{"id":"https://openalex.org/W4415432963","doi":"https://doi.org/10.21437/interspeech.2025-2394","title":"75-Speaker Annot-16: A benchmark dataset for speech articulatory rt-MRI annotation with articulator contours and phonetic alignment","display_name":"75-Speaker Annot-16: A benchmark dataset for speech articulatory rt-MRI annotation with articulator contours and phonetic alignment","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432963","doi":"https://doi.org/10.21437/interspeech.2025-2394"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-2394","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21437/Interspeech.2025-2394","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101907238","display_name":"Xuan Shi","orcid":"https://orcid.org/0000-0002-1387-5418"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xuan Shi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100700236","display_name":"Yubin Zhang","orcid":"https://orcid.org/0000-0001-8539-1474"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yubin Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020666400","display_name":"Yanqing Lu","orcid":"https://orcid.org/0000-0001-6151-8557"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yijing Lu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012084359","display_name":"Marcus Ma","orcid":"https://orcid.org/0009-0005-8754-9411"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcus Ma","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059679122","display_name":"Tiantian Feng","orcid":"https://orcid.org/0000-0002-2053-9068"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tiantian Feng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030228191","display_name":"Asterios Toutios","orcid":"https://orcid.org/0000-0003-3193-2241"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Asterios Toutios","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113221066","display_name":"Haley Hsu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haley Hsu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110122617","display_name":"Louis Goldstein","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Louis Goldstein","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101907238"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16460852,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2175","last_page":"2179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9864000082015991,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9864000082015991,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9100000262260437,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/articulator","display_name":"Articulator","score":0.902999997138977},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7538999915122986},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.609499990940094},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2736999988555908},{"id":"https://openalex.org/keywords/phonetics","display_name":"Phonetics","score":0.271699994802475}],"concepts":[{"id":"https://openalex.org/C2778415344","wikidata":"https://www.wikidata.org/wiki/Q443216","display_name":"Articulator","level":2,"score":0.902999997138977},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7538999915122986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6976000070571899},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.609499990940094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5697000026702881},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5508000254631042},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4433000087738037},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25949999690055847},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-2394","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:zenodo.org:18931763","is_oa":true,"landing_page_url":"https://doi.org/10.21437/Interspeech.2025-2394","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"75-Speaker Annot-16: A benchmark dataset for speech articulatory rt-MRI annotation with articulator contours and phonetic alignment, Rotterdam, The Netherlands, 17-21 August 2025","raw_type":"info:eu-repo/semantics/other"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:18931763","is_oa":true,"landing_page_url":"https://doi.org/10.21437/Interspeech.2025-2394","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"75-Speaker Annot-16: A benchmark dataset for speech articulatory rt-MRI annotation with articulator contours and phonetic alignment, Rotterdam, The Netherlands, 17-21 August 2025","raw_type":"info:eu-repo/semantics/other"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"<p>High-quality":[0],"speech":[1,7,92],"articulatory":[2,79],"databases":[3],"are":[4],"essential":[5],"for advancing":[6],"science":[8],"and":[9,22,50,66,102],"technology":[10],"research.":[11],"However, the":[12],"lack":[13],"of":[14],"standardized":[15],"annotations":[16],"limits":[17],"their":[18],"full":[19],"potential":[20],"use":[21],"broad":[23],"accessibility.":[24],"In":[25],"this":[26],"context,":[27],"we":[28,72],"introduce 75-Speaker":[29],"Annot-16,":[30],"a":[31],"comprehensive":[32],"annotation":[33],"dataset":[34],"derived":[35],"from":[36],"the":[37],"75-Speaker":[38],"vocal":[39],"tract":[40],"MRI":[41],"database.":[42],"Annot-16":[43,85],"provides":[44],"phonetic":[45],"alignments,":[46],"articulator":[47,53],"contour":[48,80],"annotations,":[49],"handmade":[51],"ground-truth":[52],"contours.":[54],"Our annotation":[55],"process":[56],"integrates":[57],"automated":[58],"algorithms":[59],"with":[60],"expert":[61],"verification":[62],"to":[63],"ensure":[64],"accuracy":[65],"efficiency.":[67],"To":[68],"demonstrate":[69],"its":[70],"utility,":[71],"establish":[73],"three":[74],"benchmark":[75],"tasks:":[76],"speech phoneme":[77],"recognition,":[78],"segmentation,":[81],"and articulatory":[82],"phoneme":[83],"recognition.":[84],"can":[86],"serve":[87],"as a":[88],"valuable":[89],"resource":[90],"for":[91],"modeling,":[93],"computer":[94],"vision, and":[95],"cross-modal":[96],"learning,":[97],"bridging":[98],"engineering":[99],"applications, speech":[100],"science,":[101],"linguistic":[103],"research.</p>":[104]},"counts_by_year":[],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-24T00:00:00"}