event detection. Unusual events are characterized by a number of features (rarity, unexpectedness, and relevance) that limit the application of traditional supervised model-based approaches. We propose a semi-supe ...

2005

Semi-supervised Adapted HMMs for Unusual Event Detection

Daniel Gatica-Perez, Samy Bengio, Dong Zhang

We address the problem of temporal unusual event detection. Unusual events are characterized by a number of features (rarity, unexpectedness, and relevance) that limit the application of traditional supervised model-based approaches. We propose a semi-supe ...

IDIAP2004

An information theoretic measure of sequence recognition performance

Sequence recognition performance is often summarised first in terms of the number of hits (H), substitutions (S), deletions (D) and insertions (I), and then as a single statistic by the "word error rate" WER = 100(S D I)/(H S D). While in common use, WER h ...

IDIAP2002

Supervised and unsupervised Web-based language model domain adaptation

Graph Chatbot

Chattez avec Graph Search

Emulating Temporal Receptive Fields of Auditory Mid-Brain Neurons for Automatic Speech Recognition

Emulating Temporal Receptive Fields of Auditory Mid-Brain Neurons for Automatic Speech Recognition

Emulating Temporal Receptive Fields of Higher Level Auditory Neurons for ASR

Front-end for Far-field Speech Recognition based on Frequency Domain Linear Prediction

Front-end for Far-field Speech Recognition based on Frequency Domain Linear Prediction

Ensembles for sequence learning

Ensembles for Sequence Learning

Semi-supervised Adapted HMMs for Unusual Event Detection

Semi-supervised Adapted HMMs for Unusual Event Detection

An information theoretic measure of sequence recognition performance

Emulating Temporal Receptive Fields of Higher Level Auditory Neurons for ASR

Emulating Temporal Receptive Fields of Auditory Mid-Brain Neurons for Automatic Speech Recognition

Emulating Temporal Receptive Fields of Auditory Mid-Brain Neurons for Automatic Speech Recognition

Front-end for Far-field Speech Recognition based on Frequency Domain Linear Prediction

Ensembles for sequence learning

Front-end for Far-field Speech Recognition based on Frequency Domain Linear Prediction

Ensembles for Sequence Learning

Semi-supervised Adapted HMMs for Unusual Event Detection

An information theoretic measure of sequence recognition performance

Semi-supervised Adapted HMMs for Unusual Event Detection