Improving command and control speech recognition on mobile devices: using predictive user models for language modeling View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2007-03

AUTHORS

Tim Paek, David Maxwell Chickering

ABSTRACT

Command and control (C&C) speech recognition allows users to interact with a system by speaking commands or asking questions restricted to a fixed grammar containing pre-defined phrases. Whereas C&C interaction has been commonplace in telephony and accessibility systems for many years, only recently have mobile devices had the memory and processing capacity to support client-side speech recognition. Given the personal nature of mobile devices, statistical models that can predict commands based in part on past user behavior hold promise for improving C&C recognition accuracy. For example, if a user calls a spouse at the end of every workday, the language model could be adapted to weight the spouse more than other contacts during that time. In this paper, we describe and assess statistical models learned from a large population of users for predicting the next user command of a commercial C&C application. We explain how these models were used for language modeling, and evaluate their performance in terms of task completion. The best performing model achieved a 26% relative reduction in error rate compared to the base system. Finally, we investigate the effects of personalization on performance at different learning rates via online updating of model parameters based on individual user data. Personalization significantly increased relative reduction in error rate by an additional 5%. More... »

PAGES

93-117

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s11257-006-9021-6

DOI

http://dx.doi.org/10.1007/s11257-006-9021-6

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1011323625


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

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/2008/1701", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Psychology", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/17", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Psychology and Cognitive Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Microsoft (United States)", 
          "id": "https://www.grid.ac/institutes/grid.419815.0", 
          "name": [
            "Microsoft Research, Redmond, WA, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Paek", 
        "givenName": "Tim", 
        "id": "sg:person.012601701553.65", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012601701553.65"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Microsoft (United States)", 
          "id": "https://www.grid.ac/institutes/grid.419815.0", 
          "name": [
            "Microsoft Research, Redmond, WA, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Chickering", 
        "givenName": "David Maxwell", 
        "id": "sg:person.011240332636.47", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011240332636.47"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/3-540-44566-8_1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1001994381", 
          "https://doi.org/10.1007/3-540-44566-8_1"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-44566-8_1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1001994381", 
          "https://doi.org/10.1007/3-540-44566-8_1"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/384076.384085", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018005848"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/1-4020-3075-4_19", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1024488859", 
          "https://doi.org/10.1007/1-4020-3075-4_19"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/1-4020-3075-4_19", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1024488859", 
          "https://doi.org/10.1007/1-4020-3075-4_19"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf00116900", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1025237168", 
          "https://doi.org/10.1007/bf00116900"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/s0167-6393(98)00005-3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1027261898"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1011117102175", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1039785209", 
          "https://doi.org/10.1023/a:1011117102175"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11257-006-9020-7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1041445852", 
          "https://doi.org/10.1007/s11257-006-9020-7"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/089976698300017197", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053132543"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/5.880083", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061180209"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2007-03", 
    "datePublishedReg": "2007-03-01", 
    "description": "Command and control (C&C) speech recognition allows users to interact with a system by speaking commands or asking questions restricted to a fixed grammar containing pre-defined phrases. Whereas C&C interaction has been commonplace in telephony and accessibility systems for many years, only recently have mobile devices had the memory and processing capacity to support client-side speech recognition. Given the personal nature of mobile devices, statistical models that can predict commands based in part on past user behavior hold promise for improving C&C recognition accuracy. For example, if a user calls a spouse at the end of every workday, the language model could be adapted to weight the spouse more than other contacts during that time. In this paper, we describe and assess statistical models learned from a large population of users for predicting the next user command of a commercial C&C application. We explain how these models were used for language modeling, and evaluate their performance in terms of task completion. The best performing model achieved a 26% relative reduction in error rate compared to the base system. Finally, we investigate the effects of personalization on performance at different learning rates via online updating of model parameters based on individual user data. Personalization significantly increased relative reduction in error rate by an additional 5%.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/s11257-006-9021-6", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1031131", 
        "issn": [
          "0924-1868", 
          "1573-1391"
        ], 
        "name": "User Modeling and User-Adapted Interaction", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "1-2", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "17"
      }
    ], 
    "name": "Improving command and control speech recognition on mobile devices: using predictive user models for language modeling", 
    "pagination": "93-117", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "35f33a75fa00403cb47c50dc453cbefb525480f11f69ff8ba89875a5b55d8ef0"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s11257-006-9021-6"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1011323625"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s11257-006-9021-6", 
      "https://app.dimensions.ai/details/publication/pub.1011323625"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-10T19:11", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000001_0000000264/records_8678_00000520.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "http://link.springer.com/10.1007%2Fs11257-006-9021-6"
  }
]
 

