Sciweavers

TSD
2007
Springer
14 years 1 months ago
Maximum Likelihood and Maximum Mutual Information Training in Gender and Age Recognition System
Abstract. Gender and age estimation based on Gaussian Mixture Models (GMM) is introduced. Telephone recordings from the Czech SpeechDatEast database are used as training and test d...
Valiantsina Hubeika, Igor Szöke, Lukas Burget...
TSD
2007
Springer
14 years 1 months ago
An Adaptive Keyboard with Personalized Language-Based Features
Our research is about an adaptive keyboard, which autonomously adjusts its predictive features and key displays to current user input. We used personalized word prediction to impro...
Siska Fitrianie, Léon J. M. Rothkrantz
TSD
2007
Springer
14 years 1 months ago
ECAF: Authoring Language for Embodied Conversational Agents
Abstract. Embodied Conversational Agent (ECA) is the user interface metaphor that allows to naturally communicate information during human-computer interaction in synergic modality...
Ladislav Kunc, Jan Kleindienst
TSD
2007
Springer
14 years 1 months ago
Named Entities in Czech: Annotating Data and Developing NE Tagger
Magda Sevcíková, Zdenek Zabokrtsk&ya...
TSD
2007
Springer
14 years 1 months ago
Automatic Diacritic Restoration for Resource-Scarce Languages
Abstract. The orthography of many resource-scarce languages includes diacritically marked characters. Falling outside the scope of the standard Latin encoding, these characters are...
Guy De Pauw, Peter W. Wagacha, Gilles-Maurice de S...
NOLISP
2007
Springer
14 years 1 months ago
Quantitative Perceptual Separation of Two Kinds of Degradation in Speech Denoising Applications
Classical objective criteria evaluate speech quality using one quantity which embed all possible kind of degradation. For speech denoising applications, there is a great need to d...
Anis Ben Aicha, Sofia Ben Jebara
NOLISP
2007
Springer
14 years 1 months ago
Objective and Subjective Evaluation of an Expressive Speech Corpus
This paper presents the validation of the expressive content of an acted corpus produced for its use in speech synthesis. Firstly, objective techniques have been carried out by me...
Ignasi Iriondo Sanz, Santiago Planet, Joan Claudi ...
NOLISP
2007
Springer
14 years 1 months ago
Trajectory Mixture Density Networks with Multiple Mixtures for Acoustic-Articulatory Inversion
We have previously proposed a trajectory model which is based on a mixture density network (MDN) trained with target variables augmented with dynamic features together with an algo...
Korin Richmond