Extending Whisper with prompt tuning to target-speaker ASR Article Swipe
Hao Ma
,
Zhiyuan Peng
,
Mingjie Shao
,
Jing Li
,
Ju Liu
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2312.08079
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2312.08079
Target-speaker automatic speech recognition (ASR) aims to transcribe the desired speech of a target speaker from multi-talker overlapped utterances. Most of the existing target-speaker ASR (TS-ASR) methods involve either training from scratch or fully fine-tuning a pre-trained model, leading to significant training costs and becoming inapplicable to large foundation models. This work leverages prompt tuning, a parameter-efficient fine-tuning approach, to extend Whisper, a large-scale single-talker ASR model, to TS-ASR. Variants of prompt tuning approaches along with their configurations are explored and optimized for TS-ASR.Experimental results show that prompt tuning can achieve performance comparable to state-of-the-art full training approaches while only requiring about 1\% of task-specific model parameters. Notably, the original Whisper's features, such as inverse text normalization and timestamp tagging, are retained in target-speaker ASR, keeping the generated transcriptions natural and informative.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2312.08079
- https://arxiv.org/pdf/2312.08079
- OA Status
- green
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4389768665
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4389768665Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2312.08079Digital Object Identifier
- Title
-
Extending Whisper with prompt tuning to target-speaker ASRWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-12-13Full publication date if available
- Authors
-
Hao Ma, Zhiyuan Peng, Mingjie Shao, Jing Li, Ju LiuList of authors in order
- Landing page
-
https://arxiv.org/abs/2312.08079Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2312.08079Direct 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/2312.08079Direct OA link when available
- Concepts
-
Computer science, Speech recognition, Normalization (sociology), Speaker recognition, Scratch, Task (project management), Artificial intelligence, Economics, Management, Sociology, Anthropology, Operating systemTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4389768665 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2312.08079 |
| ids.doi | https://doi.org/10.48550/arxiv.2312.08079 |
| ids.openalex | https://openalex.org/W4389768665 |
| fwci | |
| type | preprint |
| title | Extending Whisper with prompt tuning to target-speaker ASR |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10201 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9993000030517578 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Speech Recognition and Synthesis |
| topics[1].id | https://openalex.org/T10860 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9746000170707703 |
| 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 | Speech and Audio Processing |
| topics[2].id | https://openalex.org/T10181 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.974399983882904 |
| 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 | Natural Language Processing Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.8541664481163025 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C28490314 |
| concepts[1].level | 1 |
| concepts[1].score | 0.6789228320121765 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q189436 |
| concepts[1].display_name | Speech recognition |
| concepts[2].id | https://openalex.org/C136886441 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6488336324691772 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q926129 |
| concepts[2].display_name | Normalization (sociology) |
| concepts[3].id | https://openalex.org/C133892786 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5499300360679626 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1145189 |
| concepts[3].display_name | Speaker recognition |
| concepts[4].id | https://openalex.org/C2781235140 |
| concepts[4].level | 2 |
| concepts[4].score | 0.4328049123287201 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q275131 |
| concepts[4].display_name | Scratch |
| concepts[5].id | https://openalex.org/C2780451532 |
| concepts[5].level | 2 |
| concepts[5].score | 0.41073620319366455 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q759676 |
| concepts[5].display_name | Task (project management) |
| concepts[6].id | https://openalex.org/C154945302 |
| concepts[6].level | 1 |
| concepts[6].score | 0.36168527603149414 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[6].display_name | Artificial intelligence |
| concepts[7].id | https://openalex.org/C162324750 |
| concepts[7].level | 0 |
