Design of Tandem Architecture Using Segmental Trend Features View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2007

AUTHORS

Young-Sun Yun , Yunkeun Lee

ABSTRACT

This paper investigates the tandem architecture (TA) based on segmental features. The segmental feature based recognition system has been reported to show better results than the conventional feature based system in previous studies. In this paper we tried to merge the segmental feature with the tandem architecture which uses both hidden Markov models and neural networks. In general, segmental features can be separated into the trend and location. Since the trend means variation of segmental features and since it occupies a large portion of segmental features, the trend information was used as an independent or additional feature for the speech recognition system. We applied the trend information of segmental features to TA and used posterior probabilities, which are the output of the neural network, as inputs of the recognition system. Experiments were performed on Aurora2 database to examine the potentiality of the trend feature based TA. The results of our experiments verified that the proposed system outperforms the conventional system on very low SNR environments. These findings led us to conclude that the trend information on TA can be additionally used for the traditional MFCC features. More... »

PAGES

374-381

Book

TITLE

Text, Speech and Dialogue

ISBN

978-3-540-74627-0
978-3-540-74628-7

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-540-74628-7_49

DOI

http://dx.doi.org/10.1007/978-3-540-74628-7_49

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1010525812


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": "Hannam University", 
          "id": "https://www.grid.ac/institutes/grid.411970.a", 
          "name": [
            "Dept. of Information and Communication Engineering, Hannam University, Daejeon, Republic of Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Yun", 
        "givenName": "Young-Sun", 
        "id": "sg:person.012422257207.75", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012422257207.75"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Electronics and Telecommunications Research Institute", 
          "id": "https://www.grid.ac/institutes/grid.36303.35", 
          "name": [
            "Spoken Language Processing Team, ETRI, Daejeon, Republic of Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Lee", 
        "givenName": "Yunkeun", 
        "id": "sg:person.015407627203.84", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015407627203.84"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1006/csla.1998.0048", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1032307486"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/s0167-6393(01)00047-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1038027702"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0165-1684(92)90112-a", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045597341"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0165-1684(92)90112-a", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045597341"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/89.536930", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061242360"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/97.844631", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061251402"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.1993.319337", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1086258188"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.2003.1198715", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093225503"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.2001.940881", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093479864"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icslp.1996.607155", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094272655"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.2000.862024", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094516685"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2007", 
    "datePublishedReg": "2007-01-01", 
    "description": "This paper investigates the tandem architecture (TA) based on segmental features. The segmental feature based recognition system has been reported to show better results than the conventional feature based system in previous studies. In this paper we tried to merge the segmental feature with the tandem architecture which uses both hidden Markov models and neural networks. In general, segmental features can be separated into the trend and location. Since the trend means variation of segmental features and since it occupies a large portion of segmental features, the trend information was used as an independent or additional feature for the speech recognition system. We applied the trend information of segmental features to TA and used posterior probabilities, which are the output of the neural network, as inputs of the recognition system. Experiments were performed on Aurora2 database to examine the potentiality of the trend feature based TA. The results of our experiments verified that the proposed system outperforms the conventional system on very low SNR environments. These findings led us to conclude that the trend information on TA can be additionally used for the traditional MFCC features.", 
    "editor": [
      {
        "familyName": "Matou\u0161ek", 
        "givenName": "V\u00e1clav", 
        "type": "Person"
      }, 
      {
        "familyName": "Mautner", 
        "givenName": "Pavel", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-540-74628-7_49", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-540-74627-0", 
        "978-3-540-74628-7"
      ], 
      "name": "Text, Speech and Dialogue", 
      "type": "Book"
    }, 
    "name": "Design of Tandem Architecture Using Segmental Trend Features", 
    "pagination": "374-381", 
    "productId": [
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-540-74628-7_49"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "322541fa0929b690a7da75c44aead780bfac57ad3cfc14fce5086b648b77d39e"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1010525812"
        ]
      }
    ], 
    "publisher": {
      "location": "Berlin, Heidelberg", 
      "name": "Springer Berlin Heidelberg", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-540-74628-7_49", 
      "https://app.dimensions.ai/details/publication/pub.1010525812"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-16T05:26", 
    "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/v90/0000000345_0000000345/records_64103_00000000.jsonl", 
    "type": "Chapter", 
    "url": "https://link.springer.com/10.1007%2F978-3-540-74628-7_49"
  }
]
 

