US Patent Application 17735300. Ontology Driven Contextual Automated Speech Recognition simplified abstract
Contents
Ontology Driven Contextual Automated Speech Recognition
Organization Name
INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor(s)
Ashish R. Mittal of Bengaluru (IN)
Samarth Bharadwaj of Bangalore (IN)
Shreya Khare of Bangalore (IN)
Ontology Driven Contextual Automated Speech Recognition - A simplified explanation of the abstract
This abstract first appeared for US patent application 17735300 titled 'Ontology Driven Contextual Automated Speech Recognition
Simplified Explanation
- The patent application describes an automatic speech recognition (ASR) computing system and methodology. - The system uses a context acoustic biasing (CAB) engine to match key terms in historical textual content with concepts in an ontology data structure. - This matching process generates a contextual term list data structure that includes concept terms related to the matched key terms. - The CAB engine then generates acoustic representations of the concept terms in the contextual term list data structure. - These acoustic representations are inputted into an ASR computer model, which processes an input speech signal. - The ASR computer model uses the acoustic representations to predict a textual representation of the input speech signal. - The predicted textual representation is biased towards the acoustic representations of the concept terms in the contextual term list data structure.
Original Abstract Submitted
An automatic speech recognition (ASR) computing system and methodology are provided to predict a textual representation of received input speech data. A context acoustic biasing (CAB) engine of the ASR computing system receives historical textual content and an ontology data structure. The CAB engine matches key terms identified in the historical textual content with concepts present in the ontology data structure to generate a contextual term list data structure comprising the concept terms related to concepts matching the key terms. The CAB engine generates acoustic representations of the concept terms in the contextual term list data structure and inputs them to an ASR computer model of the ASR computing system which processes an input speech signal to generate a predicted textual representation of the input speech signal. The predicted textual representation is biased towards the acoustic representations of the concept terms in the contextual term list data structure.