| concepts[7].score | 0.0 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[7].display_name | Economics |
| concepts[8].id | https://openalex.org/C187736073 |
| concepts[8].level | 1 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q2920921 |
| concepts[8].display_name | Management |
| concepts[9].id | https://openalex.org/C144024400 |
| concepts[9].level | 0 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q21201 |
| concepts[9].display_name | Sociology |
| concepts[10].id | https://openalex.org/C19165224 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q23404 |
| concepts[10].display_name | Anthropology |
| concepts[11].id | https://openalex.org/C111919701 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[11].display_name | Operating system |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8541664481163025 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/speech-recognition |
| keywords[1].score | 0.6789228320121765 |
| keywords[1].display_name | Speech recognition |
| keywords[2].id | https://openalex.org/keywords/normalization |
| keywords[2].score | 0.6488336324691772 |
| keywords[2].display_name | Normalization (sociology) |
| keywords[3].id | https://openalex.org/keywords/speaker-recognition |
| keywords[3].score | 0.5499300360679626 |
| keywords[3].display_name | Speaker recognition |
| keywords[4].id | https://openalex.org/keywords/scratch |
| keywords[4].score | 0.4328049123287201 |
| keywords[4].display_name | Scratch |
| keywords[5].id | https://openalex.org/keywords/task |
| keywords[5].score | 0.41073620319366455 |
| keywords[5].display_name | Task (project management) |
| keywords[6].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[6].score | 0.36168527603149414 |
| keywords[6].display_name | Artificial intelligence |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2312.08079 |
| 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 | public-domain |
| locations[0].pdf_url | https://arxiv.org/pdf/2312.08079 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | https://openalex.org/licenses/public-domain |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2312.08079 |
| locations[1].id | doi:10.48550/arxiv.2312.08079 |
| 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 | public-domain |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/public-domain |
| 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.2312.08079 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100452334 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-8585-6665 |
| authorships[0].author.display_name | Hao Ma |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Ma, Hao |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5075223216 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-9870-4422 |
| authorships[1].author.display_name | Zhiyuan Peng |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Peng, Zhiyuan |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5025217534 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-0659-5765 |
| authorships[2].author.display_name | Mingjie Shao |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Shao, Mingjie |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5100313293 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-8446-6072 |
| authorships[3].author.display_name | Jing Li |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Li, Jing |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5100763011 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-3160-9233 |
| authorships[4].author.display_name | Ju Liu |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Liu, Ju |
| authorships[4].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2312.08079 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Extending Whisper with prompt tuning to target-speaker ASR |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10201 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9993000030517578 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Speech Recognition and Synthesis |
| related_works | https://openalex.org/W4297807400, https://openalex.org/W1491159402, https://openalex.org/W4313854686, https://openalex.org/W321304764, https://openalex.org/W2249138175, https://openalex.org/W3162054169, https://openalex.org/W1813780412, https://openalex.org/W289407349, https://openalex.org/W2029134149, https://openalex.org/W2368768466 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2312.08079 |
| 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 | public-domain |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2312.08079 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | https://openalex.org/licenses/public-domain |
| 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/2312.08079 |
| primary_location.id | pmh:oai:arXiv.org:2312.08079 |
