Spectral Reconstruction and Noise Model Estimation Based on a Masking Model for Noise Robust Speech Recognition View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2017-09

AUTHORS

Jose A. Gonzalez, Angel M. Gómez, Antonio M. Peinado, Ning Ma, Jon Barker

ABSTRACT

An effective way to increase noise robustness in automatic speech recognition (ASR) systems is feature enhancement based on an analytical distortion model that describes the effects of noise on the speech features. One of such distortion models that has been reported to achieve a good trade-off between accuracy and simplicity is the masking model. Under this model, speech distortion caused by environmental noise is seen as a spectral mask and, as a result, noisy speech features can be either reliable (speech is not masked by noise) or unreliable (speech is masked). In this paper, we present a detailed overview of this model and its applications to noise robust ASR. Firstly, using the masking model, we derive a spectral reconstruction technique aimed at enhancing the noisy speech features. Two problems must be solved in order to perform spectral reconstruction using the masking model: (1) mask estimation, i.e. determining the reliability of the noisy features, and (2) feature imputation, i.e. estimating speech for the unreliable features. Unlike missing data imputation techniques where the two problems are considered as independent, our technique jointly addresses them by exploiting a priori knowledge of the speech and noise sources in the form of a statistical model. Secondly, we propose an algorithm for estimating the noise model required by the feature enhancement technique. The proposed algorithm fits a Gaussian mixture model to the noise by iteratively maximising the likelihood of the noisy speech signal so that noise can be estimated even during speech-dominating frames. A comprehensive set of experiments carried out on the Aurora-2 and Aurora-4 databases shows that the proposed method achieves significant improvements over the baseline system and other similar missing data imputation techniques. More... »

PAGES

3731-3760

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s00034-016-0480-7

DOI

http://dx.doi.org/10.1007/s00034-016-0480-7

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1046974383


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 Sheffield", 
          "id": "https://www.grid.ac/institutes/grid.11835.3e", 
          "name": [
            "Department of Computer Science, University of Sheffield, Sheffield, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Gonzalez", 
        "givenName": "Jose A.", 
        "id": "sg:person.010477131004.17", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010477131004.17"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Department of Signal Theory, Telematics and Communications, Granada, Spain"
          ], 
          "type": "Organization"
        }, 
        "familyName": "G\u00f3mez", 
        "givenName": "Angel M.", 
        "id": "sg:person.013366554741.94", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013366554741.94"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Department of Signal Theory, Telematics and Communications, Granada, Spain"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Peinado", 
        "givenName": "Antonio M.", 
        "id": "sg:person.013434670141.68", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013434670141.68"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Sheffield", 
          "id": "https://www.grid.ac/institutes/grid.11835.3e", 
          "name": [
            "Department of Computer Science, University of Sheffield, Sheffield, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Ma", 
        "givenName": "Ning", 
        "id": "sg:person.015333272345.17", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015333272345.17"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Sheffield", 
          "id": "https://www.grid.ac/institutes/grid.11835.3e", 
          "name": [
            "Department of Computer Science, University of Sheffield, Sheffield, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Barker", 
        "givenName": "Jon", 
        "id": "sg:person.011625560553.55", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011625560553.55"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1016/j.specom.2004.03.007", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1009768526"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.specom.2007.05.003", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1010655932"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.specom.2003.10.002", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1020222130"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.specom.2003.10.002", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1020222130"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/s0167-6393(00)00034-0", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030004932"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.specom.2004.05.002", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030709436"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.csl.2006.08.001", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1035721600"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1049/el:20060510", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1056796135"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/29.35387", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061144473"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/89.928915", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061242685"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/msp.2005.1511828", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061422392"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/msp.2009.932166", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061423274"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/msp.2009.932707", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061423282"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/msp.2010.938081", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061423512"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tasl.2007.901310", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061516022"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tasl.2012.2229982", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061517047"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/taslp.2014.2304637", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061517270"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsa.2003.820201", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061786203"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.1990.115970", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1086353581"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/asru.2005.1566472", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093522703"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.2012.6288802", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093714039"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.2009.4960472", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095184059"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.2010.5495680", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095286597"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.1997.596072", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095388925"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.2005.1415143", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095392863"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2017-09", 
    "datePublishedReg": "2017-09-01", 
    "description": "An effective way to increase noise robustness in automatic speech recognition (ASR) systems is feature enhancement based on an analytical distortion model that describes the effects of noise on the speech features. One of such distortion models that has been reported to achieve a good trade-off between accuracy and simplicity is the masking model. Under this model, speech distortion caused by environmental noise is seen as a spectral mask and, as a result, noisy speech features can be either reliable (speech is not masked by noise) or unreliable (speech is masked). In this paper, we present a detailed overview of this model and its applications to noise robust ASR. Firstly, using the masking model, we derive a spectral reconstruction technique aimed at enhancing the noisy speech features. Two problems must be solved in order to perform spectral reconstruction using the masking model: (1) mask estimation, i.e. determining the reliability of the noisy features, and (2) feature imputation, i.e. estimating speech for the unreliable features. Unlike missing data imputation techniques where the two problems are considered as independent, our technique jointly addresses them by exploiting a priori knowledge of the speech and noise sources in the form of a statistical model. Secondly, we propose an algorithm for estimating the noise model required by the feature enhancement technique. The proposed algorithm fits a Gaussian mixture model to the noise by iteratively maximising the likelihood of the noisy speech signal so that noise can be estimated even during speech-dominating frames. A comprehensive set of experiments carried out on the Aurora-2 and Aurora-4 databases shows that the proposed method achieves significant improvements over the baseline system and other similar missing data imputation techniques.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/s00034-016-0480-7", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isPartOf": [
      {
        "id": "sg:journal.1136068", 
        "issn": [
          "0278-081X", 
          "1531-5878"
        ], 
        "name": "Circuits, Systems, and Signal Processing", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "9", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "36"
      }
    ], 
    "name": "Spectral Reconstruction and Noise Model Estimation Based on a Masking Model for Noise Robust Speech Recognition", 
    "pagination": "3731-3760", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "dfc50e6f6fa793d4e72d9e16fefffd8bdaf940fd2b1849ef391a294edb349c99"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s00034-016-0480-7"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1046974383"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s00034-016-0480-7", 
      "https://app.dimensions.ai/details/publication/pub.1046974383"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T10:36", 
    "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/v90/0000000349_0000000349/records_113670_00000001.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://link.springer.com/10.1007%2Fs00034-016-0480-7"
  }
]
 

