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
Keywords
Related Articles
- EP ID EP28963
- DOI -
- Views 368
- Downloads 8
Practical Approaches for Interdisciplinary Interaction Design
In this paper the evolution of software design methods is discussed with insights from the usability perspective. Usability is considered an essential factor in the success or failure of an interactive system, determinin...
Analysis of three instruments for measuring usability, satisfaction, and user experience in Romanian context
This paper focuses on the relation between the main concepts used in Human-Computer Interaction domain in order to study users’ perception of interactive products quality like usability, satisfaction, and user experience...
Analytical platform for the study of usage data generated by telemedicine services
Telemedicine researches nowadays focus more and more on the complexity of the services that can be delivered and on the development of new paradigms of healthcare delivery. The paper proposes a different approach, a stud...
UsiGesture: Test and Evaluation of an Environment for Integrating Gestures in User Interfaces
User interfaces allowing gesture recognition and manipulation are becoming more and more popular these last years. It however remains a hard task for programmers to developer such interfaces : some knowledge of recogniti...
Beta testing of a dynamic language identification software component - preliminary results
Automatic language identification in a given text belongs to a general category of algorithms of text classifications with many applications. Some recent developments concerns language dependent speech synthesis. For suc...