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.10.1007/978-3-540-74628-7_49'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-74628-7_49'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-74628-7_49'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-74628-7_49'


 

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

110 TRIPLES      23 PREDICATES      37 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-540-74628-7_49 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Ncd749fb44a8649f8879eebd122ad7316
4 schema:citation https://doi.org/10.1006/csla.1998.0048
5 https://doi.org/10.1016/0165-1684(92)90112-a
6 https://doi.org/10.1016/s0167-6393(01)00047-4
7 https://doi.org/10.1109/89.536930
8 https://doi.org/10.1109/97.844631
9 https://doi.org/10.1109/icassp.1993.319337
10 https://doi.org/10.1109/icassp.2000.862024
11 https://doi.org/10.1109/icassp.2001.940881
12 https://doi.org/10.1109/icassp.2003.1198715
13 https://doi.org/10.1109/icslp.1996.607155
14 schema:datePublished 2007
15 schema:datePublishedReg 2007-01-01
16 schema:description This paper investigates the tandem architecture (TA) based on segmental features. The segmental feature based recognition system has been reported to show better results than the conventional feature based system in previous studies. In this paper we tried to merge the segmental feature with the tandem architecture which uses both hidden Markov models and neural networks. In general, segmental features can be separated into the trend and location. Since the trend means variation of segmental features and since it occupies a large portion of segmental features, the trend information was used as an independent or additional feature for the speech recognition system. We applied the trend information of segmental features to TA and used posterior probabilities, which are the output of the neural network, as inputs of the recognition system. Experiments were performed on Aurora2 database to examine the potentiality of the trend feature based TA. The results of our experiments verified that the proposed system outperforms the conventional system on very low SNR environments. These findings led us to conclude that the trend information on TA can be additionally used for the traditional MFCC features.
17 schema:editor N074caa37ff3148708259d18aacf05769
18 schema:genre chapter
19 schema:inLanguage en
20 schema:isAccessibleForFree false
21 schema:isPartOf N5cb125cdfa60473fa26d2cca8f35e1bc
22 schema:name Design of Tandem Architecture Using Segmental Trend Features
23 schema:pagination 374-381
24 schema:productId N021462ef76044dc48539d14ab75388f2
25 Ne92efb9eed5644ae855e3f424206fde0
26 Nf14b0dffdf404c3486185c67b2677e3f
27 schema:publisher Nbe0e9f48bf834dd286d4c47c145dd85c
28 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010525812
29 https://doi.org/10.1007/978-3-540-74628-7_49
30 schema:sdDatePublished 2019-04-16T05:26
31 schema:sdLicense https://scigraph.springernature.com/explorer/license/
32 schema:sdPublisher N02eaecfb00c745dba46ea5f841534b14
33 schema:url https://link.springer.com/10.1007%2F978-3-540-74628-7_49
34 sgo:license sg:explorer/license/
35 sgo:sdDataset chapters
36 rdf:type schema:Chapter
37 N021462ef76044dc48539d14ab75388f2 schema:name readcube_id
38 schema:value 322541fa0929b690a7da75c44aead780bfac57ad3cfc14fce5086b648b77d39e
39 rdf:type schema:PropertyValue
40 N02eaecfb00c745dba46ea5f841534b14 schema:name Springer Nature - SN SciGraph project
41 rdf:type schema:Organization
42 N074caa37ff3148708259d18aacf05769 rdf:first Nba83266037da44c5b0a7b5bbc629ecb6
43 rdf:rest N86f5552cd7e1457fbdd74ca5f6f7a36e
44 N5cb125cdfa60473fa26d2cca8f35e1bc schema:isbn 978-3-540-74627-0
45 978-3-540-74628-7