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/s00034-016-0480-7'

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/s00034-016-0480-7'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s00034-016-0480-7'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s00034-016-0480-7'


 

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

165 TRIPLES      21 PREDICATES      51 URIs      19 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s00034-016-0480-7 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Ncb66394243db4855b79933ad95cfd753
4 schema:citation https://doi.org/10.1016/j.csl.2006.08.001
5 https://doi.org/10.1016/j.specom.2003.10.002
6 https://doi.org/10.1016/j.specom.2004.03.007
7 https://doi.org/10.1016/j.specom.2004.05.002
8 https://doi.org/10.1016/j.specom.2007.05.003
9 https://doi.org/10.1016/s0167-6393(00)00034-0
10 https://doi.org/10.1049/el:20060510
11 https://doi.org/10.1109/29.35387
12 https://doi.org/10.1109/89.928915
13 https://doi.org/10.1109/asru.2005.1566472
14 https://doi.org/10.1109/icassp.1990.115970
15 https://doi.org/10.1109/icassp.1997.596072
16 https://doi.org/10.1109/icassp.2005.1415143
17 https://doi.org/10.1109/icassp.2009.4960472
18 https://doi.org/10.1109/icassp.2010.5495680
19 https://doi.org/10.1109/icassp.2012.6288802
20 https://doi.org/10.1109/msp.2005.1511828
21 https://doi.org/10.1109/msp.2009.932166
22 https://doi.org/10.1109/msp.2009.932707
23 https://doi.org/10.1109/msp.2010.938081
24 https://doi.org/10.1109/tasl.2007.901310
25 https://doi.org/10.1109/tasl.2012.2229982
26 https://doi.org/10.1109/taslp.2014.2304637
27 https://doi.org/10.1109/tsa.2003.820201
28 schema:datePublished 2017-09
29 schema:datePublishedReg 2017-09-01
30 schema:description An effective way to increase noise robustness in automatic speech recognition (ASR) systems is feature enhancement based on an analytical distortion model that describes the effects of noise on the speech features. One of such distortion models that has been reported to achieve a good trade-off between accuracy and simplicity is the masking model. Under this model, speech distortion caused by environmental noise is seen as a spectral mask and, as a result, noisy speech features can be either reliable (speech is not masked by noise) or unreliable (speech is masked). In this paper, we present a detailed overview of this model and its applications to noise robust ASR. Firstly, using the masking model, we derive a spectral reconstruction technique aimed at enhancing the noisy speech features. Two problems must be solved in order to perform spectral reconstruction using the masking model: (1) mask estimation, i.e. determining the reliability of the noisy features, and (2) feature imputation, i.e. estimating speech for the unreliable features. Unlike missing data imputation techniques where the two problems are considered as independent, our technique jointly addresses them by exploiting a priori knowledge of the speech and noise sources in the form of a statistical model. Secondly, we propose an algorithm for estimating the noise model required by the feature enhancement technique. The proposed algorithm fits a Gaussian mixture model to the noise by iteratively maximising the likelihood of the noisy speech signal so that noise can be estimated even during speech-dominating frames. A comprehensive set of experiments carried out on the Aurora-2 and Aurora-4 databases shows that the proposed method achieves significant improvements over the baseline system and other similar missing data imputation techniques.
31 schema:genre research_article
32 schema:inLanguage en
33 schema:isAccessibleForFree true
34 schema:isPartOf N133a7c64303e4b19ad1c24cc2e277d9b
35 Nf166b901b0794447b6176bb39da437cf
36 sg:journal.1136068
