Voice Conversion Between Synthesized Bilingual Voices Using Line Spectral Frequencies View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2015

AUTHORS

Young-Sun Yun , Jinman Jung , Seongbae Eun

ABSTRACT

Voice conversion is a technique that transforms the source speaker individuality to that of the target speaker. We propose the simple and intuitive voice conversion algorithm not using training data between different languages and it uses text-to-speech generated speech rather than recorded real voices. The suggested method reconstructed the voice after transforming line spectral frequencies (LSF) by formant space warping functions. The formant space is the space consisted of representative four monophthongs for each language. The warping functions are represented by piecewise linear equations using pairs of four formants at matched monophthongs. In this paper, we applied LSF to voice conversion because LSF are not overly sensitive to quantization noise and can be interpolated. From experimental results, LSF based voice conversion shows good results for ABX and MOS tests than the direct frequency warping approaches. More... »

PAGES

463-471

Book

TITLE

Speech and Computer

ISBN

978-3-319-23131-0
978-3-319-23132-7

Author Affiliations

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-23132-7_57

DOI

http://dx.doi.org/10.1007/978-3-319-23132-7_57

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1007220572


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/2008/2004", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Linguistics", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/20", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Language, Communication and Culture", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Hannam University", 
          "id": "https://www.grid.ac/institutes/grid.411970.a", 
          "name": [
            "Department of Computer, Communications, and Unmanned Technology, Hannam University"
          ], 
          "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": "Hannam University", 
          "id": "https://www.grid.ac/institutes/grid.411970.a", 
          "name": [
            "Department of Computer, Communications, and Unmanned Technology, Hannam University"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Jung", 
        "givenName": "Jinman", 
        "id": "sg:person.011734132707.22", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011734132707.22"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Hannam University", 
          "id": "https://www.grid.ac/institutes/grid.411970.a", 
          "name": [
            "Department of Computer, Communications, and Unmanned Technology, Hannam University"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Eun", 
        "givenName": "Seongbae", 
        "id": "sg:person.010403215213.18", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010403215213.18"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1016/j.sigpro.2007.09.003", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1024891440"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0167-6393(94)00058-i", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1041350006"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0167-6393(94)00053-d", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1049408984"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0167-6393(94)00052-c", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1051750656"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tasl.2009.2038663", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061516465"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tasl.2012.2198058", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061516939"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tassp.1986.1164983", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061520003"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1121/1.1995189", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1062291361"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1121/1.411872", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1062363160"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/asru.2003.1318521", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093759268"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/isspit.2004.1433719", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093765558"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.1997.596120", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095088016"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.2006.1659962", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095091226"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2015", 
    "datePublishedReg": "2015-01-01", 
    "description": "Voice conversion is a technique that transforms the source speaker individuality to that of the target speaker. We propose the simple and intuitive voice conversion algorithm not using training data between different languages and it uses text-to-speech generated speech rather than recorded real voices. The suggested method reconstructed the voice after transforming line spectral frequencies (LSF) by formant space warping functions. The formant space is the space consisted of representative four monophthongs for each language. The warping functions are represented by piecewise linear equations using pairs of four formants at matched monophthongs. In this paper, we applied LSF to voice conversion because LSF are not overly sensitive to quantization noise and can be interpolated. From experimental results, LSF based voice conversion shows good results for ABX and MOS tests than the direct frequency warping approaches.", 
    "editor": [
      {
        "familyName": "Ronzhin", 
        "givenName": "Andrey", 
        "type": "Person"
      }, 
      {
        "familyName": "Potapova", 
        "givenName": "Rodmonga", 
        "type": "Person"
      }, 
      {
        "familyName": "Fakotakis", 
        "givenName": "Nikos", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-319-23132-7_57", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-319-23131-0", 
        "978-3-319-23132-7"
      ], 
      "name": "Speech and Computer", 
      "type": "Book"
    }, 
    "name": "Voice Conversion Between Synthesized Bilingual Voices Using Line Spectral Frequencies", 
    "pagination": "463-471", 
    "productId": [
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-23132-7_57"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "22648cb9d1f4ba5c10e605eb3530077902c98339991173aacc030899154e528a"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1007220572"
        ]
      }
    ], 
    "publisher": {
      "location": "Cham", 
      "name": "Springer International Publishing", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-23132-7_57", 
      "https://app.dimensions.ai/details/publication/pub.1007220572"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-15T10:31", 
    "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_8659_00000247.jsonl", 
    "type": "Chapter", 
    "url": "http://link.springer.com/10.1007/978-3-319-23132-7_57"
  }
]
 

