Using voice interaction technologies such as speech recognition and speech synthesis to work out new proposal on human machine interaction, to establish new process flow on comprehensive processing over voice information and to create standards in aerospace speech technology. Through years of development, our company has developed a mature research system,and has technology advantage in the field. We have become the main supplier in speech technology products for domestic aviation sector.
-
Command such as ‘turn on the radar’, ‘turn off the radar’, ‘status display’, pilot can input ‘window1, radar’ by voice, and then the pop-up window 1 will quickly switch to radar display screen.
-
Set waypoint: "North latitude 43 degrees 25 minutes 59 seconds”, "East longitude 120 degrees 36 minutes 18 seconds”; Set communication frequency: "master 263.48 MHz"
-
"No. 2 attack target No. 6","07(zero seven) attack target No. 2"
-
"Broadcast the height of No. 2". "Broadcast oil volume of No. 2 "
-
First generation of speech recognition devices
By adopting dual processing platform + architecture design of isolated word recognition algorithm, the speech recognition technology was applied in the airborne field for the first time.
-
Second generation of speech recognition devices
A more systematic and integrated design over the system by using dual processor + design architecture of recognition algorithm with Chinese character and numeral figures. Reduced significantly the product weight and power consumption.
-
Third generation of speech recognition devices
High speed multiple core processing platform + architecture design of continuous words recognition algorithm. Achieved recognition over isolated words, phrases, number and English.
Voice synthesis algorithm is not limited by operational system, thus it will not additionally increase customers’ hardware costs. Taking into consideration the resources limits over embedded devices, it made great breakthrough on resources occupation, portability and other aspects. The general synthesis effect has exceeded the average speech level of human being.
