Publications associées à Combining the SNR Spectrum with a Cochlear Model

On Use of Task Independent Training Data in Tandem Feature Extraction

The problem we address in this paper is, whether the feature extraction module trained on large amounts of task independent data, can improve the performance of stochastic models? We show that when there is only a small amount of task specific training dat ...

2004

Robust Audio Segmentation

Hervé Bourlard, Jitendra Ajmera

Audio segmentation, in general, is the task of segmenting a continuous audio stream in terms of acoustically homogenous regions, where the rule of homogeneity depends on the task. This thesis aims at developing and investigating efficient, robust and unsup ...

IDIAP2004

Robust Audio Segmentation

Hervé Bourlard, Jitendra Ajmera

Audio segmentation, in general, is the task of segmenting a continuous audio stream in terms of acoustically homogenous regions, where the rule of homogeneity depends on the task. This thesis aims at developing and investigating efficient, robust and unsup ...

École Polytechnique Fédérale de Lausanne2004

Spectro-Temporal Activity Pattern (STAP) Features for Noise Robust ASR

Hervé Bourlard, Hemant Misra, Shajith Ikbal

In this paper, we introduce a new noise robust representation of speech signal obtained by locating points of potential importance in the spectrogram, and parameterizing the activity of time-frequency pattern around those points. These features are referre ...

2004

Spectro-Temporal Activity Pattern (STAP) Features for Noise Robust ASR

Hervé Bourlard, Hemant Misra, Shajith Ikbal

In this paper, we introduce a new noise robust representation of speech signal obtained by locating points of potential importance in the spectrogram, and parameterizing the activity of time-frequency pattern around those points. These features are referre ...

IDIAP2004

On Use of Task Independent Training Data in Tandem Feature Extraction

Hynek Hermansky

The problem we address in this paper is, whether the feature extraction module trained on large amounts of task independent data, can improve the performance of stochastic models? We show that when there is only a small amount of task specific training dat ...

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

Robust Speech Recognition and Feature Extraction Using HMM2

Hervé Bourlard, Samy Bengio, Katrin Weber, Shajith Ikbal

This paper presents the theoretical basis and preliminary experimental results of a new HMM model, referred to as HMM2, which can be considered as a mixture of HMMs. In this new model, the emission probabilities of the temporal (primary) HMM are estimated ...

2003

Combining the SNR Spectrum with a Cochlear Model

Graph Chatbot

Chattez avec Graph Search

On Use of Task Independent Training Data in Tandem Feature Extraction

Robust Audio Segmentation

Robust Audio Segmentation

Spectro-Temporal Activity Pattern (STAP) Features for Noise Robust ASR

Spectro-Temporal Activity Pattern (STAP) Features for Noise Robust ASR

On Use of Task Independent Training Data in Tandem Feature Extraction

HMM mixtures (HMM2) for robust speech recognition

HMM Mixtures (HMM2) for Robust Speech Recognition

HMM Mixtures (HMM2) for Robust Speech Recognition

Robust Speech Recognition and Feature Extraction Using HMM2

On Use of Task Independent Training Data in Tandem Feature Extraction

HMM mixtures (HMM2) for robust speech recognition

Spectro-Temporal Activity Pattern (STAP) Features for Noise Robust ASR

On Use of Task Independent Training Data in Tandem Feature Extraction

Spectro-Temporal Activity Pattern (STAP) Features for Noise Robust ASR

HMM Mixtures (HMM2) for Robust Speech Recognition

HMM Mixtures (HMM2) for Robust Speech Recognition

Robust Audio Segmentation

Robust Audio Segmentation

Robust Speech Recognition and Feature Extraction Using HMM2