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.10.1007/978-3-319-23132-7_57'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-23132-7_57'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-23132-7_57'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-23132-7_57'


 

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

128 TRIPLES      23 PREDICATES      40 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-23132-7_57 schema:about anzsrc-for:20
2 anzsrc-for:2004
3 schema:author Ne169596f262d438ca4871718ed2b809b
4 schema:citation https://doi.org/10.1016/0167-6393(94)00052-c
5 https://doi.org/10.1016/0167-6393(94)00053-d
6 https://doi.org/10.1016/0167-6393(94)00058-i
7 https://doi.org/10.1016/j.sigpro.2007.09.003
8 https://doi.org/10.1109/asru.2003.1318521
9 https://doi.org/10.1109/icassp.1997.596120
10 https://doi.org/10.1109/icassp.2006.1659962
11 https://doi.org/10.1109/isspit.2004.1433719
12 https://doi.org/10.1109/tasl.2009.2038663
13 https://doi.org/10.1109/tasl.2012.2198058
14 https://doi.org/10.1109/tassp.1986.1164983
15 https://doi.org/10.1121/1.1995189
16 https://doi.org/10.1121/1.411872
17 schema:datePublished 2015
18 schema:datePublishedReg 2015-01-01
19 schema:description Voice conversion is a technique that transforms the source speaker individuality to that of the target speaker. We propose the simple and intuitive voice conversion algorithm not using training data between different languages and it uses text-to-speech generated speech rather than recorded real voices. The suggested method reconstructed the voice after transforming line spectral frequencies (LSF) by formant space warping functions. The formant space is the space consisted of representative four monophthongs for each language. The warping functions are represented by piecewise linear equations using pairs of four formants at matched monophthongs. In this paper, we applied LSF to voice conversion because LSF are not overly sensitive to quantization noise and can be interpolated. From experimental results, LSF based voice conversion shows good results for ABX and MOS tests than the direct frequency warping approaches.
20 schema:editor N1c4b26d2529344d996ace136c8e0c630
21 schema:genre chapter
22 schema:inLanguage en
23 schema:isAccessibleForFree false
24 schema:isPartOf N04c677a2e0e64563a8b5e9bb5c2689b3
25 schema:name Voice Conversion Between Synthesized Bilingual Voices Using Line Spectral Frequencies
26 schema:pagination 463-471
27 schema:productId N58a7ef12d2ba4c0a866f6bb82edf8552
28 N9e52113b12cb48c2968db7cb0aa9df01
29 Nd490bf58b7d341a68d04ac3fbf19b7c0
30 schema:publisher N83f0dbe5c4ae4d2abb17b7e709812c4f
31 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007220572
32 https://doi.org/10.1007/978-3-319-23132-7_57
33 schema:sdDatePublished 2019-04-15T10:31
34 schema:sdLicense https://scigraph.springernature.com/explorer/license/
35 schema:sdPublisher Ne42f32fbd475465fa2fb264f5656aaa0
36 schema:url http://link.springer.com/10.1007/978-3-319-23132-7_57
37 sgo:license sg:explorer/license/
38 sgo:sdDataset chapters
39 rdf:type schema:Chapter
40 N04c677a2e0e64563a8b5e9bb5c2689b3 schema:isbn 978-3-319-23131-0
41 978-3-319-23132-7
42 schema:name Speech and Computer
43 rdf:type schema:Book
44 N1c4b26d2529344d996ace136c8e0c630 rdf:first Nb6fea169e610435c9a0937baba300f77
45 rdf:rest Nef6b64002ff643139e9bc08b0d11f681
46 N39fa6e9887574846a4626f0c75e8e01f rdf:first Nf2995b3165c74295b5e0d146009033b4
47 rdf:rest rdf:nil
48 N417f3a8f7bfd453b8b5e84719e535d5c rdf:first sg:person.011734132707.22
49 rdf:rest Nb1895474cead435fb8605aa0db3ea20c
50 N58a7ef12d2ba4c0a866f6bb82edf8552 schema:name doi
51 schema:value 10.1007/978-3-319-23132-7_57
52 rdf:type schema:PropertyValue
53 N83f0dbe5c4ae4d2abb17b7e709812c4f schema:location Cham
54 schema:name Springer International Publishing
55 rdf:type schema:Organisation
56 N8f90bb275e35469c8b087370c6619476 schema:familyName Potapova
57 schema:givenName Rodmonga
58 rdf:type schema:Person
59 N9e52113b12cb48c2968db7cb0aa9df01 schema:name readcube_id
