Publications related to Learning to recognise talking faces

HMM-based Non-native Accent Assessment using Posterior Features

Automatic non-native accent assessment has many potential benefits in language learning and speech technologies. The three fundamental challenges in automatic accent assessment are to characterize, model and assess individual variation in speech of the non ...

Idiap2015

Unified Framework of Feature Based Adaptation for Statistical Speech Synthesis and Recognition

Lakshmi Babu Saheer

The advent of statistical parametric speech synthesis has paved new ways to a unified framework for hidden Markov model (HMM) based text to speech synthesis (TTS) and automatic speech recognition (ASR). The techniques and advancements made in the field of ...

EPFL2013

Crosslingual Tandem-SGMM: Exploiting Out-Of-Language Data for Acoustic Model and Feature Level Adaptation

Petr Motlicek, Philip Neil Garner, David Imseng

Recent studies have shown that speech recognizers may benefit from data in languages other than the target language through efficient acoustic model- or feature-level adaptation. Crosslingual Tandem-Subspace Gaussian Mixture Models (SGMM) are successfully ...

ISCA2013

Crosslingual Tandem-SGMM: Exploiting Out-Of-Language Data for Acoustic Model and Feature Level Adaptation

Petr Motlicek, Philip Neil Garner, David Imseng

Recent studies have shown that speech recognizers may benefit from data in languages other than the target language through efficient acoustic model- or feature-level adaptation. Crosslingual Tandem-Subspace Gaussian Mixture Models (SGMM) are successfully ...

Idiap2013

Source/Filter Factorial Hidden Markov Model, with Application to Pitch and Formant Tracking

Jean-Philippe Thiran

Tracking vocal tract formant frequencies (

f_p

) and estimating the fundamental frequency (

f_0

) are two tracking problems that have been tackled in many speech processing works, often independently, with applications to articulatory parameters estimation ...

Institute of Electrical and Electronics Engineers2013

Multi-parametric source-filter separation of speech and prosodic voice restoration

Olaf Schleusing

In this thesis, methods and models are developed and presented aiming at the estimation, restoration and transformation of the characteristics of human speech. During a first period of the thesis, a concept was developed that allows restoring prosodic voic ...

EPFL2012

Unified Framework Of Feature Based Adaptation For Statistical Speech Synthesis And Recognition

Lakshmi Babu Saheer

The advent of statistical parametric speech synthesis has paved new ways to a unified framework for hidden Markov model (HMM) based text to speech synthesis (TTS) and automatic speech recognition (ASR). The techniques and advancements made in the field of ...

Ecole Polytechnique Federale de Lausanne (EPFL)2012

VTLN-Based Rapid Cross-Lingual Adaptation for Statistical Parametric Speech Synthesis

Philip Neil Garner, John David Scott Dines, Hui Liang, Lakshmi Babu Saheer

Cross-lingual speaker adaptation (CLSA) has emerged as a new challenge in statistical parametric speech syn- thesis, with specific application to speech-to-speech translation. Recent research has shown that reasonable speaker similarity can be achieved in ...

Idiap2012

Feature distribution modelling techniques for 3D face recognition

Sébastien Marcel

This paper shows that Hidden Markov Models (HMMs) can be effectively ap- plied to 3D face data. The examined HMM techniques are shown to be superior to a previously examined Gaussian Mixture Model (GMM) technique. Experi- ments conducted on the Face Recogn ...

2010

Measuring the gap between HMM-based ASR and TTS

John David Scott Dines, Simon King

The EMIME European project is conducting research in the development of technologies for mobile, personalised speech-tospeech translation systems. The hidden Markov model is being used as the underlying technology in both automatic speech recognition (ASR) ...

2009

Learning to recognise talking faces

Graph Chatbot

Chat with Graph Search

HMM-based Non-native Accent Assessment using Posterior Features

Unified Framework of Feature Based Adaptation for Statistical Speech Synthesis and Recognition

Crosslingual Tandem-SGMM: Exploiting Out-Of-Language Data for Acoustic Model and Feature Level Adaptation

Crosslingual Tandem-SGMM: Exploiting Out-Of-Language Data for Acoustic Model and Feature Level Adaptation

Source/Filter Factorial Hidden Markov Model, with Application to Pitch and Formant Tracking

Multi-parametric source-filter separation of speech and prosodic voice restoration

Unified Framework Of Feature Based Adaptation For Statistical Speech Synthesis And Recognition

VTLN-Based Rapid Cross-Lingual Adaptation for Statistical Parametric Speech Synthesis

Feature distribution modelling techniques for 3D face recognition

Measuring the gap between HMM-based ASR and TTS

HMM-based Non-native Accent Assessment using Posterior Features

Multi-parametric source-filter separation of speech and prosodic voice restoration

Crosslingual Tandem-SGMM: Exploiting Out-Of-Language Data for Acoustic Model and Feature Level Adaptation

Unified Framework of Feature Based Adaptation for Statistical Speech Synthesis and Recognition

Crosslingual Tandem-SGMM: Exploiting Out-Of-Language Data for Acoustic Model and Feature Level Adaptation

VTLN-Based Rapid Cross-Lingual Adaptation for Statistical Parametric Speech Synthesis

Source/Filter Factorial Hidden Markov Model, with Application to Pitch and Formant Tracking

Feature distribution modelling techniques for 3D face recognition

Measuring the gap between HMM-based ASR and TTS

Unified Framework Of Feature Based Adaptation For Statistical Speech Synthesis And Recognition