Novel LVCSR Decoder Based on Perfect Hash Automata and Tuple Structures – SPREAD –
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2014, Vol 5, Issue 5
Abstract
The paper presents the novel design of a one-pass large vocabulary continuous-speech recognition decoder engine, named SPREAD. The decoder is based on a time-synchronous beam-search approach, including statically expanded cross-word triphone contexts. An approach using efficient tuple structures is proposed for the construction of the complete search-network. The foremost benefits are the important space savings and higher processing speed, and the compact and reduced size of the tuple structure, especially when exploiting the structure of the key. In this way, the time needed to load the ASR search-network into the memory is also significantly reduced. Further, the paper proposes and presents the complete methodology for compiling general ASR knowledge sources into a tuple structures. Additionally, the beam search is enhanced with the novel implementation of a bigram language model Look-Ahead technique, by using tuple structures and a caching scheme. The SPREAD LVCSR decoder is based on a token-passing algorithm, capable of restricting its search-space by several types of token pruning. By using the presented language model Look-Ahead technique, it is possible to increase the number of tokens that can be pruned without decoding precision loss.
Authors and Affiliations
Matej Rojc, Kacic Zdravko
Keywords
Related Articles
- EP ID EP105025
- DOI 10.14569/IJACSA.2014.050504
- Views 112
- Downloads 0
Educational Game Application Development on Classification of Diseases and Related Health Problems Treatment in Android Platform
The classification and codification of diseases and related problems is one of the competences of medical recorder as stated in Kepmenkes RI.377 in 2007. The current problem is the lack of reference exercise in learning...
Virtual Identity Approaches Evaluation for Anonymous Communication in Cloud Environments
Since the era’s of Cloud computing beginning, the Identity Management is considered as a permanent challenge especially for the hybrid IT environments that permit for many users’ applications to share the same data cente...
Evaluating M-Learning in Saudi Arabia Universities using Concerns-Based Adoption Model Level of use Framework
Numerous studies have evaluated aspects of m-learning use in Saudi Arabia, mostly focused on technology use and its impact on students, or technology challenges and promises. Few studies have explored features of m-learn...
A Shape Based Image Search Technique
This paper describes an interactive application we have developed based on shaped-based image retrieval technique. The key concepts described in the project are, i)matching of images based on contour matching; ii)matchin...
Different Classification Algorithms Based on Arabic Text Classification: Feature Selection Comparative Study
Feature selection is necessary for effective text classification. Dataset preprocessing is essential to make upright result and effective performance. This paper investigates the effectiveness of using feature selection....