In this Google Pi, Raspberry Pi is used as a core system. Respeaker a 4 Mic array is connected with Raspberry Pi to receive voice commands from a distance. For Object recognition and Currency recognition, Deep learning is used. For Voice assistance and YouTube Google API is used and also customized. It will be a friendly device for blind people. For object and currency recognition Web camera or Mobile camera can be interfaced with the Raspberry Pi.
Nowadays, there are a lot of Voice assistance devices such as Amazon Echo, Google Home Mini, etc. Likewise this Google Pi is also one kind of voice assistant device which is mainly for visually impaired people to fulfil their needs. It has 4 Great Features, they are
- Currency Recognition?? This will be helpful for Blind people while doing Purchase
- Object Recognition?? This will be helpful to know the object or vehicle present in front of them
- Voice assistance?? This will be helpful for asking about the weather, General?knowledge, Jokes, etc.
- YouTube support ? This will be helpful to listen to music and any other educational audio from YouTube Video
In the existing system, there are a lot of disadvantages which stopped only up to voice assistance, none other than features. Some device works only by getting the voice input from the USB Mic which should be placed near to the mouth, else input given through mobile
- Hard to setup
- Needs more components
- Needs to give voice command directly to mic
- Not possible control from distance
In this proposed system, all old disadvantages get broken by this new Google Pi. Through deep?Learning application classifications are more accurate, for voice assistant by using Google API?the responses are faster as well as more accurate. Re-speaker a 4 Mic array, helps to give voice?command from distance and from any direction
- Can give voice command from anywhere in the room
- Easy to setup compared to old methods
- Accuracy of output is increased
- User friendly system
- Raspberry pi connects the whole system to Google assistant API
- Re-speaker mic and speaker module is connected to raspberry pi
- Re-speaker is used for audio input and output
- Re-speaker which has a 40 pin interface directly plugged in the Raspberry Pi 40 Pin GPIO. Then for echoing the voice response from the system, a 3.5mm audio speaker is connected to the audio jack of the Raspberry Pi.
- Raspberry Pi 3
- Respeaker 4 Mic Array
- 16GB Class 10 SD Card
- Laptop Speaker with 3.5mm Audio Jack
- Power adapter with Type-B USB Cable
- USB Camera?/ Android Mobile
- Raspbian Image
- SD Card Formatter
- Etcher/Win32 disk imager
 Mummaka Sai Srinath and Manepalli Nanda Kishore, ? Interactive Home Automation System With Google Assistant ? International Journal Of Pure and Applied Mathematics, Volume 119, No.12, 14083-14086, 2018.
 P. Milhorat, S. Schogl, G. Chollet et all ?Building the Next? Generation of Personal Digital Assistants? 1st International Conference on Advanced Technologies for Signal and Image Processing ? ATSIP?2014, March 17-19, 2014, Sousse, Tunisia, pp.458?463.
 V. Kepuska and G. Bohouta, ?Next Generation of Virtulal Personal Assistants (Microsoft Cortana, Apple Siri, Amazon Alexa and Google Home)?, 2018 IEEE 8thAnnual Computing and Communication Workshop and Conference 8-10 Jan. 2018 Las Vegas, USA, pp.99?103.
 P. J. Young, J. H. Jin, S. Woo and D. H. Lee, ?Bad Voice: Soundless Voice-control Replay Attack on Modern Smartphones?, 2016 Eigth International Conference on Ubiquitous and Future Networks (ICUFN), Vienna, Austria, pp. 882?887.
 M. Ceaparu, S.A. Toma, S. Seg?rceanu and I. Gav?t, ?Voice-based User Interaction System for Call-Centers, Using a Small Vocabulary for Romanian?, The 12th International Conference on Communications, COMM 2018, 14-16 June, 2018, Bucharest, Romania.