Research on Key Technologies of Audio on Demand Based on Syllable Models View Homepage


Ontology type: schema:MonetaryGrant     


Grant Info

YEARS

2013-2016

FUNDING AMOUNT

230000 CNY

ABSTRACT

In Chinese, there are a large number of homophones and a small number of syllables, and more than one Chinese character corresponds to the same syllable. Therefore, the audio indexing library is established for every Chinese syllable and the input speech is recognized as a syllable sequence in this project. In the syllable matching procedure, the potential audio tracks are selected from the audio indexing library according to the syllable information of the input speech and then the syllable sequence of the input speech is compared with the syllable sequence of every potential audio track. The traditional text matching is replaced by the syllable sequence matching, which improves the decoding accuracy and reduces the system complexity. For the front-end speech recognition procedure, the nonlinear compensation technology is employed to compensate the additive noise, channel distortion and room reverberation, which can improve the robustness of speech recognition systems. Furthermore, the N-best algorithm is used to produce more than one potential syllable sequence of the input speech, which reduces the impact of the wrong speech recognition results and improves the accuracy of the syllable sequence decoding. More... »

URL

http://npd.nsfc.gov.cn/projectDetail.action?pid=61301218

Related SciGraph Publications

  • 2017-01. Full band watermarking in DCT domain with Weibull model in MULTIMEDIA TOOLS AND APPLICATIONS
  • 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/2008/2208", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "type": "DefinedTerm"
          }
        ], 
        "amount": {
          "currency": "CNY", 
          "type": "MonetaryAmount", 
          "value": "230000"
        }, 
        "description": "In Chinese, there are a large number of homophones and a small number of syllables, and more than one Chinese character corresponds to the same syllable. Therefore, the audio indexing library is established for every Chinese syllable and the input speech is recognized as a syllable sequence in this project. In the syllable matching procedure, the potential audio tracks are selected from the audio indexing library according to the syllable information of the input speech and then the syllable sequence of the input speech is compared with the syllable sequence of every potential audio track. The traditional text matching is replaced by the syllable sequence matching, which improves the decoding accuracy and reduces the system complexity. For the front-end speech recognition procedure, the nonlinear compensation technology is employed to compensate the additive noise, channel distortion and room reverberation, which can improve the robustness of speech recognition systems. Furthermore, the N-best algorithm is used to produce more than one potential syllable sequence of the input speech, which reduces the impact of the wrong speech recognition results and improves the accuracy of the syllable sequence decoding.", 
        "endDate": "2016-12-30T00:00:00Z", 
        "funder": {
          "id": "https://www.grid.ac/institutes/grid.419696.5", 
          "type": "Organization"
        }, 
        "id": "sg:grant.7176290", 
        "identifier": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "7176290"
            ]
          }, 
          {
            "name": "nsfc_id", 
            "type": "PropertyValue", 
            "value": [
              "61301218"
            ]
          }
        ], 
        "inLanguage": [
          "zh"
        ], 
        "keywords": [
          "same syllable", 
          "speech recognition system", 
          "syllable matching procedure", 
          "system complexity", 
          "audio indexing library", 
          "syllable sequence decoding", 
          "Chinese", 
          "accuracy", 
          "input speech", 
          "Key Technologies", 
          "syllables", 
          "research", 
          "syllable information", 
          "potential audio track", 
          "room reverberation", 
          "best algorithm", 
          "nonlinear compensation technology", 
          "Syllable Models", 
          "audio", 
          "robustness", 
          "demand", 
          "syllable sequences", 
          "traditional text matching", 
          "decoding accuracy", 
          "channel distortion", 
          "syllable sequence matching", 
          "additive noise", 
          "potential syllable sequence", 
          "wrong speech recognition results", 
          "Chinese syllables", 
          "homophones", 
          "front-end speech recognition procedure", 
          "Chinese characters", 
          "impact", 
          "project", 
          "large number", 
          "small number"
        ], 
        "name": "Research on Key Technologies of Audio on Demand Based on Syllable Models", 
        "recipient": [
          {
            "id": "https://www.grid.ac/institutes/grid.257065.3", 
            "type": "Organization"
          }, 
          {
            "affiliation": {
              "id": "https://www.grid.ac/institutes/grid.257065.3", 
              "name": "HoHai University", 
              "type": "Organization"
            }, 
            "familyName": "Lu", 
            "givenName": "Yong", 
            "id": "sg:person.014131270160.75", 
            "type": "Person"
          }, 
          {
            "member": "sg:person.014131270160.75", 
            "roleName": "PI", 
            "type": "Role"
          }
        ], 
        "sameAs": [
          "https://app.dimensions.ai/details/grant/grant.7176290"
        ], 
        "sdDataset": "grants", 
        "sdDatePublished": "2019-03-07T12:38", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com.uberresearch.data.processor/core_data/20181219_192338/projects/base/nsfc_projects.xml.gz", 
        "startDate": "2013-12-31T00:00:00Z", 
        "type": "MonetaryGrant", 
        "url": "http://npd.nsfc.gov.cn/projectDetail.action?pid=61301218"
      }
    ]
     

