Theoretical learning guarantees applied to acoustic modeling View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2019-12

AUTHORS

Christopher D. Shulby, Martha D. Ferreira, Rodrigo F. de Mello, Sandra M. Aluisio

ABSTRACT

In low-resource scenarios, for example, small datasets or a lack in computational resources available, state-of-the-art deep learning methods for speech recognition have been known to fail. It is possible to achieve more robust models if care is taken to ensure the learning guarantees provided by the statistical learning theory. This work presents a shallow and hybrid approach using a convolutional neural network feature extractor fed into a hierarchical tree of support vector machines for classification. Here, we show that gross errors present even in state-of-the-art systems can be avoided and that an accurate acoustic model can be built in a hierarchical fashion. Furthermore, we present proof that our algorithm does adhere to the learning guarantees provided by the statistical learning theory. The acoustic model produced in this work outperforms traditional hidden Markov models, and the hierarchical support vector machine tree outperforms a multi-class multilayer perceptron classifier using the same features. More importantly, we isolate the performance of the acoustic model and provide results on both the frame and phoneme level, considering the true robustness of the model. We show that even with a small amount of data, accurate and robust recognition rates can be obtained. More... »

PAGES

1

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1186/s13173-018-0081-3

DOI

http://dx.doi.org/10.1186/s13173-018-0081-3

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1111155042


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/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "University of Sao Paulo", 
          "id": "https://www.grid.ac/institutes/grid.11899.38", 
          "name": [
            "Samsung SIDI Institute, Rua Agua\u00e7u, 171, 13098-321, Campinas, SP, Brazil", 
            "Institute of Mathematical and Computer Sciences, University of S\u00e3o Paulo, Avenida Trabalhador S\u00e3o-Carlense, 400, 13566-590, S\u00e3o Carlos, SP, Brazil"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Shulby", 
        "givenName": "Christopher D.", 
        "id": "sg:person.015201346171.82", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015201346171.82"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Sao Paulo", 
          "id": "https://www.grid.ac/institutes/grid.11899.38", 
          "name": [
            "Institute of Mathematical and Computer Sciences, University of S\u00e3o Paulo, Avenida Trabalhador S\u00e3o-Carlense, 400, 13566-590, S\u00e3o Carlos, SP, Brazil"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Ferreira", 
        "givenName": "Martha D.", 
        "id": "sg:person.015717216300.47", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015717216300.47"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Sao Paulo", 
          "id": "https://www.grid.ac/institutes/grid.11899.38", 
          "name": [
            "Institute of Mathematical and Computer Sciences, University of S\u00e3o Paulo, Avenida Trabalhador S\u00e3o-Carlense, 400, 13566-590, S\u00e3o Carlos, SP, Brazil"
          ], 
          "type": "Organization"
        }, 
        "familyName": "de Mello", 
        "givenName": "Rodrigo F.", 
        "id": "sg:person.07524107231.42", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07524107231.42"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Sao Paulo", 
          "id": "https://www.grid.ac/institutes/grid.11899.38", 
          "name": [
            "Institute of Mathematical and Computer Sciences, University of S\u00e3o Paulo, Avenida Trabalhador S\u00e3o-Carlense, 400, 13566-590, S\u00e3o Carlos, SP, Brazil"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Aluisio", 
        "givenName": "Sandra M.", 
        "id": "sg:person.01232077143.12", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01232077143.12"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1186/s13636-015-0068-3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1005261561", 
          "https://doi.org/10.1186/s13636-015-0068-3"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/s13636-015-0068-3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1005261561", 
          "https://doi.org/10.1186/s13636-015-0068-3"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/nature14539", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1010020120", 
          "https://doi.org/10.1038/nature14539"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1113/jphysiol.1962.sp006837", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1037811822"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0004-3702(89)90049-0", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1040179661"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0004-3702(89)90049-0", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1040179661"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-30568-2_13", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1042786652", 
          "https://doi.org/10.1007/978-3-540-30568-2_13"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-30568-2_13", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1042786652", 
          "https://doi.org/10.1007/978-3-540-30568-2_13"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-319-13623-3_15", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1043170142", 