60 schema:value 22648cb9d1f4ba5c10e605eb3530077902c98339991173aacc030899154e528a
61 rdf:type schema:PropertyValue
62 Nb1895474cead435fb8605aa0db3ea20c rdf:first sg:person.010403215213.18
63 rdf:rest rdf:nil
64 Nb6fea169e610435c9a0937baba300f77 schema:familyName Ronzhin
65 schema:givenName Andrey
66 rdf:type schema:Person
67 Nd490bf58b7d341a68d04ac3fbf19b7c0 schema:name dimensions_id
68 schema:value pub.1007220572
69 rdf:type schema:PropertyValue
70 Ne169596f262d438ca4871718ed2b809b rdf:first sg:person.012422257207.75
71 rdf:rest N417f3a8f7bfd453b8b5e84719e535d5c
72 Ne42f32fbd475465fa2fb264f5656aaa0 schema:name Springer Nature - SN SciGraph project
73 rdf:type schema:Organization
74 Nef6b64002ff643139e9bc08b0d11f681 rdf:first N8f90bb275e35469c8b087370c6619476
75 rdf:rest N39fa6e9887574846a4626f0c75e8e01f
76 Nf2995b3165c74295b5e0d146009033b4 schema:familyName Fakotakis
77 schema:givenName Nikos
78 rdf:type schema:Person
79 anzsrc-for:20 schema:inDefinedTermSet anzsrc-for:
80 schema:name Language, Communication and Culture
81 rdf:type schema:DefinedTerm
82 anzsrc-for:2004 schema:inDefinedTermSet anzsrc-for:
83 schema:name Linguistics
84 rdf:type schema:DefinedTerm
85 sg:person.010403215213.18 schema:affiliation https://www.grid.ac/institutes/grid.411970.a
86 schema:familyName Eun
87 schema:givenName Seongbae
88 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010403215213.18
89 rdf:type schema:Person
90 sg:person.011734132707.22 schema:affiliation https://www.grid.ac/institutes/grid.411970.a
91 schema:familyName Jung
92 schema:givenName Jinman
93 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011734132707.22
94 rdf:type schema:Person
95 sg:person.012422257207.75 schema:affiliation https://www.grid.ac/institutes/grid.411970.a
96 schema:familyName Yun
97 schema:givenName Young-Sun
98 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012422257207.75
99 rdf:type schema:Person
100 https://doi.org/10.1016/0167-6393(94)00052-c schema:sameAs https://app.dimensions.ai/details/publication/pub.1051750656
101 rdf:type schema:CreativeWork
102 https://doi.org/10.1016/0167-6393(94)00053-d schema:sameAs https://app.dimensions.ai/details/publication/pub.1049408984
103 rdf:type schema:CreativeWork
104 https://doi.org/10.1016/0167-6393(94)00058-i schema:sameAs https://app.dimensions.ai/details/publication/pub.1041350006
105 rdf:type schema:CreativeWork
106 https://doi.org/10.1016/j.sigpro.2007.09.003 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024891440
107 rdf:type schema:CreativeWork
108 https://doi.org/10.1109/asru.2003.1318521 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093759268
109 rdf:type schema:CreativeWork
110 https://doi.org/10.1109/icassp.1997.596120 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095088016
111 rdf:type schema:CreativeWork
112 https://doi.org/10.1109/icassp.2006.1659962 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095091226
113 rdf:type schema:CreativeWork
114 https://doi.org/10.1109/isspit.2004.1433719 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093765558
115 rdf:type schema:CreativeWork
116 https://doi.org/10.1109/tasl.2009.2038663 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061516465
117 rdf:type schema:CreativeWork
118 https://doi.org/10.1109/tasl.2012.2198058 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061516939
119 rdf:type schema:CreativeWork
120 https://doi.org/10.1109/tassp.1986.1164983 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061520003
121 rdf:type schema:CreativeWork
122 https://doi.org/10.1121/1.1995189 schema:sameAs https://app.dimensions.ai/details/publication/pub.1062291361
123 rdf:type schema:CreativeWork
124 https://doi.org/10.1121/1.411872 schema:sameAs https://app.dimensions.ai/details/publication/pub.1062363160
125 rdf:type schema:CreativeWork
126 https://www.grid.ac/institutes/grid.411970.a schema:alternateName Hannam University
127 schema:name Department of Computer, Communications, and Unmanned Technology, Hannam University
128 rdf:type schema:Organization
 




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


...