| 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 | public-domain |
| primary_location.pdf_url | https://arxiv.org/pdf/2312.08079 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | https://openalex.org/licenses/public-domain |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2312.08079 |
| publication_date | 2023-12-13 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 12, 35, 55, 62 |
| abstract_inverted_index.as | 113 |
| abstract_inverted_index.in | 122 |
| abstract_inverted_index.of | 11, 20, 70, 103 |
| abstract_inverted_index.or | 32 |
| abstract_inverted_index.to | 6, 39, 46, 59, 67, 93 |
| abstract_inverted_index.1\% | 102 |
| abstract_inverted_index.ASR | 24, 65 |
| abstract_inverted_index.and | 43, 80, 117, 130 |
| abstract_inverted_index.are | 78, 120 |
| abstract_inverted_index.can | 89 |
| abstract_inverted_index.for | 82 |
| abstract_inverted_index.the | 8, 21, 108, 126 |
| abstract_inverted_index.ASR, | 124 |
| abstract_inverted_index.Most | 19 |
| abstract_inverted_index.This | 50 |
| abstract_inverted_index.aims | 5 |
| abstract_inverted_index.from | 15, 30 |
| abstract_inverted_index.full | 95 |
| abstract_inverted_index.only | 99 |
| abstract_inverted_index.show | 85 |
| abstract_inverted_index.such | 112 |
| abstract_inverted_index.text | 115 |
| abstract_inverted_index.that | 86 |
| abstract_inverted_index.with | 75 |
| abstract_inverted_index.work | 51 |
| abstract_inverted_index.(ASR) | 4 |
| abstract_inverted_index.about | 101 |
| abstract_inverted_index.along | 74 |
| abstract_inverted_index.costs | 42 |
| abstract_inverted_index.fully | 33 |
| abstract_inverted_index.large | 47 |
| abstract_inverted_index.model | 105 |
| abstract_inverted_index.their | 76 |
| abstract_inverted_index.while | 98 |
| abstract_inverted_index.either | 28 |
| abstract_inverted_index.extend | 60 |
| abstract_inverted_index.model, | 37, 66 |
| abstract_inverted_index.prompt | 53, 71, 87 |
| abstract_inverted_index.speech | 2, 10 |
| abstract_inverted_index.target | 13 |
| abstract_inverted_index.tuning | 72, 88 |
| abstract_inverted_index.TS-ASR. | 68 |
| abstract_inverted_index.achieve | 90 |
| abstract_inverted_index.desired | 9 |
| abstract_inverted_index.inverse | 114 |
| abstract_inverted_index.involve | 27 |
| abstract_inverted_index.keeping | 125 |
| abstract_inverted_index.leading | 38 |
| abstract_inverted_index.methods | 26 |
| abstract_inverted_index.models. | 49 |
| abstract_inverted_index.natural | 129 |
| abstract_inverted_index.results | 84 |
| abstract_inverted_index.scratch | 31 |
| abstract_inverted_index.speaker | 14 |
| abstract_inverted_index.tuning, | 54 |
| abstract_inverted_index.(TS-ASR) | 25 |
| abstract_inverted_index.Notably, | 107 |
| abstract_inverted_index.Variants | 69 |
| abstract_inverted_index.Whisper, | 61 |
| abstract_inverted_index.becoming | 44 |
| abstract_inverted_index.existing | 22 |
| abstract_inverted_index.explored | 79 |
| abstract_inverted_index.original | 109 |
| abstract_inverted_index.retained | 121 |
| abstract_inverted_index.tagging, | 119 |
| abstract_inverted_index.training | 29, 41, 96 |
| abstract_inverted_index.Whisper's | 110 |
| abstract_inverted_index.approach, | 58 |
| abstract_inverted_index.automatic | 1 |
| abstract_inverted_index.features, | 111 |
| abstract_inverted_index.generated | 127 |
| abstract_inverted_index.leverages | 52 |
| abstract_inverted_index.optimized | 81 |
| abstract_inverted_index.requiring | 100 |
| abstract_inverted_index.timestamp | 118 |
| abstract_inverted_index.approaches | 73, 97 |
| abstract_inverted_index.comparable | 92 |
| abstract_inverted_index.foundation | 48 |
| abstract_inverted_index.overlapped | 17 |
| abstract_inverted_index.transcribe | 7 |
| abstract_inverted_index.fine-tuning | 34, 57 |
| abstract_inverted_index.large-scale | 63 |
| abstract_inverted_index.parameters. | 106 |
| abstract_inverted_index.performance | 91 |
| abstract_inverted_index.pre-trained | 36 |
| abstract_inverted_index.recognition | 3 |
| abstract_inverted_index.significant | 40 |
| abstract_inverted_index.utterances. | 18 |
| abstract_inverted_index.inapplicable | 45 |
| abstract_inverted_index.informative. | 131 |
| abstract_inverted_index.multi-talker | 16 |
| abstract_inverted_index.normalization | 116 |
| abstract_inverted_index.single-talker | 64 |
| abstract_inverted_index.task-specific | 104 |
| abstract_inverted_index.Target-speaker | 0 |
| abstract_inverted_index.configurations | 77 |
| abstract_inverted_index.target-speaker | 23, 123 |
| abstract_inverted_index.transcriptions | 128 |
| abstract_inverted_index.state-of-the-art | 94 |
| abstract_inverted_index.TS-ASR.Experimental | 83 |
| abstract_inverted_index.parameter-efficient | 56 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.47999998927116394 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile |