Dialogue management
Assignee2236008 Ontario Inc.
InventorDarrin Kenneth John Fry
Life of this patent
Estimating the term…
Abstract
A system and method to receive a spoken utterance and convert the spoken utterance into a recognized speech results through an automatic speech recognition service. A spoken utterance into a recognized speech result through an automatic speech recognition service. The recognized speech results are interpreted through a natural language processing module. A normalizer processes the recognized speech results that transforms the recognized speech interpretations into predefined form for a given automatic speech recognition domain and further determines which automatic speech recognition domains or the recognized speech results are processed by a dedicated dialogue management proxy module or a conversation module.
Claims16
An automatic speech recognition system, comprising:
- a processor configured to receive a spoken utterance and convert the spoken utterance into a recognized speech result through an automatic speech recognition service;
- the processor is further configured to interpret the recognized speech results rendered by the automatic speech recognition service through a recognition processing module;
- the processor is further configured to process the recognized speech results through a normalization that transforms the interpreted recognized speech into a predefined form for a given automatic speech recognition domain;
- wherein the normalization further determines which automatic speech recognition domains or which recognized speech results are processed by a dedicated dialogue management proxy module and which automatic speech recognition domains or which recognized speech results are processed by a separate conversation module.
A method that convert spoken commands to text and interpret a recognized speech comprising:
- receiving a spoken utterance and converting the spoken utterance into a recognized speech result through an automatic speech recognition service;
- interpreting the recognized speech results rendered by the automatic speech recognition service through a recognition processing module;
- normalizing the recognized speech results through a normalization that transforms the interpreted recognized speech into a predefined form for a given automatic speech recognition domain;
- and
- determining which automatic speech recognition domains or which recognized speech results are processed by a dedicated dialogue management proxy module and which automatic speech recognition domains or which recognized speech results are processed by a separate conversation module.
A non-transitory machine-readable medium encoded with machine-executable instructions, wherein execution of the machine-executable instructions is for:
- receiving a spoken utterance and converting the spoken utterance into a recognized speech result through an automatic speech recognition service;
- interpreting the recognized speech results rendered by the automatic speech recognition service through a recognition processing module;
- normalizing the recognized speech results through a normalization that transforms the interpreted recognized speech into a predefined form for a given automatic speech recognition domain;
- and
- determining which automatic speech recognition domains or which recognized speech results are processed by a dedicated dialogue management proxy module and which automatic speech recognition domains or which recognized speech results are processed by a separate conversation module.
Dependencies are inferred from the claim text.