Automatic Speech Recognition, Question Answering, Information Retrieval
Automatic Speech Recognition, Mobile Virtual Assistant
Spoken dialog systems (SDS) have been an active area of research for the past few decades. Research projects in India focus on understanding the linguistic structure of Indian languages and to make them easily representable in digital form. Structural analysis of languages coupled with SDS can create viable solutions for health- care. Vaidya is a spoken dialog system for medical diagnosis. The system is capable of providing an approximate diagnosis by accepting symptoms as free-form speech in real-time on both laptop and hand-held devices. The system focuses on challenges in speech recognition specific to Indian languages and capturing the intent of the user. Another challenge is to create models which are memory and CPU efficient for hand-held devices.
Vaidya is an example of a SDS which is focussing on Health care but the framework can be extended to many domains. The primary goal of this work was to develop a extensible model for SDS which is as domain independent as possible.
Type of Work
Software system, System design, though NOT a software
Current State of work
Technology designed and implemented
1. Any scenario where the client wants to furnish information to the consumer through a automated spoken dialog system would be a good place for Vaidya. For example, Troubleshooting, Dynamic information dissemination, interactive guidelines or manuals, etc.
Benefit - Productivity and cost of operations
1. Vaidya: A Spoken Dialog System for Health Domain - Proceedings of the 13th ICON, 2016