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/pub.10.1007/s11257-006-9021-6'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s11257-006-9021-6'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s11257-006-9021-6'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s11257-006-9021-6'


 

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

100 TRIPLES      21 PREDICATES      36 URIs      19 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s11257-006-9021-6 schema:about anzsrc-for:17
2 anzsrc-for:1701
3 schema:author Ncb35daf41383495ab179ebe245c9f7b4
4 schema:citation sg:pub.10.1007/1-4020-3075-4_19
5 sg:pub.10.1007/3-540-44566-8_1
6 sg:pub.10.1007/bf00116900
7 sg:pub.10.1007/s11257-006-9020-7
8 sg:pub.10.1023/a:1011117102175
9 https://doi.org/10.1016/s0167-6393(98)00005-3
10 https://doi.org/10.1109/5.880083
11 https://doi.org/10.1145/384076.384085
12 https://doi.org/10.1162/089976698300017197
13 schema:datePublished 2007-03
14 schema:datePublishedReg 2007-03-01
15 schema:description Command and control (C&C) speech recognition allows users to interact with a system by speaking commands or asking questions restricted to a fixed grammar containing pre-defined phrases. Whereas C&C interaction has been commonplace in telephony and accessibility systems for many years, only recently have mobile devices had the memory and processing capacity to support client-side speech recognition. Given the personal nature of mobile devices, statistical models that can predict commands based in part on past user behavior hold promise for improving C&C recognition accuracy. For example, if a user calls a spouse at the end of every workday, the language model could be adapted to weight the spouse more than other contacts during that time. In this paper, we describe and assess statistical models learned from a large population of users for predicting the next user command of a commercial C&C application. We explain how these models were used for language modeling, and evaluate their performance in terms of task completion. The best performing model achieved a 26% relative reduction in error rate compared to the base system. Finally, we investigate the effects of personalization on performance at different learning rates via online updating of model parameters based on individual user data. Personalization significantly increased relative reduction in error rate by an additional 5%.
16 schema:genre research_article
17 schema:inLanguage en
18 schema:isAccessibleForFree false
19 schema:isPartOf N88c3ac65d92b4c66b91fa7b712a13412
20 Nb827502556204370939da5c0046d0a61
21 sg:journal.1031131
22 schema:name Improving command and control speech recognition on mobile devices: using predictive user models for language modeling
23 schema:pagination 93-117
24 schema:productId N4da496287f144da1860247e2cad49f16
25 N866b63a10f684c97a800f8b6858070e7
26 Ndf000546ebf74bad8b95dc44aba8e08d
27 schema:sameAs https://app.dimensions.ai/details/publication/pub.1011323625
28 https://doi.org/10.1007/s11257-006-9021-6
29 schema:sdDatePublished 2019-04-10T19:11
30 schema:sdLicense https://scigraph.springernature.com/explorer/license/
31 schema:sdPublisher Ne25974ae4cd840adb0c50d2b750012f6
32 schema:url http://link.springer.com/10.1007%2Fs11257-006-9021-6
33 sgo:license sg:explorer/license/
34 sgo:sdDataset articles
35 rdf:type schema:ScholarlyArticle
36 N4da496287f144da1860247e2cad49f16 schema:name doi