          "https://doi.org/10.1007/978-3-319-13623-3_15"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.5772/17600", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1051562518"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/s0167-6393(00)00007-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053319917"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/29.21701", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061144393"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/29.46546", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061144561"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/5.726791", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061179979"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/msp.2012.2205597", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061423808"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tasl.2008.2010286", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061516216"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tasl.2011.2109382", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061516710"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/taslp.2014.2339736", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061517330"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/taslp.2016.2621675", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061517912"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1121/1.2935783", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1062319069"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.17485/ijst/2015/v8i35/80681", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1068338435"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/taslp.2017.2765819", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1092392163"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.eswa.2017.10.052", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1092415128"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.2015.7178964", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093288270"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/asru.2013.6707742", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093592115"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.2013.6639347", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094334987"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icce.2016.7430534", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094724939"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.2012.6288864", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095072289"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/bracis.2017.62", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1100254410"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1613/jair.953", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1105579550"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2019-12", 
    "datePublishedReg": "2019-12-01", 
    "description": "In low-resource scenarios, for example, small datasets or a lack in computational resources available, state-of-the-art deep learning methods for speech recognition have been known to fail. It is possible to achieve more robust models if care is taken to ensure the learning guarantees provided by the statistical learning theory. This work presents a shallow and hybrid approach using a convolutional neural network feature extractor fed into a hierarchical tree of support vector machines for classification. Here, we show that gross errors present even in state-of-the-art systems can be avoided and that an accurate acoustic model can be built in a hierarchical fashion. Furthermore, we present proof that our algorithm does adhere to the learning guarantees provided by the statistical learning theory. The acoustic model produced in this work outperforms traditional hidden Markov models, and the hierarchical support vector machine tree outperforms a multi-class multilayer perceptron classifier using the same features. More importantly, we isolate the performance of the acoustic model and provide results on both the frame and phoneme level, considering the true robustness of the model. We show that even with a small amount of data, accurate and robust recognition rates can be obtained.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1186/s13173-018-0081-3", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isPartOf": [
      {
        "id": "sg:journal.1136200", 
        "issn": [
          "0104-6500", 
          "1678-4804"
        ], 
        "name": "Journal of the Brazilian Computer Society", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "1", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "25"
      }
    ], 
    "name": "Theoretical learning guarantees applied to acoustic modeling", 
    "pagination": "1", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "8e91e174b5158c70d8cec6243489edcfb77353f87d0ced15a1a6f39fb7db104c"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1186/s13173-018-0081-3"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1111155042"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1186/s13173-018-0081-3", 
      "https://app.dimensions.ai/details/publication/pub.1111155042"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T08:34", 
    "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/v90/0000000311_0000000311/records_55454_00000000.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://link.springer.com/10.1186%2Fs13173-018-0081-3"
  }
]
 

