Process and system for semantically recognizing, correcting, and suggesting domain specific speech


Ontology type: sgo:Patent     


Patent Info

DATE

2008-06-03T00:00

AUTHORS

Patrick William Jamieson

ABSTRACT

Semantic understanding of hypotheses returned by a speech engine could improve the quality of recognition and in cases of misrecognition speed the identification of errors and potential substitutions. Unfortunately, semantic recognition using natural language parsers is hard since semantic and syntactic rules for processing language are complex and computationally expensive. Additionally, semantic recognition should be performed in a knowledge domain—a domain of interest such as radiology, pathology, or tort law. This adds additional complexity to building semantic rules. The method described achieves semantic understanding by coupling a speech recognition engine to a semantic recognizer, which draws from a database of domain sentences derived from a document corpus, and a knowledge base created for these domain sentences. The method is able to identify in near real-time the best sentence hypotheses from the speech recognizer and its associated meanings, i.e. propositions, which belong to the knowledge domain, and if no hypotheses are found mark it as invalid for easy identification. For invalid sentences, closely matched sentences from the domain database can be displayed to speed correction. The semantic propositions can be semantically typed, such as normal and abnormal, further aiding in the identification of recognition errors. The system automatically displays the semantic meaning of related ideas of valid sentences by retrieving proposition (s) from the knowledge base. More... »

Related SciGraph Publications

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/2746", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/2790", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "name": "Patrick William Jamieson", 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/bf03167667", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1051111472", 
          "https://doi.org/10.1007/bf03167667"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf03167667", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1051111472", 
          "https://doi.org/10.1007/bf03167667"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2008-06-03T00:00", 
    "description": "

Semantic understanding of hypotheses returned by a speech engine could improve the quality of recognition and in cases of misrecognition speed the identification of errors and potential substitutions. Unfortunately, semantic recognition using natural language parsers is hard since semantic and syntactic rules for processing language are complex and computationally expensive. Additionally, semantic recognition should be performed in a knowledge domain—a domain of interest such as radiology, pathology, or tort law. This adds additional complexity to building semantic rules. The method described achieves semantic understanding by coupling a speech recognition engine to a semantic recognizer, which draws from a database of domain sentences derived from a document corpus, and a knowledge base created for these domain sentences. The method is able to identify in near real-time the best sentence hypotheses from the speech recognizer and its associated meanings, i.e. propositions, which belong to the knowledge domain, and if no hypotheses are found mark it as invalid for easy identification. For invalid sentences, closely matched sentences from the domain database can be displayed to speed correction. The semantic propositions can be semantically typed, such as normal and abnormal, further aiding in the identification of recognition errors. The system automatically displays the semantic meaning of related ideas of valid sentences by retrieving proposition (s) from the knowledge base.

", "id": "sg:patent.US-7383172-B1", "keywords": [ "correcting", "domain", "semantics", "hypothesise", "speech", "recognition", "error", "substitution", "natural language", "processing", "complex", "radiology", "pathology", "additional complexity", "method", "coupling", "speech recognition", "recognizer", "database", "sentence", "corpus", "knowledge base", "speech recognizers", "meaning", "proposition", "knowledge domain", "invalid", "correction", "related idea" ], "name": "Process and system for semantically recognizing, correcting, and suggesting domain specific speech", "recipient": [ { "id": "https://www.grid.ac/institutes/grid.420982.5", "type": "Organization" } ], "sameAs": [ "https://app.dimensions.ai/details/patent/US-7383172-B1" ], "sdDataset": "patents", "sdDatePublished": "2019-04-18T10:31", "sdLicense": "https://scigraph.springernature.com/explorer/license/", "sdPublisher": { "name": "Springer Nature - SN SciGraph project", "type": "Organization" }, "sdSource": "s3://com-uberresearch-data-patents-target-20190320-rc/data/sn-export/402f166718b70575fb5d4ffe01f064d1/0000100128-0000352499/json_export_03596.jsonl", "type": "Patent" } ]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/patent.US-7383172-B1'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/patent.US-7383172-B1'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/patent.US-7383172-B1'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/patent.US-7383172-B1'


 

This table displays all metadata directly associated to this object as RDF triples.

