AlignSTS: Speech-to-Singing Conversion via Cross-Modal Alignment Article Swipe
Ruiqi Li
,
Rongjie Huang
,
Lichao Zhang
,
Jinglin Liu
,
Zhou Zhao
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2305.04476
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2305.04476
The speech-to-singing (STS) voice conversion task aims to generate singing samples corresponding to speech recordings while facing a major challenge: the alignment between the target (singing) pitch contour and the source (speech) content is difficult to learn in a text-free situation. This paper proposes AlignSTS, an STS model based on explicit cross-modal alignment, which views speech variance such as pitch and content as different modalities. Inspired by the mechanism of how humans will sing the lyrics to the melody, AlignSTS: 1) adopts a novel rhythm adaptor to predict the target rhythm representation to bridge the modality gap between content and pitch, where the rhythm representation is computed in a simple yet effective way and is quantized into a discrete space; and 2) uses the predicted rhythm representation to re-align the content based on cross-attention and conducts a cross-modal fusion for re-synthesize. Extensive experiments show that AlignSTS achieves superior performance in terms of both objective and subjective metrics. Audio samples are available at https://alignsts.github.io.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2305.04476
- https://arxiv.org/pdf/2305.04476
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4376122405
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4376122405Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2305.04476Digital Object Identifier
- Title
-
AlignSTS: Speech-to-Singing Conversion via Cross-Modal AlignmentWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-05-08Full publication date if available
- Authors
-
Ruiqi Li, Rongjie Huang, Lichao Zhang, Jinglin Liu, Zhou ZhaoList of authors in order
- Landing page
-
https://arxiv.org/abs/2305.04476Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2305.04476Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2305.04476Direct OA link when available
- Concepts
-
Computer science, Singing, Speech recognition, Rhythm, Representation (politics), Modal, Lyrics, Acoustics, Political science, Chemistry, Law, Politics, Polymer chemistry, PhysicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4376122405 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2305.04476 |
| ids.doi | https://doi.org/10.48550/arxiv.2305.04476 |
| ids.openalex | https://openalex.org/W4376122405 |
| fwci | |
| type | preprint |
| title | AlignSTS: Speech-to-Singing Conversion via Cross-Modal Alignment |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10860 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9983000159263611 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1711 |
| topics[0].subfield.display_name | Signal Processing |
| topics[0].display_name | Speech and Audio Processing |
| topics[1].id | https://openalex.org/T11309 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9922999739646912 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1711 |
| topics[1].subfield.display_name | Signal Processing |
| topics[1].display_name | Music and Audio Processing |
| topics[2].id | https://openalex.org/T10201 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9911999702453613 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Speech Recognition and Synthesis |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7437887191772461 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C44819458 |
| concepts[1].level | 2 |
| concepts[1].score | 0.724590003490448 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q27939 |
| concepts[1].display_name | Singing |
| concepts[2].id | https://openalex.org/C28490314 |
| concepts[2].level | 1 |
| concepts[2].score | 0.6976752877235413 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q189436 |
| concepts[2].display_name | Speech recognition |
| concepts[3].id | https://openalex.org/C135343436 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6030333638191223 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q170406 |
| concepts[3].display_name | Rhythm |
| concepts[4].id | https://openalex.org/C2776359362 |
| concepts[4].level | 3 |
| concepts[4].score | 0.5618041753768921 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q2145286 |
| concepts[4].display_name | Representation (politics) |
| concepts[5].id | https://openalex.org/C71139939 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5135464668273926 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q910194 |
| concepts[5].display_name | Modal |
| concepts[6].id | https://openalex.org/C2776436406 |
| concepts[6].level | 2 |
| concepts[6].score | 0.457892507314682 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q602446 |
| concepts[6].display_name | Lyrics |
| concepts[7].id | https://openalex.org/C24890656 |
| concepts[7].level | 1 |
