Title :
An automatic language identification system
Author :
Savic, Michael ; Acosta, Elena ; Gupta, Sunil K.
Author_Institution :
Rensselaer Polytech. Inst., Troy, NY, USA
Abstract :
An automatic language identification system which makes use of several language specific features is described. The system concurrently utilizes features associated with two methodologies, the hidden Markov model, (HMM) and language-specific pitch contours. Experimental results show that transition probabilities and pitch contours show differences between the languages. However, each of the described criteria will not give in every case a definitive answer, but will lead in the correct direction. Therefore, a voting classifier should be used to combine the results from each of the criteria
Keywords :
Markov processes; natural languages; speech recognition; HMM; automatic language identification system; hidden Markov model; language-specific pitch contours; transition probabilities; voting classifier; Application software; Autocorrelation; Frequency; Hidden Markov models; Natural languages; Production; Stochastic processes; Systems engineering and theory; Telephony; Voting;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference on
Conference_Location :
Toronto, Ont.
Print_ISBN :
0-7803-0003-3
DOI :
10.1109/ICASSP.1991.150462