46 schema:name Text, Speech and Dialogue
47 rdf:type schema:Book
48 N85fb70ce5a81487fa685aeb2c2941ee8 schema:familyName Mautner
49 schema:givenName Pavel
50 rdf:type schema:Person
51 N86f5552cd7e1457fbdd74ca5f6f7a36e rdf:first N85fb70ce5a81487fa685aeb2c2941ee8
52 rdf:rest rdf:nil
53 Nba83266037da44c5b0a7b5bbc629ecb6 schema:familyName Matoušek
54 schema:givenName Václav
55 rdf:type schema:Person
56 Nbe0e9f48bf834dd286d4c47c145dd85c schema:location Berlin, Heidelberg
57 schema:name Springer Berlin Heidelberg
58 rdf:type schema:Organisation
59 Nc5123c2f8df3432292faf282eb9f67d7 rdf:first sg:person.015407627203.84
60 rdf:rest rdf:nil
61 Ncd749fb44a8649f8879eebd122ad7316 rdf:first sg:person.012422257207.75
62 rdf:rest Nc5123c2f8df3432292faf282eb9f67d7
63 Ne92efb9eed5644ae855e3f424206fde0 schema:name dimensions_id
64 schema:value pub.1010525812
65 rdf:type schema:PropertyValue
66 Nf14b0dffdf404c3486185c67b2677e3f schema:name doi
67 schema:value 10.1007/978-3-540-74628-7_49
68 rdf:type schema:PropertyValue
69 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
70 schema:name Information and Computing Sciences
71 rdf:type schema:DefinedTerm
72 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
73 schema:name Artificial Intelligence and Image Processing
74 rdf:type schema:DefinedTerm
75 sg:person.012422257207.75 schema:affiliation https://www.grid.ac/institutes/grid.411970.a
76 schema:familyName Yun
77 schema:givenName Young-Sun
78 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012422257207.75
79 rdf:type schema:Person
80 sg:person.015407627203.84 schema:affiliation https://www.grid.ac/institutes/grid.36303.35
81 schema:familyName Lee
82 schema:givenName Yunkeun
83 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015407627203.84
84 rdf:type schema:Person
85 https://doi.org/10.1006/csla.1998.0048 schema:sameAs https://app.dimensions.ai/details/publication/pub.1032307486
86 rdf:type schema:CreativeWork
87 https://doi.org/10.1016/0165-1684(92)90112-a schema:sameAs https://app.dimensions.ai/details/publication/pub.1045597341
88 rdf:type schema:CreativeWork
89 https://doi.org/10.1016/s0167-6393(01)00047-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038027702
90 rdf:type schema:CreativeWork
91 https://doi.org/10.1109/89.536930 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061242360
92 rdf:type schema:CreativeWork
93 https://doi.org/10.1109/97.844631 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061251402
94 rdf:type schema:CreativeWork
95 https://doi.org/10.1109/icassp.1993.319337 schema:sameAs https://app.dimensions.ai/details/publication/pub.1086258188
96 rdf:type schema:CreativeWork
97 https://doi.org/10.1109/icassp.2000.862024 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094516685
98 rdf:type schema:CreativeWork
99 https://doi.org/10.1109/icassp.2001.940881 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093479864
100 rdf:type schema:CreativeWork
101 https://doi.org/10.1109/icassp.2003.1198715 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093225503
102 rdf:type schema:CreativeWork
103 https://doi.org/10.1109/icslp.1996.607155 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094272655
104 rdf:type schema:CreativeWork
105 https://www.grid.ac/institutes/grid.36303.35 schema:alternateName Electronics and Telecommunications Research Institute
106 schema:name Spoken Language Processing Team, ETRI, Daejeon, Republic of Korea
107 rdf:type schema:Organization
108 https://www.grid.ac/institutes/grid.411970.a schema:alternateName Hannam University
109 schema:name Dept. of Information and Communication Engineering, Hannam University, Daejeon, Republic of Korea
110 rdf:type schema:Organization
 




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


...