出版社：Faculty of Humanities, Kaunas University of Technology
其他摘要：Paper focuses on the new vocabulary renewal algorithm designed for the hardware implemented Lithuanian speech recognizer. The isolated word recognition is performed using dynamic time warping of the Mel-frequency cepstrum coefficients (MFCC) estimated during short-time analysis of speech signals. A self-organizing feature map is used to extract the time-dependent MFCC features variations. To increase the isolated word recognition rate, four references are stored in the vocabulary for each word to be recognized. In order to make vocabulary adaptive to long-term changes of the user speech and adapt recognizer to the environment the references should be updated. The renewal of the vocabulary is performed if two conditions are met: the distance between same word references and the distance between new reference and other word references in the feature set should be increased. The comparison of the time-dependent MFCC feature variations is performed using Needleman-Wunsch sequence alignment algorithm. DOI: http://dx.doi.org/10.5755/j01.eee.20.6.7280