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.10.1186/s13173-018-0081-3'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1186/s13173-018-0081-3'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1186/s13173-018-0081-3'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1186/s13173-018-0081-3'


 

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

168 TRIPLES      21 PREDICATES      54 URIs      19 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1186/s13173-018-0081-3 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N14c507bae09e4a418ac55539cf0535ca
4 schema:citation sg:pub.10.1007/978-3-319-13623-3_15
5 sg:pub.10.1007/978-3-540-30568-2_13
6 sg:pub.10.1038/nature14539
7 sg:pub.10.1186/s13636-015-0068-3
8 https://doi.org/10.1016/0004-3702(89)90049-0
9 https://doi.org/10.1016/j.eswa.2017.10.052
10 https://doi.org/10.1016/s0167-6393(00)00007-8
11 https://doi.org/10.1109/29.21701
12 https://doi.org/10.1109/29.46546
13 https://doi.org/10.1109/5.726791
14 https://doi.org/10.1109/asru.2013.6707742
15 https://doi.org/10.1109/bracis.2017.62
16 https://doi.org/10.1109/icassp.2012.6288864
17 https://doi.org/10.1109/icassp.2013.6639347
18 https://doi.org/10.1109/icassp.2015.7178964
19 https://doi.org/10.1109/icce.2016.7430534
20 https://doi.org/10.1109/msp.2012.2205597
21 https://doi.org/10.1109/tasl.2008.2010286
22 https://doi.org/10.1109/tasl.2011.2109382
23 https://doi.org/10.1109/taslp.2014.2339736
24 https://doi.org/10.1109/taslp.2016.2621675
25 https://doi.org/10.1109/taslp.2017.2765819
26 https://doi.org/10.1113/jphysiol.1962.sp006837
27 https://doi.org/10.1121/1.2935783
28 https://doi.org/10.1613/jair.953
29 https://doi.org/10.17485/ijst/2015/v8i35/80681
30 https://doi.org/10.5772/17600
31 schema:datePublished 2019-12
32 schema:datePublishedReg 2019-12-01
33 schema:description In low-resource scenarios, for example, small datasets or a lack in computational resources available, state-of-the-art deep learning methods for speech recognition have been known to fail. It is possible to achieve more robust models if care is taken to ensure the learning guarantees provided by the statistical learning theory. This work presents a shallow and hybrid approach using a convolutional neural network feature extractor fed into a hierarchical tree of support vector machines for classification. Here, we show that gross errors present even in state-of-the-art systems can be avoided and that an accurate acoustic model can be built in a hierarchical fashion. Furthermore, we present proof that our algorithm does adhere to the learning guarantees provided by the statistical learning theory. The acoustic model produced in this work outperforms traditional hidden Markov models, and the hierarchical support vector machine tree outperforms a multi-class multilayer perceptron classifier using the same features. More importantly, we isolate the performance of the acoustic model and provide results on both the frame and phoneme level, considering the true robustness of the model. We show that even with a small amount of data, accurate and robust recognition rates can be obtained.
34 schema:genre research_article
35 schema:inLanguage en
36 schema:isAccessibleForFree true
37 schema:isPartOf N0b82460bcf1b48f1be5f3f11749d0a2f
38 N9f91f79b6c4143978902780125390e2a
39 sg:journal.1136200
40 schema:name Theoretical learning guarantees applied to acoustic modeling
41 schema:pagination 1
42 schema:productId N0a7126b4a9524a459cd57aa66d8c9be7
43 N5c9f551f13fd4224911a7528b88bcc91
44 Nd8c9581cad6445ec910115bdebbf29c3
45 schema:sameAs https://app.dimensions.ai/details/publication/pub.1111155042
46 https://doi.org/10.1186/s13173-018-0081-3
47 schema:sdDatePublished 2019-04-11T08:34
48 schema:sdLicense https://scigraph.springernature.com/explorer/license/
49 schema:sdPublisher Nee0680cc705547b3934d3cc629164e35
50 schema:url https://link.springer.com/10.1186%2Fs13173-018-0081-3
51 sgo:license sg:explorer/license/
52 sgo:sdDataset articles
53 rdf:type schema:ScholarlyArticle
54 N0a7126b4a9524a459cd57aa66d8c9be7 schema:name readcube_id
55 schema:value 8e91e174b5158c70d8cec6243489edcfb77353f87d0ced15a1a6f39fb7db104c
56 rdf:type schema:PropertyValue
57 N0b82460bcf1b48f1be5f3f11749d0a2f schema:issueNumber 1
58 rdf:type schema:PublicationIssue
59 N14c507bae09e4a418ac55539cf0535ca rdf:first sg:person.015201346171.82
60 rdf:rest Ne1b10fc0e0a54e0fa73603a17484265e
61 N1bff48ac88574be394585f6f7b67d06b rdf:first sg:person.01232077143.12
62 rdf:rest rdf:nil
63 N4a7df9283b24421f8fb2006f55387432 rdf:first sg:person.07524107231.42
64 rdf:rest N1bff48ac88574be394585f6f7b67d06b
65 N5c9f551f13fd4224911a7528b88bcc91 schema:name doi
66 schema:value 10.1186/s13173-018-0081-3
67 rdf:type schema:PropertyValue
68 N9f91f79b6c4143978902780125390e2a schema:volumeNumber 25
69 rdf:type schema:PublicationVolume
70 Nd8c9581cad6445ec910115bdebbf29c3 schema:name dimensions_id
71 schema:value pub.1111155042
72 rdf:type schema:PropertyValue
73 Ne1b10fc0e0a54e0fa73603a17484265e rdf:first sg:person.015717216300.47
74 rdf:rest N4a7df9283b24421f8fb2006f55387432
75 Nee0680cc705547b3934d3cc629164e35 schema:name Springer Nature - SN SciGraph project
76 rdf:type schema:Organization
77 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
78 schema:name Information and Computing Sciences
79 rdf:type schema:DefinedTerm
80 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
81 schema:name Artificial Intelligence and Image Processing
82 rdf:type schema:DefinedTerm
83 sg:journal.1136200 schema:issn 0104-6500
84 1678-4804
