Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 449339

Development of Acoustic Model for Croatian Language Using HTK


Dropuljić, Branimir; Petrinović, Davor
Development of Acoustic Model for Croatian Language Using HTK // Automatika : časopis za automatiku, mjerenje, elektroniku, računarstvo i komunikacije, 51 (2010), 1; 79-88 (međunarodna recenzija, članak, znanstveni)


CROSBI ID: 449339 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Development of Acoustic Model for Croatian Language Using HTK

Autori
Dropuljić, Branimir ; Petrinović, Davor

Izvornik
Automatika : časopis za automatiku, mjerenje, elektroniku, računarstvo i komunikacije (0005-1144) 51 (2010), 1; 79-88

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
Acoustic model; Automatic speech recognition; Croatian language; Hidden Markov models; Phonetic assimilation; Phonetic transcription algorithm; Recognition accuracy

Sažetak
Paper presents development of the acoustic model for Croatian language for automatic speech recognition (ASR). Continuous speech recognition is performed by means of the Hidden Markov Models (HMM) implemented in the HMM Toolkit (HTK). In order to adjust the HTK to the native language a novel algorithm for Croatian language transcription (CLT) has been developed. It is based on phonetic assimilation rules that are applied within uttered words. Phonetic questions for state tying of different triphone models have also been developed. The automated system for training and evaluation of acoustic models has been developed and integrated with the new graphical user interface (GUI). Targeted applications of this ASR system are stress inoculation training (SIT) and virtual reality exposure therapy (VRET). Adaptability of the model to a closed set of speakers is important for such applications and this paper investigates the applicability of the HTK tool for typical scenarios. Robustness of the tool to a new language was tested in matched conditions by a parallel training of an English model that was used as a baseline. Ten native Croatian speakers participated in experiments. Encouraging results were achieved and reported with the developed model for Croatian language.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo



POVEZANOST RADA


Projekti:
0036054
036-0000000-2029 - Adaptivno upravljanje scenarijima u VR terapiji PTSP-a (Ćosić, Krešimir, MZOS ) ( POIROT)

Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb

Profili:

Avatar Url Davor Petrinović (autor)

Avatar Url Branimir Dropuljić (autor)

Poveznice na cjeloviti tekst rada:

Pristup cjelovitom tekstu rada Hrčak

Citiraj ovu publikaciju:

Dropuljić, Branimir; Petrinović, Davor
Development of Acoustic Model for Croatian Language Using HTK // Automatika : časopis za automatiku, mjerenje, elektroniku, računarstvo i komunikacije, 51 (2010), 1; 79-88 (međunarodna recenzija, članak, znanstveni)
Dropuljić, B. & Petrinović, D. (2010) Development of Acoustic Model for Croatian Language Using HTK. Automatika : časopis za automatiku, mjerenje, elektroniku, računarstvo i komunikacije, 51 (1), 79-88.
@article{article, year = {2010}, pages = {79-88}, keywords = {Acoustic model, Automatic speech recognition, Croatian language, Hidden Markov models, Phonetic assimilation, Phonetic transcription algorithm, Recognition accuracy}, journal = {Automatika : \v{c}asopis za automatiku, mjerenje, elektroniku, ra\v{c}unarstvo i komunikacije}, volume = {51}, number = {1}, issn = {0005-1144}, title = {Development of Acoustic Model for Croatian Language Using HTK}, keyword = {Acoustic model, Automatic speech recognition, Croatian language, Hidden Markov models, Phonetic assimilation, Phonetic transcription algorithm, Recognition accuracy} }
@article{article, year = {2010}, pages = {79-88}, keywords = {Acoustic model, Automatic speech recognition, Croatian language, Hidden Markov models, Phonetic assimilation, Phonetic transcription algorithm, Recognition accuracy}, journal = {Automatika : \v{c}asopis za automatiku, mjerenje, elektroniku, ra\v{c}unarstvo i komunikacije}, volume = {51}, number = {1}, issn = {0005-1144}, title = {Development of Acoustic Model for Croatian Language Using HTK}, keyword = {Acoustic model, Automatic speech recognition, Croatian language, Hidden Markov models, Phonetic assimilation, Phonetic transcription algorithm, Recognition accuracy} }

Časopis indeksira:


  • Web of Science Core Collection (WoSCC)
    • Science Citation Index Expanded (SCI-EXP)
    • SCI-EXP, SSCI i/ili A&HCI
  • Scopus


Uključenost u ostale bibliografske baze podataka::


  • INSPEC
  • Science Citation Index Expanded
  • Chemical Abstracts
  • Current Bibliography on Science and Technology
  • Science Abstracts
  • Referativnii Zurnal





Contrast
Increase Font
Decrease Font
Dyslexic Font