Standards-Compliant Voice Browser with Support for Multiple Language Understanding Implementations

Hey there,

 

last year, I published a conference paper about our efforts towards a
standards-compliant voice browser with support for multiple language
understanding Implementations. It aims at providing access to current NLU
services that provide their result in terms of intent and associated
entities in VoiceXML.

 

In this paper we suggest 2 alternatives

1.       Introduction of a new grammar definition that can be used in
VoiceXML to capture the extracted semantic information

2.       Calling a web service 

 

My hope is that this could be a first step to bridge the gap between current
efforts to modern dialog concepts like flexible

switching between user goals, custom grammar design and adaptivity to users
while remaining standards compliant.

 

The paper is available at
https://www.researchgate.net/publication/320009033_An_Open_Source_Standards-
Compliant_Voice_Browser_with_Support_for_Multiple_Language_Understanding_Imp
lementations

 

Maybe, it can also be some experience that may be used in the efforts
towards standardization efforts for voice-based personal assistants.

 

Dirk