Publications related to Hierarchical Multi-Stream Posterior Based Speech Recognition System

Acoustic Models for Posterior Features in Speech Recognition

In this thesis, we investigate the use of posterior probabilities of sub-word units directly as input features for automatic speech recognition (ASR). These posteriors, estimated from data-driven methods, display some favourable properties such as increase ...

Idiap2008

Using more informative posterior probabilities for speech recognition

Hervé Bourlard, Samy Bengio, Hamed Ketabdar

In this paper, we present initial investigations towards boosting posterior probability based speech recognition systems by estimating more informative posteriors taking into account acoustic context (e.g., the whole utterance), as well as possible prior i ...

2006

Map-matching for pedestrians via Bayesian inference

Michel Bierlaire, Bertrand Merminod

A navigation process is to start from a known (initial) position and to ensure a continued localisation of the user during the movement. Consider a pedestrian navigation system which contains a GPS receiver and a set of inertial sensors connected with the ...

2006

Bayesian Inference for Autonomous Personal Localisation Indoors

Michel Bierlaire, Bertrand Merminod

The principal concept of navigation is to start from a known (initial) position and to ensure a continued and reliable localisation of the user during his/her movement. The initial position of the trajectory is usually obtained via GPS or defined by the us ...

2006

Bayesian Approach for Indoor Pedestrian Localisation

The principal concept of navigation is to start from a known (initial) position and to ensure a continued and reliable localisation of the user during his/her movement. The initial position of the trajectory is usually obtained via GPS or defined by the us ...

STRC 20062006

Multi-stream Processing for Noise Robust Speech Recognition

Hemant Misra

In this thesis, the framework of multi-stream combination has been explored to improve the noise robustness of automatic speech recognition (ASR) systems. The central idea of multi-stream ASR is to combine information from several sources to improve the pe ...

École Polytechnique Fédérale de Lausanne2006

Multi-stream Processing for Noise Robust Speech Recognition

Hemant Misra

In this thesis, the framework of multi-stream combination has been explored to improve the noise robustness of automatic speech recognition (ASR) systems. The central idea of multi-stream ASR is to combine information from several sources to improve the pe ...

IDIAP2006

Multi-stream processing for noise robust speech recognition

Hemant Misra

In this thesis, the framework of multi-stream combination has been explored to improve the noise robustness of automatic speech recognition (ASR) systems. The central idea of multi-stream ASR is to combine information from several sources to improve the pe ...

EPFL2006

Bayesian Approach for Indoor Pedestrian Localisation

Michel Bierlaire, Bertrand Merminod

The principal concept of navigation is to start from a known (initial) position and to ensure a continued and reliable localisation of the user during his/her movement. The initial position of the trajectory is usually obtained via GPS or defined by the us ...

2006

Hierarchical Multi-Stream Posterior Based Speech Recognition System

Hervé Bourlard, Samy Bengio, Hamed Ketabdar

In this paper, we present initial results towards boosting posterior based speech recognition systems by estimating more informative posteriors using multiple streams of features and taking into account acoustic context (e.g., as available in the whole utt ...

2005

Hierarchical Multi-Stream Posterior Based Speech Recognition System

Graph Chatbot

Chat with Graph Search

Acoustic Models for Posterior Features in Speech Recognition

Using more informative posterior probabilities for speech recognition

Map-matching for pedestrians via Bayesian inference

Bayesian Inference for Autonomous Personal Localisation Indoors

Bayesian Approach for Indoor Pedestrian Localisation

Multi-stream Processing for Noise Robust Speech Recognition

Multi-stream Processing for Noise Robust Speech Recognition

Multi-stream processing for noise robust speech recognition

Bayesian Approach for Indoor Pedestrian Localisation

Hierarchical Multi-Stream Posterior Based Speech Recognition System

Acoustic Models for Posterior Features in Speech Recognition

Multi-stream processing for noise robust speech recognition

Bayesian Inference for Autonomous Personal Localisation Indoors

Map-matching for pedestrians via Bayesian inference

Bayesian Approach for Indoor Pedestrian Localisation

Using more informative posterior probabilities for speech recognition

Multi-stream Processing for Noise Robust Speech Recognition

Multi-stream Processing for Noise Robust Speech Recognition

Bayesian Approach for Indoor Pedestrian Localisation

Hierarchical Multi-Stream Posterior Based Speech Recognition System