DocumentCode :
2403529
Title :
ProtoLOGOS, system for Romanian language automatic speech recognition and understanding (ASRU)
Author :
Militaru, Diana ; Gavat, Inge ; Dumitru, Octavian ; Zaharia, Tiberiu ; Segarceanu, Svetlana
Author_Institution :
Fac. of Electron., Telecommun. & Inf. Technol., Univ. Politeh., Bucharest, Romania
fYear :
2009
fDate :
18-21 June 2009
Firstpage :
1
Lastpage :
9
Abstract :
The ProtoLOGOS Romanian language automatic speech recognition and understanding system is based at the level of acoustical modeling on the statistical framework of hidden Markov models and at the linguistic level on a finite state grammar or a bigram language model. The system enhanced the speech signal modeling by using for the first time the PLP (Perceptual Linear Prediction) features in a Romanian language recognition system. The main performance indicator for our system is the phrase recognition rate. This paper presents the main results obtained using the two language models already mentioned and the METEO database, constituted by broadcasted forecast news records.
Keywords :
hidden Markov models; natural language processing; speech recognition; statistical analysis; Romanian language automatic speech recognition; acoustical modeling; bigram language model; finite state grammar; hidden Markov model; perceptual linear prediction; phrase recognition rate; speech signal modeling; statistical framework; Automatic speech recognition; Cepstral analysis; Dictionaries; Hidden Markov models; Information technology; Mel frequency cepstral coefficient; Natural languages; Predictive models; Speech enhancement; Speech recognition; CDHMM; HMM; Romanian language; SCHMM; language model; monophones; speech recognition; speech understanding; triphones;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Speech Technology and Human-Computer Dialogue, 2009. SpeD '09. Proceedings of the 5-th Conference on
Conference_Location :
Constant
Print_ISBN :
978-1-4244-4727-5
Type :
conf
DOI :
10.1109/SPED.2009.5156171
Filename :
5156171
Link To Document :
بازگشت