Abstract
This paper deals with some aspects of development voice user interfaces for several applications. The realistic scenario when developing VUI for such languages as Lithuanian is adaptation of foreign language speech recognizer. But not all voice commands could be recognized successfully enough using adapted recognizer. Hence the importance to implement hybrid recognizer arises. Several practical applications using Lithuanian voice command recognitions are presented. The experimental investigation showed that 90 percent recognition accuracy was achieved in average using adaptation of foreign language speech engine. Detailed analysis showed that most commands are recognized with very high accuracy. For those commands that aren’t recognized accurately enough hybrid recognition principle may be applied.DOI: http://dx.doi.org/10.5755/j01.eee.19.2.3469
Highlights
Voice user interfaces has a series of advantages for the control of various applications
The accuracy of 100 Lithuanian voice commands recognition should be more than 95%
In our previous experiments we showed that proper selection of phonetic transcriptions enables to achieve high enough recognition accuracy of Lithuanian voice commands using foreign language speech engine
Summary
Voice user interfaces has a series of advantages for the control of various applications. The success of Siri is caused by three main components: improved speech recognizer, improved natural language modeller and as semantic analyser These three components enabled the implementation of voice user interface with the flexibility never seen before in practical applications available to the general public. The history of the development of such flexible voice recognition using systems as Siri shows how complicated task are facing the researchers in this field: Siri was the outcome of the very big and very expensive research project which was carried for more than five years, grants were provided by US DoD DARPA agency, project cost was about 200 million USD, it involved more than 300 researchers from about 25 leading universities and private research laboratories The extent of these projects raised the necessity to rethink the principles and strategy when developing voice user interfaces were Lithuanian language is used as a primary means of communication. In this case hybrid recognition principle could be used which will be discussed below
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
