Change search
ReferencesLink to record
Permanent link

Direct link
Speech recognition for short range radio in a noisy environment
2002 (English)Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

This report describes a possible implementation of speech recognition for the short range radio system, the SRR300, produced by Saab Communication AB. The radio system is designed for communication in a high ambient noise situation. This system is for example used by airplane engineers, to be able to communicate with each other while they are working. Today's system uses a number of buttons to switch commands. With speech recognition added to the system, work would be much easier for them having both hands free. The suitable implementation described is the isolated word speech recognizer, which is built upon the Hidden Markov Model technique for speech modeling. To be able to make a specification of such a system a number of areas have been considered such as the characteristics of speech, a description of algorithms already implemented in the radio, linear predictive coding, the theory of HMM's and how the speech recognizer is to be implemented. The idea was also to make a first implementation in MATLAB. Unfortunately MATLAB turned out to be too slow for such task, and due to lack of time could another implementation not be done.

Place, publisher, year, edition, pages
Keyword [en]
Technology, Speech Recognition
Keyword [sv]
URN: urn:nbn:se:ltu:diva-45359ISRN: LTU-EX--02/042--SELocal ID: 30f29b7a-224b-48bd-970a-5975b2949eb5OAI: diva2:1018649
Subject / course
Student thesis, at least 30 credits
Educational program
Electrical Engineering, master's level
Validerat; 20101217 (root)Available from: 2016-10-04 Created: 2016-10-04Bibliographically approved

Open Access in DiVA

No full text

Search outside of DiVA

GoogleGoogle Scholar

Total: 14 hits
ReferencesLink to record
Permanent link

Direct link