Building Medium-Vocabulary Isolated-Word Lithuanian HMM Speech Recognition System

  • Authors:

  • Gailius Raškinis;Danutė Raškinienė

  • Affiliations:

  • Faculty of Computer Science, Vytautas Magnus University, Vileikos 8, LT-3035 Kaunas, Lithuania, e-mail: idgara@vdu.lt;Institute of Information Technologies, Lithuanian University of Agriculture, Studentų 11, LT-4324 Akademija, Kauno r., Lithuania, e-mail: danra@info.lzua.lt

  • Venue:
  • Informatica
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, the opening work on the development of aLithuanian HMM speech recognition system is described. The triphonesingle-Gaussian HMM speech recognition system based on MelFrequency Cepstral Coefficients (MFCC) was developed using HTKtoolkit. Hidden Markov model's parameters were estimated fromphone-level hand-annotated Lithuanian speech corpus. The system wasevaluated on a speaker-independent