37 schema:name Spectral Reconstruction and Noise Model Estimation Based on a Masking Model for Noise Robust Speech Recognition
38 schema:pagination 3731-3760
39 schema:productId N019eb2f7d21e4155814f6f5fb91321df
40 N4c0f8abd639a46159b9a0a17aeed3a26
41 N842c2f5e23474142b0ba4ab6140c88d5
42 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046974383
43 https://doi.org/10.1007/s00034-016-0480-7
44 schema:sdDatePublished 2019-04-11T10:36
45 schema:sdLicense https://scigraph.springernature.com/explorer/license/
46 schema:sdPublisher N7374db9e3fdf44d4b657635397e49e6b
47 schema:url https://link.springer.com/10.1007%2Fs00034-016-0480-7
48 sgo:license sg:explorer/license/
49 sgo:sdDataset articles
50 rdf:type schema:ScholarlyArticle
51 N019eb2f7d21e4155814f6f5fb91321df schema:name doi
52 schema:value 10.1007/s00034-016-0480-7
53 rdf:type schema:PropertyValue
54 N133a7c64303e4b19ad1c24cc2e277d9b schema:volumeNumber 36
55 rdf:type schema:PublicationVolume
56 N17e1522dd0e34e34923241c6facbed7b rdf:first sg:person.013434670141.68
57 rdf:rest Ne89f34258b66420f9eb1fdcbb27e637d
58 N4c0f8abd639a46159b9a0a17aeed3a26 schema:name readcube_id
59 schema:value dfc50e6f6fa793d4e72d9e16fefffd8bdaf940fd2b1849ef391a294edb349c99
60 rdf:type schema:PropertyValue
61 N7374db9e3fdf44d4b657635397e49e6b schema:name Springer Nature - SN SciGraph project
62 rdf:type schema:Organization
63 N842c2f5e23474142b0ba4ab6140c88d5 schema:name dimensions_id
64 schema:value pub.1046974383
65 rdf:type schema:PropertyValue
66 Nb045f4ecb1184456a498a0c0fc8e481f rdf:first sg:person.011625560553.55
67 rdf:rest rdf:nil
68 Nb980782e6b604bf394a4d4d4e0c98aa6 schema:name Department of Signal Theory, Telematics and Communications, Granada, Spain
69 rdf:type schema:Organization
70 Ncb66394243db4855b79933ad95cfd753 rdf:first sg:person.010477131004.17
71 rdf:rest Ne3edd6562ba148a0bdaac4695a41c34c
72 Ne3edd6562ba148a0bdaac4695a41c34c rdf:first sg:person.013366554741.94
73 rdf:rest N17e1522dd0e34e34923241c6facbed7b
74 Ne89f34258b66420f9eb1fdcbb27e637d rdf:first sg:person.015333272345.17
75 rdf:rest Nb045f4ecb1184456a498a0c0fc8e481f
76 Ne95eb8088518472eadf6bdd62d602bd5 schema:name Department of Signal Theory, Telematics and Communications, Granada, Spain
77 rdf:type schema:Organization
78 Nf166b901b0794447b6176bb39da437cf schema:issueNumber 9
79 rdf:type schema:PublicationIssue
80 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
81 schema:name Information and Computing Sciences
82 rdf:type schema:DefinedTerm
83 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
84 schema:name Artificial Intelligence and Image Processing
85 rdf:type schema:DefinedTerm
86 sg:journal.1136068 schema:issn 0278-081X
87 1531-5878
88 schema:name Circuits, Systems, and Signal Processing
89 rdf:type schema:Periodical
90 sg:person.010477131004.17 schema:affiliation https://www.grid.ac/institutes/grid.11835.3e
91 schema:familyName Gonzalez
92 schema:givenName Jose A.
93 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010477131004.17
94 rdf:type schema:Person
95 sg:person.011625560553.55 schema:affiliation https://www.grid.ac/institutes/grid.11835.3e
96 schema:familyName Barker
97 schema:givenName Jon
98 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011625560553.55
99 rdf:type schema:Person
100 sg:person.013366554741.94 schema:affiliation Ne95eb8088518472eadf6bdd62d602bd5
101 schema:familyName Gómez
102 schema:givenName Angel M.
103 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013366554741.94
104 rdf:type schema:Person
105 sg:person.013434670141.68 schema:affiliation Nb980782e6b604bf394a4d4d4e0c98aa6
106 schema:familyName Peinado
107 schema:givenName Antonio M.
108 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013434670141.68
109 rdf:type schema:Person
110 sg:person.015333272345.17 schema:affiliation https://www.grid.ac/institutes/grid.11835.3e
111 schema:familyName Ma
