Architectures of neural networks applied for LVCSR language modeling

• Published in: Neurocomputing (Amsterdam) Vol. 133; pp. 46 - 53
• Main Author: Gajecki, Leszek
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 10.06.2014; Elsevier
• Subjects: Acoustic signal processing; Acoustics; Applied sciences; Artificial intelligence; Computer science; control theory; systems; Connectionism. Neural networks; Exact sciences and technology; Fundamental areas of phenomenology (including applications); Information, signal and communications theory; Language modeling; Neural network architectures; Physics; Self-organized maps; Signal processing; Speech and sound recognition and synthesis. Linguistics; Speech processing; Speech recognition; Telecommunications and information theory; Neural network architectures; Self-organized maps; Speech recognition; Language modeling; Capability index; Vocabulary; Modelling language; Probabilistic approach; Slavonic language; Modular system; Network architecture; Syntactic analysis; Verbal perception; Neural network; Kohonen algorithm; Modeling; Self organization; N gram model; Data visualization; Derivative; Computational linguistics
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2013.11.033

The n-gram model and its derivatives are both widely applied solutions for Large Vocabulary Continuous Speech Recognition (LVCSR) systems. However, Slavonic languages require a language model that considers word order less strictly than English, i.e. the language that is the subject of most linguistic research. Such a language model is a necessary module in LVCSR systems, because it increases the probability of finding the right word sequences. The aim of the presented work is to create a language module for the Polish language with the application of neural networks. Here, the capabilities of Kohonen's Self-Organized Maps will be explored to find the associations between words in spoken utterances. To fulfill such a task, the application of neural networks to evaluate sequences of words will be presented. Then, the next step of language model development, the network architectures, will be discussed. The network proposed for the construction of the considered model is inspired by the Cocke–Young–Kasami parsing algorithm.