יחידת קצה למערכת זיהוי דיבור

פרויקט מצטיין 

ביצועי מערכת לזיהוי דיבור נפגמים כתוצאה מנוכחות רעש. בפרויקט זה מומש תקן DSR, המבוסס על סינון וינר ושולב עם מערכת הזיהוי שפותחה בחברת NSC. 

בשיתוף פעולה עם חברת NSC.

Speech Recognition Front End
by Asaf Danino

The performance of speech recognition systems receiving speech that has been transmitted over mobile channels can be significantly degraded when compared to using an unmodified speech signals. The degradations are as a result of both the low bit rate speech coding and channel transmission errors. The Distributed Speech Recognition (DSR) standard overcomes these problems by eliminating the speech channel and instead using an error protected data channel to send a parameterized representation of the speech, which is suitable for recognition. The DSR standard contains: noise reduction, blind equalization, mfcc feature extraction and feature compression/decompression.

In collaboration with NSC