112 schema:givenName Ning
113 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015333272345.17
114 rdf:type schema:Person
115 https://doi.org/10.1016/j.csl.2006.08.001 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035721600
116 rdf:type schema:CreativeWork
117 https://doi.org/10.1016/j.specom.2003.10.002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020222130
118 rdf:type schema:CreativeWork
119 https://doi.org/10.1016/j.specom.2004.03.007 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009768526
120 rdf:type schema:CreativeWork
121 https://doi.org/10.1016/j.specom.2004.05.002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030709436
122 rdf:type schema:CreativeWork
123 https://doi.org/10.1016/j.specom.2007.05.003 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010655932
124 rdf:type schema:CreativeWork
125 https://doi.org/10.1016/s0167-6393(00)00034-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030004932
126 rdf:type schema:CreativeWork
127 https://doi.org/10.1049/el:20060510 schema:sameAs https://app.dimensions.ai/details/publication/pub.1056796135
128 rdf:type schema:CreativeWork
129 https://doi.org/10.1109/29.35387 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061144473
130 rdf:type schema:CreativeWork
131 https://doi.org/10.1109/89.928915 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061242685
132 rdf:type schema:CreativeWork
133 https://doi.org/10.1109/asru.2005.1566472 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093522703
134 rdf:type schema:CreativeWork
135 https://doi.org/10.1109/icassp.1990.115970 schema:sameAs https://app.dimensions.ai/details/publication/pub.1086353581
136 rdf:type schema:CreativeWork
137 https://doi.org/10.1109/icassp.1997.596072 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095388925
138 rdf:type schema:CreativeWork
139 https://doi.org/10.1109/icassp.2005.1415143 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095392863
140 rdf:type schema:CreativeWork
141 https://doi.org/10.1109/icassp.2009.4960472 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095184059
142 rdf:type schema:CreativeWork
143 https://doi.org/10.1109/icassp.2010.5495680 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095286597
144 rdf:type schema:CreativeWork
145 https://doi.org/10.1109/icassp.2012.6288802 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093714039
146 rdf:type schema:CreativeWork
147 https://doi.org/10.1109/msp.2005.1511828 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061422392
148 rdf:type schema:CreativeWork
149 https://doi.org/10.1109/msp.2009.932166 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061423274
150 rdf:type schema:CreativeWork
151 https://doi.org/10.1109/msp.2009.932707 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061423282
152 rdf:type schema:CreativeWork
153 https://doi.org/10.1109/msp.2010.938081 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061423512
154 rdf:type schema:CreativeWork
155 https://doi.org/10.1109/tasl.2007.901310 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061516022
156 rdf:type schema:CreativeWork
157 https://doi.org/10.1109/tasl.2012.2229982 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061517047
158 rdf:type schema:CreativeWork
159 https://doi.org/10.1109/taslp.2014.2304637 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061517270
160 rdf:type schema:CreativeWork
161 https://doi.org/10.1109/tsa.2003.820201 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061786203
162 rdf:type schema:CreativeWork
163 https://www.grid.ac/institutes/grid.11835.3e schema:alternateName University of Sheffield
164 schema:name Department of Computer Science, University of Sheffield, Sheffield, UK
165 rdf:type schema:Organization
 




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


...