Department of Telecommunications and Teleinformatics Faculty of Automatic Control, Electronics and Computer Science

@article{ ISI:000395006200001,
Author = {Klosowski, Piotr},
Title = {{Statistical analysis of orthographic and phonemic language corpus for
   word-based and phoneme-based Polish language modelling}},
Journal = {{EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING}},
Year = {{2017}},
Month = {{FEB 28}},
Abstract = {{This article presents the original results of Polish language
   statistical analysis, based on the orthographic and phonemic language
   corpus. Phonemic language corpus for Polish was developed by using
   automatic grapheme-to-phoneme conversion of the source orthographic
   language corpus, obtained from the National Corpus of Polish (NCP). The
   corpus contains the most frequently used Polish words, written with the
   use of phonemic notation. Performed statistical analysis of Polish
   language based on phonemic language corpus, includes frequency of
   occurrence calculation of the orthographic and phonemic language
   components, as well as their sequence. Statistical language data,
   obtained as a result of performed statistical analysis, enable to
   develop statistical word-based and phoneme-based language models for
   Polish. Applying these language models can effectively contribute to
   efficiency improvement of automatic speech recognition for Polish.}},
DOI = {{10.1186/s13636-017-0102-8}},
Article-Number = {{5}},
ISSN = {{1687-4722}},
Unique-ID = {{ISI:000395006200001}},
}