Modeling of Call Services for Public Sector
Abstract
Paper deals with application of English speech recognizer for multi-speaker Lithuanian digit names recognition. Many services in public sector require the identification of user or recognition of Lithuanian digit names with 95% or more accuracy. Combined multiple transcription selection method allowed to achieve multi-speaker recognition accuracy of ten Lithuanian digit names and two auxiliary words above 90%. It is possible to construct reliable user identification using only 7 digit names, so the experiments with three different sets of 7 Lithuanian digit names were performed and in all cases overall recognition accuracy exceeded 95%. Ill. 2, bibl. 11, tabl. 3 (in English; abstracts in English, Russian and Lithuanian).
Downloads
Published
How to Cite
Issue
Section
License
The copyright for the paper in this journal is retained by the author(s) with the first publication right granted to the journal. The authors agree to the Creative Commons Attribution 4.0 (CC BY 4.0) agreement under which the paper in the Journal is licensed.
By virtue of their appearance in this open access journal, papers are free to use with proper attribution in educational and other non-commercial settings with an acknowledgement of the initial publication in the journal.