Figure 1 - uploaded by Jimcymol James
Content may be subject to copyright.
![Architecture of the Voice Assistant [4]](profile/Jimcymol-James/publication/333893369/figure/fig1/AS:771766779658240@1561014947099/Architecture-of-the-Voice-Assistant-4.png)
Architecture of the Voice Assistant [4]
Source publication
![Figure 1. Architecture of the Voice Assistant [4]](profile/Jimcymol-James/publication/333893369/figure/fig1/AS:771766779658240@1561014947099/Architecture-of-the-Voice-Assistant-4_Q320.jpg)
This technical paper presents the design and development of an Artificial Intelligence Voice Assistant for a University campus that can interact with the user and answer questions related to its domain of knowledge. It uses Artificial Intelligence to enhance user satisfaction by improving one to one communication. It will take the user's voice as a...
Context in source publication
Similar publications
Wake-word detection is an indispensable technology for preventing virtual voice agents from being unintentionally triggered. Although various neural networks were proposed for wake-word detection, less attention has been paid to efficient corpus design, which we address in this study. For this purpose, we collected speech data via a crowdsourcing p...
Citations
This chapter entitled “Virtual Moratorium System” gathers data about why the customers have opted for the moratorium. This is a web and android application. We have developed a chatbot for easy communication. In today's time, it is difficult to use physical banking services to resolve the issue. By using a proposed system, the banker will get all the information regarding a customer who has opted for the moratorium. The user will interact with the chatbot and submit the moratorium request. The chatbot will ask questions based on customers’ responses. Rasa Natural language Processing (NLP) and Rasa Natural Language Understanding algorithm will classify the intents from user response. Intents will be compared with predefined patterns to extract the specific data. These responses will be stored in the NoSQL (MongoDB) database. These data will be shared with the banker, who will further analyze them. The main purpose of this chapter is to help the banker to know whether the customer who has applied for the moratorium is genuine. With this system, both the customer and the banker will be able to save their time and efforts. The proposed system will allow the customers to register moratorium at anytime and anywhere using a dedicated web platform and android application as well as some social media platform. Complete chatbot moratorium system will be encrypted with secure encryption algorithms (AES‐256, SSH). This system does not contain only moratorium functionalities but also has some extra features like news and updates that are crawled from various genuine news platforms and official banking sites. With all of these features, REST API services are also available for further enhancements and integration to multiple platforms.