37 schema:value 10.1007/s11257-006-9021-6
38 rdf:type schema:PropertyValue
39 N866b63a10f684c97a800f8b6858070e7 schema:name dimensions_id
40 schema:value pub.1011323625
41 rdf:type schema:PropertyValue
42 N88c3ac65d92b4c66b91fa7b712a13412 schema:volumeNumber 17
43 rdf:type schema:PublicationVolume
44 Nb827502556204370939da5c0046d0a61 schema:issueNumber 1-2
45 rdf:type schema:PublicationIssue
46 Ncb35daf41383495ab179ebe245c9f7b4 rdf:first sg:person.012601701553.65
47 rdf:rest Nd3313f76c0144aa3b4da9ea5122d93a7
48 Nd3313f76c0144aa3b4da9ea5122d93a7 rdf:first sg:person.011240332636.47
49 rdf:rest rdf:nil
50 Ndf000546ebf74bad8b95dc44aba8e08d schema:name readcube_id
51 schema:value 35f33a75fa00403cb47c50dc453cbefb525480f11f69ff8ba89875a5b55d8ef0
52 rdf:type schema:PropertyValue
53 Ne25974ae4cd840adb0c50d2b750012f6 schema:name Springer Nature - SN SciGraph project
54 rdf:type schema:Organization
55 anzsrc-for:17 schema:inDefinedTermSet anzsrc-for:
56 schema:name Psychology and Cognitive Sciences
57 rdf:type schema:DefinedTerm
58 anzsrc-for:1701 schema:inDefinedTermSet anzsrc-for:
59 schema:name Psychology
60 rdf:type schema:DefinedTerm
61 sg:journal.1031131 schema:issn 0924-1868
62 1573-1391
63 schema:name User Modeling and User-Adapted Interaction
64 rdf:type schema:Periodical
65 sg:person.011240332636.47 schema:affiliation https://www.grid.ac/institutes/grid.419815.0
66 schema:familyName Chickering
67 schema:givenName David Maxwell
68 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011240332636.47
69 rdf:type schema:Person
70 sg:person.012601701553.65 schema:affiliation https://www.grid.ac/institutes/grid.419815.0
71 schema:familyName Paek
72 schema:givenName Tim
73 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012601701553.65
74 rdf:type schema:Person
75 sg:pub.10.1007/1-4020-3075-4_19 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024488859
76 https://doi.org/10.1007/1-4020-3075-4_19
77 rdf:type schema:CreativeWork
78 sg:pub.10.1007/3-540-44566-8_1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1001994381
79 https://doi.org/10.1007/3-540-44566-8_1
80 rdf:type schema:CreativeWork
81 sg:pub.10.1007/bf00116900 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025237168
82 https://doi.org/10.1007/bf00116900
83 rdf:type schema:CreativeWork
84 sg:pub.10.1007/s11257-006-9020-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041445852
85 https://doi.org/10.1007/s11257-006-9020-7
86 rdf:type schema:CreativeWork
87 sg:pub.10.1023/a:1011117102175 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039785209
88 https://doi.org/10.1023/a:1011117102175
89 rdf:type schema:CreativeWork
90 https://doi.org/10.1016/s0167-6393(98)00005-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027261898
91 rdf:type schema:CreativeWork
92 https://doi.org/10.1109/5.880083 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061180209
93 rdf:type schema:CreativeWork
94 https://doi.org/10.1145/384076.384085 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018005848
95 rdf:type schema:CreativeWork
96 https://doi.org/10.1162/089976698300017197 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053132543
97 rdf:type schema:CreativeWork
98 https://www.grid.ac/institutes/grid.419815.0 schema:alternateName Microsoft (United States)
99 schema:name Microsoft Research, Redmond, WA, USA
100 rdf:type schema:Organization
 




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


...