A general description of automatic speech recognition systems architecture
Journal Title: Romanian Journal of Human - Computer Interaction - Year 2015, Vol 8, Issue 1
Abstract
Over the last decades, the progress in the ASR domain has been amplified by a significant amount of technical and scientific advancements, amongst which the continuous expansion in the power of computing systems. From a technological point of view, speech recognition has been undergoing tides of major innovations in methodology, algorithms, learning concepts or practical system implementations. This paper provides an up-to-date perspective on the architecture of automatic speech recognition systems and their constituent components. It presents modeling paradigms currently dominant in this type of systems (Hidden Markov Models, Gaussian mixture models, Bayes classifiers, N-gram language model, etc.) together with the architectural constraints they impose upon the design of the system. This study stands for an intermediate step in a larger process which aims to conceive and implement a highly accurate speaker independent ASR system for the recognition of the Romanian language in a limited field of application, such as justice.
Authors and Affiliations
Valentina Sofroni, Alexandru Stan
A Formative Measurement Model For The Motivational Value Of An AR-Based Educational Application
An objective of e-learning systems design is to increase the educational and motivational values. The evaluation of the motivational value of the applications based on the augmented reality technology as well as the eval...
User Localization by Spatial Context Processing
This paper presents a case study and a proposed solution for a train localization system, designed to satisfy the safety requirements specific to the railway domain, and the limits imposed by the low cost regional railwa...
MDL – Computer Assisted Lesson Development Module
In this article we present a new approach to teaching computer science - the evaluation and visual modeling of algorithms based on metaphorical forms - applied within the core of a virtual education system, the developme...
News Web Portal based on Natural Language Processing
The paper presents an autonomous text classification module for a news web portal for the Romanian language. Statistical natural language processing techniques are combined in order to achieve a completely autonomous fun...
The analysis of interactions in a collaborative learning session on instant messagery
The paper analyzes the interaction in a group of students who use instant messaging (IM) Yahoo Messenger to write a sorting algorithm. This analysis aims to identify words in a natural language and the methods of extract...