Sciweavers

2990 search results - page 108 / 598
» Hidden Markov processes
Sort
View
ICASSP
2008
IEEE
14 years 4 months ago
Exploiting contextual information for improved phoneme recognition
In this paper, we investigate the significance of contextual information in a phoneme recognition system using the hidden Markov model - artificial neural network paradigm. Cont...
Joel Pinto, B. Yegnanarayana, Hynek Hermansky, Mat...
ICASSP
2008
IEEE
14 years 4 months ago
Gradient steepness metrics using extended Baum-Welch transformations for universal pattern recognition tasks
In many pattern recognition tasks, given some input data and a family of models, the “best” model is defined as the one which maximizes the likelihood of the data given the m...
Tara N. Sainath, Dimitri Kanevsky, Bhuvana Ramabha...
ICASSP
2008
IEEE
14 years 4 months ago
Accurate statistical spoken language understanding from limited development resources
Robust Spoken Language Understanding (SLU) is a key component of spoken dialogue systems. Recent statistical approaches to this problem require additional resources (e.g. gazettee...
I. V. Meza-Ruiz, Sebastian Riedel, Oliver Lemon
TSD
2004
Springer
14 years 3 months ago
Slovak Text-to-Speech Synthesis in ARTIC System
Abstract. This paper presents a brand-new Slovak text-to-speech system. It was developed within the framework of ARTIC system (primarily designed to synthesize Czech speech) with r...
Jindrich Matousek, Daniel Tihelka
ICASSP
2009
IEEE
14 years 1 months ago
Graphical Models: Statistical inference vs. determination
Using discrete Hidden-Markov-Models (HMMs) for recognition requires the quantization of the continuous feature vectors. In handwritten whiteboard note recognition it turns out tha...
Joachim Schenk, Benedikt Hörnler, Artur Braun...