Semantic Interpretation for Speech Recognition explained

Semantic Interpretation for Speech Recognition (SISR) defines the syntax and semantics of annotations to grammar rules in the Speech Recognition Grammar Specification (SRGS). Since 5 April 2007, it is a World Wide Web Consortium recommendation.^[1]

By building upon SRGS grammars, it allows voice browsers via ECMAScript to semantically interpret complex grammars and provide the information back to the application. For example, it allows utterances like "I would like a Coca-cola and three large pizzas with pepperoni and mushrooms." to be interpreted into an object that can be understood by an application. For example, the utterance could produce the following object named : If used against this grammar that includes SISR markup in addition to the standard SRGS grammar in XML format:

I would like a out.drink = new Object; out.drink.liquid=rules.drink.type; out.drink.drinksize=rules.drink.drinksize; and out.pizza=rules.pizza; coke pepsi coca colaout="coke"; out="medium"; smallout="small"; medium largeout="large"; regularout="medium"; out=new Array; out.push(rules.top); and out.push(rules.top); anchovies pepperoni mushroomout="mushrooms"; mushrooms out.drinksize=rules.foodsize; out.type=rules.kindofdrink; out.pizzasize=rules.foodsize; out.number=rules.number; pizzas with out.topping=rules.tops; out=1; a one twoout=2; threeout=3;

See also

• VoiceXML
• SRGS

External links

• SRGS Specification (W3C Recommendation)
• SISR Specification (W3C Recommendation)
• W3C's Voice Browser Working Group

Notes and References

1. http://www.w3.org/TR/semantic-interpretation/ Semantic Interpretation for Speech Recognition (SISR) Version 1.0