58 TRIPLES      15 PREDICATES      45 URIs      37 LITERALS      2 BLANK NODES

Subject Predicate Object
1 sg:patent.US-7383172-B1 schema:about anzsrc-for:2746
2 anzsrc-for:2790
3 schema:author N2a13f95423134487bae5e90f3850eed2
4 schema:citation sg:pub.10.1007/bf03167667
5 schema:datePublished 2008-06-03T00:00
6 schema:description <p num="p-0001">Semantic understanding of hypotheses returned by a speech engine could improve the quality of recognition and in cases of misrecognition speed the identification of errors and potential substitutions. Unfortunately, semantic recognition using natural language parsers is hard since semantic and syntactic rules for processing language are complex and computationally expensive. Additionally, semantic recognition should be performed in a knowledge domain&#8212;a domain of interest such as radiology, pathology, or tort law. This adds additional complexity to building semantic rules. The method described achieves semantic understanding by coupling a speech recognition engine to a semantic recognizer, which draws from a database of domain sentences derived from a document corpus, and a knowledge base created for these domain sentences. The method is able to identify in near real-time the best sentence hypotheses from the speech recognizer and its associated meanings, i.e. propositions, which belong to the knowledge domain, and if no hypotheses are found mark it as invalid for easy identification. For invalid sentences, closely matched sentences from the domain database can be displayed to speed correction. The semantic propositions can be semantically typed, such as normal and abnormal, further aiding in the identification of recognition errors. The system automatically displays the semantic meaning of related ideas of valid sentences by retrieving proposition (s) from the knowledge base.</p>
7 schema:keywords additional complexity
8 complex
9 corpus
10 correcting
11 correction
12 coupling
13 database
14 domain
15 error
16 hypothesise
17 invalid
18 knowledge base
19 knowledge domain
20 meaning
21 method
22 natural language
23 pathology
24 processing
25 proposition
26 radiology
27 recognition
28 recognizer
29 related idea
30 semantics
31 sentence
32 speech
33 speech recognition
34 speech recognizers
35 substitution
36 schema:name Process and system for semantically recognizing, correcting, and suggesting domain specific speech
37 schema:recipient https://www.grid.ac/institutes/grid.420982.5
38 schema:sameAs https://app.dimensions.ai/details/patent/US-7383172-B1
39 schema:sdDatePublished 2019-04-18T10:31
40 schema:sdLicense https://scigraph.springernature.com/explorer/license/
41 schema:sdPublisher N93ca7df632bc461d8dc007c8280eae90
42 sgo:license sg:explorer/license/
43 sgo:sdDataset patents
44 rdf:type sgo:Patent
45 N2a13f95423134487bae5e90f3850eed2 rdf:first Nb5403d187a9d4f308908c379730f4e68
46 rdf:rest rdf:nil
47 N93ca7df632bc461d8dc007c8280eae90 schema:name Springer Nature - SN SciGraph project
48 rdf:type schema:Organization
49 Nb5403d187a9d4f308908c379730f4e68 schema:name Patrick William Jamieson
50 rdf:type schema:Person
51 anzsrc-for:2746 schema:inDefinedTermSet anzsrc-for:
52 rdf:type schema:DefinedTerm
53 anzsrc-for:2790 schema:inDefinedTermSet anzsrc-for:
54 rdf:type schema:DefinedTerm
55 sg:pub.10.1007/bf03167667 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051111472
56 https://doi.org/10.1007/bf03167667
57 rdf:type schema:CreativeWork
58 https://www.grid.ac/institutes/grid.420982.5 schema:Organization
 




Preview window. Press ESC to close (or click here)


...