Publications related to Paralanguage

Using Pitch as Prior Knowledge in Template-Based Speech Recognition

In a previous paper on speech recognition, we showed that templates can better capture the dynamics of speech signal compared to parametric models such as hidden Markov models. The key point in template matching approaches is finding the most similar templ ...

2006

Using Pitch as Prior Knowledge in Template-Based Speech Recognition

Hervé Bourlard, Guillermo Aradilla

In a previous paper on speech recognition, we showed that templates can better capture the dynamics of speech signal compared to parametric models such as hidden Markov models. The key point in template matching approaches is finding the most similar templ ...

IDIAP2005

Spectral Entropy Based Feature for Robust ASR

Hervé Bourlard, Hynek Hermansky, Hemant Misra, Shajith Ikbal

In general, entropy gives us a measure of the number of bits required to represent some information. When applied to probability mass function (PMF), entropy can also be used to measure the ``peakiness'' of a distribution. In this paper, we propose using t ...

2004

Spectral Entropy Based Feature for Robust ASR

Hervé Bourlard, Hynek Hermansky, Hemant Misra, Shajith Ikbal

In general, entropy gives us a measure of the number of bits required to represent some information. When applied to probability mass function (PMF), entropy can also be used to measure the ``peakiness'' of a distribution. In this paper, we propose using t ...

IDIAP2003

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

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 ...

IDIAP2003

IDIAP HMM/HMM2 System: Theoretical Basis and Software Specifications

Hervé Bourlard, Samy Bengio, Katrin Weber, Shajith Ikbal

State-of-the-art Automatic Speech Recognition (ASR) systems make extensive use of Hidden Markov Models (HMMs), characterized by flexible statistical modeling, powerful optimization (training) techniques and efficient recognition algorithms. When allowed by ...

IDIAP2001

Paralanguage

Graph Chatbot

Chat with Graph Search

Using Pitch as Prior Knowledge in Template-Based Speech Recognition

Using Pitch as Prior Knowledge in Template-Based Speech Recognition

Spectral Entropy Based Feature for Robust ASR

Spectral Entropy Based Feature for Robust ASR

HMM mixtures (HMM2) for robust speech recognition

HMM Mixtures (HMM2) for Robust Speech Recognition

HMM Mixtures (HMM2) for Robust Speech Recognition

IDIAP HMM/HMM2 System: Theoretical Basis and Software Specifications

Using Pitch as Prior Knowledge in Template-Based Speech Recognition

HMM mixtures (HMM2) for robust speech recognition

Spectral Entropy Based Feature for Robust ASR

Using Pitch as Prior Knowledge in Template-Based Speech Recognition

HMM Mixtures (HMM2) for Robust Speech Recognition

Spectral Entropy Based Feature for Robust ASR

IDIAP HMM/HMM2 System: Theoretical Basis and Software Specifications

HMM Mixtures (HMM2) for Robust Speech Recognition