pinkbas.blogg.se

Subsequently, the massive speech resources are obtained through the network connection into the iFLYTEK’s open platform, which can realize online speech recognition, semantic understanding, and speech synthesis. Furthermore, the local speech recognition is realized through the special chip for speech recognition hbr740, while the local speech synthesis is realized through the special chip for speech synthesis syn6288. Real time face detection is realized by transplanting the Opencv library into the Android system and combining that with the AdaBoost algorithm. The whole system mainly includes face detection, speech synthesis, and speech recognition. This paper designs a hotel human-computer interaction (HCI) system which is based on deep learning. These images contribute to shortening the debugging time for developers and testers. In addition, the data was visualized in images containing the update information of the memory. Through the proposed method, the ECU memory information during the HiL test was successfully collected using the CAN the transmission is completed without any loss of data. The collected data can be visualized as update information in each cycle and the cumulative number of updates. Next, the simulation is repeated for the each divided regions to obtain the different areas in each simulation. Therefore, to overcome the above limitations, in this study, the memory is divided into multiple regions to transmit generated data via CAN. However, when the 32 KB memory is observed with 10 ms period, about 96% of the data on each cycle is lost, since the CAN only can transfer 1.25 KB of data at each cycle. Meanwhile, the logs of how the program uses memory can be utilized as debugging information collected by the controller area network (CAN).

However, the characteristics of HiL test limit the usage of common debugging techniques.

A hardware-in-the-loop (HiL) test is performed to verify the software functions mounted on automotive electronic control units (ECUs).