    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/grant.7176290'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/grant.7176290'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/grant.7176290'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/grant.7176290'


     

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

    81 TRIPLES      19 PREDICATES      59 URIs      51 LITERALS      5 BLANK NODES

    Subject Predicate Object
    1 sg:grant.7176290 schema:about anzsrc-for:2208
    2 schema:amount N5b0c622e2f19444ba8c8947851b28fb4
    3 schema:description In Chinese, there are a large number of homophones and a small number of syllables, and more than one Chinese character corresponds to the same syllable. Therefore, the audio indexing library is established for every Chinese syllable and the input speech is recognized as a syllable sequence in this project. In the syllable matching procedure, the potential audio tracks are selected from the audio indexing library according to the syllable information of the input speech and then the syllable sequence of the input speech is compared with the syllable sequence of every potential audio track. The traditional text matching is replaced by the syllable sequence matching, which improves the decoding accuracy and reduces the system complexity. For the front-end speech recognition procedure, the nonlinear compensation technology is employed to compensate the additive noise, channel distortion and room reverberation, which can improve the robustness of speech recognition systems. Furthermore, the N-best algorithm is used to produce more than one potential syllable sequence of the input speech, which reduces the impact of the wrong speech recognition results and improves the accuracy of the syllable sequence decoding.
    4 schema:endDate 2016-12-30T00:00:00Z
    5 schema:funder https://www.grid.ac/institutes/grid.419696.5
    6 schema:identifier N7b020fd6237c49aaace3c9e9fa836b1b
    7 N974dfffff7e042ce8daae38c32486bdc
    8 schema:inLanguage zh
    9 schema:keywords Chinese
    10 Chinese characters
    11 Chinese syllables
    12 Key Technologies
    13 Syllable Models
    14 accuracy
    15 additive noise
    16 audio
    17 audio indexing library
    18 best algorithm
    19 channel distortion
    20 decoding accuracy
    21 demand
    22 front-end speech recognition procedure
    23 homophones
    24 impact
    25 input speech
    26 large number
    27 nonlinear compensation technology
    28 potential audio track
    29 potential syllable sequence
    30 project
    31 research
    32 robustness
    33 room reverberation
    34 same syllable
    35 small number
    36 speech recognition system
    37 syllable information
    38 syllable matching procedure
    39 syllable sequence decoding
    40 syllable sequence matching
    41 syllable sequences
    42 syllables
    43 system complexity
    44 traditional text matching
    45 wrong speech recognition results
    46 schema:name Research on Key Technologies of Audio on Demand Based on Syllable Models
    47 schema:recipient N65af2f7c34e243c9be1e49c1c12562ee
    48 sg:person.014131270160.75
    49 https://www.grid.ac/institutes/grid.257065.3
    50 schema:sameAs https://app.dimensions.ai/details/grant/grant.7176290
    51 schema:sdDatePublished 2019-03-07T12:38
    52 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    53 schema:sdPublisher Nb018baf01316434da968a77863b8e27a
    54 schema:startDate 2013-12-31T00:00:00Z
    55 schema:url http://npd.nsfc.gov.cn/projectDetail.action?pid=61301218
    56 sgo:license sg:explorer/license/
    57 sgo:sdDataset grants
    58 rdf:type schema:MonetaryGrant
    59 N5b0c622e2f19444ba8c8947851b28fb4 schema:currency CNY
    60 schema:value 230000
    61 rdf:type schema:MonetaryAmount
    62 N65af2f7c34e243c9be1e49c1c12562ee schema:member sg:person.014131270160.75
    63 schema:roleName PI
    64 rdf:type schema:Role
    65 N7b020fd6237c49aaace3c9e9fa836b1b schema:name nsfc_id
    66 schema:value 61301218
    67 rdf:type schema:PropertyValue
    68 N974dfffff7e042ce8daae38c32486bdc schema:name dimensions_id
    69 schema:value 7176290
    70 rdf:type schema:PropertyValue
    71 Nb018baf01316434da968a77863b8e27a schema:name Springer Nature - SN SciGraph project
    72 rdf:type schema:Organization
    73 anzsrc-for:2208 schema:inDefinedTermSet anzsrc-for:
    74 rdf:type schema:DefinedTerm
    75 sg:person.014131270160.75 schema:affiliation https://www.grid.ac/institutes/grid.257065.3
    76 schema:familyName Lu
    77 schema:givenName Yong
    78 rdf:type schema:Person
    79 https://www.grid.ac/institutes/grid.257065.3 schema:name HoHai University
    80 rdf:type schema:Organization
    81 https://www.grid.ac/institutes/grid.419696.5 schema:Organization
     




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


    ...