85 schema:name Journal of the Brazilian Computer Society
86 rdf:type schema:Periodical
87 sg:person.01232077143.12 schema:affiliation https://www.grid.ac/institutes/grid.11899.38
88 schema:familyName Aluisio
89 schema:givenName Sandra M.
90 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01232077143.12
91 rdf:type schema:Person
92 sg:person.015201346171.82 schema:affiliation https://www.grid.ac/institutes/grid.11899.38
93 schema:familyName Shulby
94 schema:givenName Christopher D.
95 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015201346171.82
96 rdf:type schema:Person
97 sg:person.015717216300.47 schema:affiliation https://www.grid.ac/institutes/grid.11899.38
98 schema:familyName Ferreira
99 schema:givenName Martha D.
100 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015717216300.47
101 rdf:type schema:Person
102 sg:person.07524107231.42 schema:affiliation https://www.grid.ac/institutes/grid.11899.38
103 schema:familyName de Mello
104 schema:givenName Rodrigo F.
105 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07524107231.42
106 rdf:type schema:Person
107 sg:pub.10.1007/978-3-319-13623-3_15 schema:sameAs https://app.dimensions.ai/details/publication/pub.1043170142
108 https://doi.org/10.1007/978-3-319-13623-3_15
109 rdf:type schema:CreativeWork
110 sg:pub.10.1007/978-3-540-30568-2_13 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042786652
111 https://doi.org/10.1007/978-3-540-30568-2_13
112 rdf:type schema:CreativeWork
113 sg:pub.10.1038/nature14539 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010020120
114 https://doi.org/10.1038/nature14539
115 rdf:type schema:CreativeWork
116 sg:pub.10.1186/s13636-015-0068-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1005261561
117 https://doi.org/10.1186/s13636-015-0068-3
118 rdf:type schema:CreativeWork
119 https://doi.org/10.1016/0004-3702(89)90049-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040179661
120 rdf:type schema:CreativeWork
121 https://doi.org/10.1016/j.eswa.2017.10.052 schema:sameAs https://app.dimensions.ai/details/publication/pub.1092415128
122 rdf:type schema:CreativeWork
123 https://doi.org/10.1016/s0167-6393(00)00007-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053319917
124 rdf:type schema:CreativeWork
125 https://doi.org/10.1109/29.21701 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061144393
126 rdf:type schema:CreativeWork
127 https://doi.org/10.1109/29.46546 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061144561
128 rdf:type schema:CreativeWork
129 https://doi.org/10.1109/5.726791 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061179979
130 rdf:type schema:CreativeWork
131 https://doi.org/10.1109/asru.2013.6707742 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093592115
132 rdf:type schema:CreativeWork
133 https://doi.org/10.1109/bracis.2017.62 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100254410
134 rdf:type schema:CreativeWork
135 https://doi.org/10.1109/icassp.2012.6288864 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095072289
136 rdf:type schema:CreativeWork
137 https://doi.org/10.1109/icassp.2013.6639347 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094334987
138 rdf:type schema:CreativeWork
139 https://doi.org/10.1109/icassp.2015.7178964 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093288270
140 rdf:type schema:CreativeWork
141 https://doi.org/10.1109/icce.2016.7430534 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094724939
142 rdf:type schema:CreativeWork
143 https://doi.org/10.1109/msp.2012.2205597 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061423808
144 rdf:type schema:CreativeWork
145 https://doi.org/10.1109/tasl.2008.2010286 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061516216
146 rdf:type schema:CreativeWork
147 https://doi.org/10.1109/tasl.2011.2109382 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061516710
148 rdf:type schema:CreativeWork
149 https://doi.org/10.1109/taslp.2014.2339736 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061517330
150 rdf:type schema:CreativeWork
151 https://doi.org/10.1109/taslp.2016.2621675 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061517912
152 rdf:type schema:CreativeWork
153 https://doi.org/10.1109/taslp.2017.2765819 schema:sameAs https://app.dimensions.ai/details/publication/pub.1092392163
154 rdf:type schema:CreativeWork
155 https://doi.org/10.1113/jphysiol.1962.sp006837 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037811822
156 rdf:type schema:CreativeWork
157 https://doi.org/10.1121/1.2935783 schema:sameAs https://app.dimensions.ai/details/publication/pub.1062319069
158 rdf:type schema:CreativeWork
159 https://doi.org/10.1613/jair.953 schema:sameAs https://app.dimensions.ai/details/publication/pub.1105579550
160 rdf:type schema:CreativeWork
161 https://doi.org/10.17485/ijst/2015/v8i35/80681 schema:sameAs https://app.dimensions.ai/details/publication/pub.1068338435
162 rdf:type schema:CreativeWork
163 https://doi.org/10.5772/17600 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051562518
164 rdf:type schema:CreativeWork
165 https://www.grid.ac/institutes/grid.11899.38 schema:alternateName University of Sao Paulo
166 schema:name Institute of Mathematical and Computer Sciences, University of São Paulo, Avenida Trabalhador São-Carlense, 400, 13566-590, São Carlos, SP, Brazil
167 Samsung SIDI Institute, Rua Aguaçu, 171, 13098-321, Campinas, SP, Brazil
168 rdf:type schema:Organization
 




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


...