| concepts[7].score | 0.16644597053527832 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q82811 |
| concepts[7].display_name | Acoustics |
| concepts[8].id | https://openalex.org/C17744445 |
| concepts[8].level | 0 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q36442 |
| concepts[8].display_name | Political science |
| concepts[9].id | https://openalex.org/C185592680 |
| concepts[9].level | 0 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[9].display_name | Chemistry |
| concepts[10].id | https://openalex.org/C199539241 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q7748 |
| concepts[10].display_name | Law |
| concepts[11].id | https://openalex.org/C94625758 |
| concepts[11].level | 2 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q7163 |
| concepts[11].display_name | Politics |
| concepts[12].id | https://openalex.org/C188027245 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q750446 |
| concepts[12].display_name | Polymer chemistry |
| concepts[13].id | https://openalex.org/C121332964 |
| concepts[13].level | 0 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[13].display_name | Physics |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7437887191772461 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/singing |
| keywords[1].score | 0.724590003490448 |
| keywords[1].display_name | Singing |
| keywords[2].id | https://openalex.org/keywords/speech-recognition |
| keywords[2].score | 0.6976752877235413 |
| keywords[2].display_name | Speech recognition |
| keywords[3].id | https://openalex.org/keywords/rhythm |
| keywords[3].score | 0.6030333638191223 |
| keywords[3].display_name | Rhythm |
| keywords[4].id | https://openalex.org/keywords/representation |
| keywords[4].score | 0.5618041753768921 |
| keywords[4].display_name | Representation (politics) |
| keywords[5].id | https://openalex.org/keywords/modal |
| keywords[5].score | 0.5135464668273926 |
| keywords[5].display_name | Modal |
| keywords[6].id | https://openalex.org/keywords/lyrics |
| keywords[6].score | 0.457892507314682 |
| keywords[6].display_name | Lyrics |
| keywords[7].id | https://openalex.org/keywords/acoustics |
| keywords[7].score | 0.16644597053527832 |
| keywords[7].display_name | Acoustics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2305.04476 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2305.04476 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2305.04476 |
| locations[1].id | doi:10.48550/arxiv.2305.04476 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2305.04476 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100345540 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-2414-0617 |
| authorships[0].author.display_name | Ruiqi Li |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Li, Ruiqi |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5011787904 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-1695-9000 |
| authorships[1].author.display_name | Rongjie Huang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Huang, Rongjie |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5100638146 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-7555-7020 |
| authorships[2].author.display_name | Lichao Zhang |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Zhang, Lichao |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5065126806 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-9905-3887 |
| authorships[3].author.display_name | Jinglin Liu |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Liu, Jinglin |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5079260216 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-6121-0384 |
| authorships[4].author.display_name | Zhou Zhao |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Zhao, Zhou |
| authorships[4].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2305.04476 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | AlignSTS: Speech-to-Singing Conversion via Cross-Modal Alignment |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10860 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9983000159263611 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1711 |
| primary_topic.subfield.display_name | Signal Processing |
| primary_topic.display_name | Speech and Audio Processing |
| related_works | https://openalex.org/W2360952181, https://openalex.org/W4310670065, https://openalex.org/W634160686, https://openalex.org/W2597614303, https://openalex.org/W3214861561, https://openalex.org/W2389838651, https://openalex.org/W437317580, https://openalex.org/W2352995288, https://openalex.org/W2378183644, https://openalex.org/W2287414930 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2305.04476 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2305.04476 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2305.04476 |
| primary_location.id | pmh:oai:arXiv.org:2305.04476 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2305.04476 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2305.04476 |
