Publications related to On quantifying the quality of acoustic models in hybrid DNN-HMM ASR

Modeling Individual and Group Actions in Meetings With Layered HMMs

Daniel Gatica-Perez, Samy Bengio, Guillaume Lathoud, Dong Zhang

We address the problem of recognizing sequences of human interaction patterns in meetings, with the goal of structuring them in semantic terms. The investigated patterns are inherently group-based (defined by the individual activities of meeting participan ...

2004

Modeling Individual and Group Actions in Meetings With Layered HMMs

Daniel Gatica-Perez, Samy Bengio, Guillaume Lathoud, Dong Zhang

We address the problem of recognizing sequences of human interaction patterns in meetings, with the goal of structuring them in semantic terms. The investigated patterns are inherently group-based (defined by the individual activities of meeting participan ...

IDIAP2004

User-Customized Password Speaker Verification Using Multiple Reference and Background Models

Hervé Bourlard

This paper discusses and optimizes an HMM/GMM based User-Customized Password Speaker Verification (UCP-SV) system. Unlike text-dependent speaker verification, in UCP-SV systems, customers can choose their own passwords with no lexical constraints. The pass ...

IDIAP2004

Speech recognition with auxiliary information

Automatic speech recognition (ASR) is a very challenging problem due to the wide variety of the data that it must be able to deal with. Being the standard tool for ASR, hidden Markov models (HMMs) have proven to work well for ASR when there are controls ov ...

EPFL2003

Speech Recognition with Auxiliary Information

Automatic speech recognition (ASR) is a very challenging problem due to the wide variety of the data that it must be able to deal with. Being the standard tool for ASR, hidden Markov models (HMMs) have proven to work well for ASR when there are controls ov ...

IDIAP2003

Speech Recognition with Auxiliary Information

Automatic speech recognition (ASR) is a very challenging problem due to the wide variety of the data that it must be able to deal with. Being the standard tool for ASR, hidden Markov models (HMMs) have proven to work well for ASR when there are controls ov ...

École Polytechnique Fédérale de Lausanne, Computer Science Department2003

Speech/Music Discrimination using Entropy and Dynamism Features in a HMM Classification Framework

Hervé Bourlard, Jitendra Ajmera

In this paper, we present a new approach towards high performance speech/music discrimination on realistic tasks related to the automatic transcription of broadcast news. In the approach presented here, the (local) Probability Density Function (PDF) estima ...

2003

HMM inference towards flexible speech recognition

One of the difficulties in Automatic Speech Recognizer (ASR) is the pronunciation variability. Each word (modeled by a baseline phonetic transcription in the ASR dictionary) can be pronounced in many different ways depending on many complex qualitative and ...

IDIAP2003

User-Customized Password Speaker Verification based on HMM/ANN and GMM Models

Hervé Bourlard

In this paper, we present a new approach towards user-custom-ized password speaker verification combining the advantages of hybrid HMM/ANN systems, using Artificial Neural Networks (ANN) to estimate emission probabilities of Hidden Markov Models, and Gaus ...

IDIAP2002

User-Customized Password Speaker Verification based on HMM/ANN and GMM Models

Hervé Bourlard

In this paper, we present a new approach towards user-custom-ized password speaker verification combining the advantages of hybrid HMM/ANN systems, using Artificial Neural Networks (ANN) to estimate emission probabilities of Hidden Markov Models, and Gaus ...

2002

On quantifying the quality of acoustic models in hybrid DNN-HMM ASR

Graph Chatbot

Chat with Graph Search

Modeling Individual and Group Actions in Meetings With Layered HMMs

Modeling Individual and Group Actions in Meetings With Layered HMMs

User-Customized Password Speaker Verification Using Multiple Reference and Background Models

Speech recognition with auxiliary information

Speech Recognition with Auxiliary Information

Speech Recognition with Auxiliary Information

Speech/Music Discrimination using Entropy and Dynamism Features in a HMM Classification Framework

HMM inference towards flexible speech recognition

User-Customized Password Speaker Verification based on HMM/ANN and GMM Models

User-Customized Password Speaker Verification based on HMM/ANN and GMM Models

Modeling Individual and Group Actions in Meetings With Layered HMMs

Modeling Individual and Group Actions in Meetings With Layered HMMs

Speech Recognition with Auxiliary Information

Speech recognition with auxiliary information

Speech Recognition with Auxiliary Information

HMM inference towards flexible speech recognition

User-Customized Password Speaker Verification based on HMM/ANN and GMM Models

User-Customized Password Speaker Verification Using Multiple Reference and Background Models

Speech/Music Discrimination using Entropy and Dynamism Features in a HMM Classification Framework

User-Customized Password Speaker Verification based on HMM/ANN and GMM Models