Language Modeling for Automatic Speech Recognition of Inflective Languages

An Applications-Oriented Approach Using Lexical Data

  • Gregor Donaj
  • Zdravko Kačič

Part of the SpringerBriefs in Electrical and Computer Engineering book series

Also part of the SpringerBriefs in Speech Technology book sub series (BRIEFSSPEECHTECH)

Table of contents

  1. Front Matter
    Pages i-viii
  2. Gregor Donaj, Zdravko Kačič
    Pages 1-4
  3. Gregor Donaj, Zdravko Kačič
    Pages 5-29
  4. Gregor Donaj, Zdravko Kačič
    Pages 31-47
  5. Gregor Donaj, Zdravko Kačič
    Pages 49-63
  6. Gregor Donaj, Zdravko Kačič
    Pages 65-71

About this book


This book covers language modeling and automatic speech recognition for inflective languages (e.g. Slavic languages), which represent roughly half of the languages spoken in Europe. These languages do not perform as well as English in speech recognition systems and it is therefore harder to develop an application with sufficient quality for the end user. The authors describe the most important language features for the development of a speech recognition system. This is then presented through the analysis of errors in the system and the development of language models and their inclusion in speech recognition systems, which specifically address the errors that are relevant for targeted applications. The error analysis is done with regard to morphological characteristics of the word in the recognized sentences. The book is oriented towards speech recognition with large vocabularies and continuous and even spontaneous speech. Today such applications work with a rather small number of languages compared to the number of spoken languages.

Concentrates on speech recognition for inflective languages – representative of roughly half of Europe -- and their unique characteristics

Introduces new application-oriented methods for measuring the performance of a speech recognition system

Presents examples of language modeling to maximize the performance of a speech recognition system

Provides techniques for analyzing errors and identifying their sources in a speech recognition system from a lexical point of view rather than acoustic point of view


Apple Siri Application Oriented Language Modeling Automatic Speech Recognition Google Voice Search Human-Machine Interaction Inflectional Language Inflective Language Language Modeling Lexical Error Analysis Natural Interaction Slavic Languages Speech Synthesis

Authors and affiliations

  • Gregor Donaj
    • 1
  • Zdravko Kačič
    • 2
  1. 1.Faculty of Electrical Engineering and Computer ScienceUniversity of MariborMariborSlovenia
  2. 2.University of MariborMariborSlovenia

Bibliographic information

  • DOI
  • Copyright Information The Author(s) - SpringerBriefs 2017
  • Publisher Name Springer, Cham
  • eBook Packages Engineering
  • Print ISBN 978-3-319-41605-2
  • Online ISBN 978-3-319-41607-6
  • Series Print ISSN 2191-8112
  • Series Online ISSN 2191-8120
  • Buy this book on publisher's site
Industry Sectors
Finance, Business & Banking
IT & Software
Consumer Packaged Goods
Oil, Gas & Geosciences