| publication_date | 2023-05-08 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 17, 38, 82, 108, 117, 136 |
| abstract_inverted_index.1) | 80 |
| abstract_inverted_index.2) | 121 |
| abstract_inverted_index.an | 45 |
| abstract_inverted_index.as | 58, 62 |
| abstract_inverted_index.at | 161 |
| abstract_inverted_index.by | 66 |
| abstract_inverted_index.in | 37, 107, 149 |
| abstract_inverted_index.is | 33, 105, 114 |
| abstract_inverted_index.of | 69, 151 |
| abstract_inverted_index.on | 49, 132 |
| abstract_inverted_index.to | 7, 12, 35, 76, 86, 92, 127 |
| abstract_inverted_index.STS | 46 |
| abstract_inverted_index.The | 0 |
| abstract_inverted_index.and | 28, 60, 99, 113, 120, 134, 154 |
| abstract_inverted_index.are | 159 |
| abstract_inverted_index.for | 139 |
| abstract_inverted_index.gap | 96 |
| abstract_inverted_index.how | 70 |
| abstract_inverted_index.the | 20, 23, 29, 67, 74, 77, 88, 94, 102, 123, 129 |
| abstract_inverted_index.way | 112 |
| abstract_inverted_index.yet | 110 |
| abstract_inverted_index.This | 41 |
| abstract_inverted_index.aims | 6 |
| abstract_inverted_index.both | 152 |
| abstract_inverted_index.into | 116 |
| abstract_inverted_index.show | 143 |
| abstract_inverted_index.sing | 73 |
| abstract_inverted_index.such | 57 |
| abstract_inverted_index.task | 5 |
| abstract_inverted_index.that | 144 |
| abstract_inverted_index.uses | 122 |
| abstract_inverted_index.will | 72 |
| abstract_inverted_index.(STS) | 2 |
| abstract_inverted_index.Audio | 157 |
| abstract_inverted_index.based | 48, 131 |
| abstract_inverted_index.learn | 36 |
| abstract_inverted_index.major | 18 |
| abstract_inverted_index.model | 47 |
| abstract_inverted_index.novel | 83 |
| abstract_inverted_index.paper | 42 |
| abstract_inverted_index.pitch | 26, 59 |
| abstract_inverted_index.terms | 150 |
| abstract_inverted_index.views | 54 |
| abstract_inverted_index.voice | 3 |
| abstract_inverted_index.where | 101 |
| abstract_inverted_index.which | 53 |
| abstract_inverted_index.while | 15 |
| abstract_inverted_index.adopts | 81 |
| abstract_inverted_index.bridge | 93 |
| abstract_inverted_index.facing | 16 |
| abstract_inverted_index.fusion | 138 |
| abstract_inverted_index.humans | 71 |
| abstract_inverted_index.lyrics | 75 |
| abstract_inverted_index.pitch, | 100 |
| abstract_inverted_index.rhythm | 84, 90, 103, 125 |
| abstract_inverted_index.simple | 109 |
| abstract_inverted_index.source | 30 |
| abstract_inverted_index.space; | 119 |
| abstract_inverted_index.speech | 13, 55 |
| abstract_inverted_index.target | 24, 89 |
| abstract_inverted_index.adaptor | 85 |
| abstract_inverted_index.between | 22, 97 |
| abstract_inverted_index.content | 32, 61, 98, 130 |
| abstract_inverted_index.contour | 27 |
| abstract_inverted_index.melody, | 78 |
| abstract_inverted_index.predict | 87 |
| abstract_inverted_index.samples | 10, 158 |
| abstract_inverted_index.singing | 9 |
| abstract_inverted_index.(speech) | 31 |
| abstract_inverted_index.AlignSTS | 145 |
| abstract_inverted_index.Inspired | 65 |
| abstract_inverted_index.achieves | 146 |
| abstract_inverted_index.computed | 106 |
| abstract_inverted_index.conducts | 135 |
| abstract_inverted_index.discrete | 118 |
| abstract_inverted_index.explicit | 50 |
| abstract_inverted_index.generate | 8 |
| abstract_inverted_index.metrics. | 156 |
| abstract_inverted_index.modality | 95 |
| abstract_inverted_index.proposes | 43 |
| abstract_inverted_index.re-align | 128 |
| abstract_inverted_index.superior | 147 |
| abstract_inverted_index.variance | 56 |
| abstract_inverted_index.(singing) | 25 |
| abstract_inverted_index.AlignSTS, | 44 |
| abstract_inverted_index.AlignSTS: | 79 |
| abstract_inverted_index.Extensive | 141 |
| abstract_inverted_index.alignment | 21 |
| abstract_inverted_index.available | 160 |
| abstract_inverted_index.different | 63 |
| abstract_inverted_index.difficult | 34 |
| abstract_inverted_index.effective | 111 |
| abstract_inverted_index.mechanism | 68 |
| abstract_inverted_index.objective | 153 |
| abstract_inverted_index.predicted | 124 |
| abstract_inverted_index.quantized | 115 |
| abstract_inverted_index.text-free | 39 |
| abstract_inverted_index.alignment, | 52 |
| abstract_inverted_index.challenge: | 19 |
| abstract_inverted_index.conversion | 4 |
| abstract_inverted_index.recordings | 14 |
| abstract_inverted_index.situation. | 40 |
| abstract_inverted_index.subjective | 155 |
| abstract_inverted_index.cross-modal | 51, 137 |
| abstract_inverted_index.experiments | 142 |
| abstract_inverted_index.modalities. | 64 |
| abstract_inverted_index.performance | 148 |
| abstract_inverted_index.corresponding | 11 |
| abstract_inverted_index.re-synthesize. | 140 |
| abstract_inverted_index.representation | 91, 104, 126 |
| abstract_inverted_index.cross-attention | 133 |
| abstract_inverted_index.speech-to-singing | 1 |
| abstract_inverted_index.https://alignsts.github.io. | 162 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| citation_normalized_percentile |