Artificial intelligence

Scientific journal

ISSN 2710-1673

ONLINE: ISSN 2710-1681

Search by:

Year of publication
Author name
Paper title

Problems of cross-platform speech recognition system creation

Vasylieva N.1, Fedoryn D.2
1 Department of Speech Recognition and Synthesis, International Research and Training Center of Information Technologies and Systems
2 International Research and Training Centre for Information Technologies and Systems

Full text (PDF)

UDC: 004.934
Publication Language: Ukrainian
Stuc. intelekt. 2013; 18(4):158-167

Abstract: The problems associated with building a speech recognition system on different computing platforms are considered. Particular attention is given to the data and knowledge base forming for acoustic, phonetic and lexical levels. Relation between speech recognition acoustic and linguistic components is being modeled as well as spoken element selection has been investigated and element order constraining methods are applied. Aspects of decoder implementation on the DSP microprocessor architecture including the possibility of speech signal remote processing are described.

Keywords: linguistic model, acoustic model, cross-platform systems, speech recognition

References:

  1. Vintsiuk T.K. The analysis, pattern recognition and semantic interpretation of the speech signals. – Kiev : Naukova Dumka, 1987. – 263 p.
  2. M. Gales, S. Young. The Application of Hidden Markov Models in Speech Recognition. // Foundations and Trends in Signal Processing. – 2007. – № 1(3). – P. 195-304.
  3. T. Vintsiuk, M. Sazhok. Multi-Level Multi-Decision Models in ASR. // Proc. of the 10th International Workshop “Speech and Computer” (SPECOM’2005). – Patras, 2005. – P. 69-76.
  4. http://www.creaceed.com/ceedvocal/about
  5. http://www.apple.com/ios/siri/
  6. http://www.nuance.com/for-business/by-product/automotive-products-services/vocon-hybrid/
  7. Robeiko V.V., Sazhok M.M. Multi-level multi-decision model transformation orthographic text to phonemic// Artificial Intelligence. – № 4'2011. – Donetsk, 2011. – P. 117-125.
  8. Sazhok N.N. Clustering words for construction of a linguistic model for the automatic recognition of the speech signal // Cybernetics and Computer Science: Interagency collection of scientific papers. – Issue. 170. – Kyiv, 2012. – P. 59-66.
  9. Vasylieva N.B. Free phoneme and syllable order grammar application for continuous speech phonemeby-phoneme recognition. Artificial Intelligence. – № 4'2011. – Donetsk, 2011. – P. 80-86.
  10. A. Lee, T. Kawahara. Julius – an open source real-time large vocabulary recognition engine. // Proc. European Conference on Speech Communication and Technology (EUROSPEECH) – 2001.
  11. The development of software and hardware base module of computer speech technology embedded in modern computer systems, the creation on their basis of high-tech electronic products widespread use and implementation of measures for their implementation in production (OK_2009_2): report of research work (final). IRTC IT&S. Supervisor Vintsiuk Т.К. – Kyiv, 2010. № DR 0109U004244.

View full text (PDF)