Quality Measurement of Speech Recognition Features in Context of Nearest Neighbour Classifier
AbstractThe quality feature set is a key of importance of successful speech recognition system. The quality of features is estimated by classification error. Yet, this method is limited as the classification experiments must be run with each feature system. The major issue of this paper is to propose the method for quality estimation of speech recognition features that is based on metrics and does not require classification experiments. Experimental researches were made in context of Nearest neighbour classifier usage. Within the proposed method PLP was established to have the higher quality comparing to LFCC. The adequateness of the method was validated by Nearest neighbour classification error. Ill. 3, bibl. 25, tabl. 1 (in English; abstracts in English and Lithuanian).
Authors retain copyright and grant the journal the right of the first publication with the paper simultaneously licensed under the Creative Commons Attribution 4.0 (CC BY 4.0) licence.
Authors are allowed to enter into separate, additional contractual arrangements for the non-exclusive distribution of the paper published in the journal with an acknowledgement of the initial publication in the journal.
Copyright terms are indicated in the Republic of Lithuania Law on Copyright and Related Rights, Articles 4-37.