{"id":"https://openalex.org/W4415433641","doi":"https://doi.org/10.21437/interspeech.2025-17","title":"Auto-Landmark: Acoustic Landmark Dataset and Open-Source Toolkit for Landmark Extraction","display_name":"Auto-Landmark: Acoustic Landmark Dataset and Open-Source Toolkit for Landmark Extraction","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433641","doi":"https://doi.org/10.21437/interspeech.2025-17"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-17","doi":"https://doi.org/10.21437/interspeech.2025-17","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-17","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.07969","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100362464","display_name":"Xiangyu Zhang","orcid":"https://orcid.org/0000-0003-0876-6783","observed_orcids":["https://orcid.org/0000-0003-0876-6783"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangyu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027916884","display_name":"Daijiao Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daijiao Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Tianyi Xiao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyi Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110996142","display_name":"Cihan Xiao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cihan Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072612005","display_name":"T\u00fcnde Szalay","orcid":"https://orcid.org/0000-0002-6982-5639","observed_orcids":["https://orcid.org/0000-0002-6982-5639"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"T\u00fcnde Szalay","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073612124","display_name":"Mostafa Ali Shahin","orcid":"https://orcid.org/0000-0002-1091-8531","observed_orcids":["https://orcid.org/0000-0002-1091-8531"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mostafa Shahin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077436139","display_name":"Beena Ahmed","orcid":"https://orcid.org/0000-0002-1240-6572","observed_orcids":["https://orcid.org/0000-0002-1240-6572"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Beena Ahmed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5030922449","display_name":"Julien Epps","orcid":"https://orcid.org/0000-0001-6624-5551","observed_orcids":["https://orcid.org/0000-0001-6624-5551"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julien Epps","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6112,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.94430993,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4263","last_page":"4267"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.6195999979972839,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.6195999979972839,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.10159999877214432,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10860","display_name":"Speech and Audio Processing","score":0.028200000524520874,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/acoustic-landmarks","display_name":"acoustic landmarks","score":0.7900000214576721},{"id":"https://openalex.org/keywords/landmark-extraction","display_name":"landmark extraction","score":0.8899999856948853},{"id":"https://openalex.org/keywords/speech-processing","display_name":"speech processing","score":0.4099999964237213},{"id":"https://openalex.org/keywords/open-source-toolkit","display_name":"open-source software toolkit","score":0.7450000047683716}],"concepts":[{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.8794999718666077},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6262999773025513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6119999885559082},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5485000014305115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.21490000188350677},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.21160000562667847}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2025-17","doi":"https://doi.org/10.21437/interspeech.2025-17","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-17","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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:arXiv.org:2409.07969","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.07969","pdf_url":"https://arxiv.org/pdf/2409.07969","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2409.07969","doi":"https://doi.org/10.48550/arxiv.2409.07969","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.07969","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.07969","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.07969","pdf_url":"https://arxiv.org/pdf/2409.07969","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415433641.pdf","grobid_xml":"https://content.openalex.org/works/W4415433641.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W207577192","https://openalex.org/W7165663326","https://openalex.org/W2624975422","https://openalex.org/W4242640703","https://openalex.org/W2396422315","https://openalex.org/W7112175973","https://openalex.org/W2068877227","https://openalex.org/W389609507","https://openalex.org/W2041368561","https://openalex.org/W7098365902"],"abstract_inverted_index":{"In":[0,73],"the":[1,9,13,42,78,89,142],"speech":[2,31,33,39],"signal,":[3],"acoustic":[4,10,81],"landmarks":[5,22,82],"identify":[6],"times":[7],"when":[8],"manifestations":[11],"of":[12,38,44,98,133,139,161],"linguistically":[14],"motivated":[15],"distinctive":[16],"features":[17],"are":[18,154],"most":[19,79],"salient.":[20],"Acoustic":[21],"have":[23],"been":[24,63],"widely":[25],"applied":[26],"in":[27],"various":[28],"domains,":[29],"including":[30],"recognition,":[32],"depression":[34],"detection,":[35],"clinical":[36],"analysis":[37],"abnormalities,":[40],"and":[41,87,102,129,152],"detection":[43,135],"disordered":[45],"speech.":[46],"However,":[47],"there":[48],"is":[49],"currently":[50],"no":[51],"dataset":[52,91,143],"available":[53],"that":[54],"provides":[55],"precise":[56,146],"timing":[57,147],"information":[58,101],"for":[59,68],"landmarks,":[60],"which":[61],"has":[62],"proven":[64],"to":[65,117,156],"be":[66],"crucial":[67],"downstream":[69],"applications":[70],"involving":[71],"landmarks.":[72],"this":[74],"paper,":[75],"we":[76,120],"selected":[77],"useful":[80],"based":[83,94],"on":[84,95],"previous":[85,106],"research":[86],"annotated":[88],"TIMIT":[90],"with":[92,144],"them,":[93],"a":[96,131,158],"combination":[97],"phoneme":[99],"boundary":[100],"manual":[103],"inspection.":[104],"Moreover,":[105],"landmark":[107,126,134,145,149],"extraction":[108,127,150],"tools":[109],"were":[110],"not":[111],"open":[112,123],"source":[113,124],"or":[114],"benchmarked,":[115],"so":[116],"address":[118],"this,":[119],"developed":[121],"an":[122],"Python-based":[125],"tool":[128,151],"established":[130],"series":[132],"baselines.":[136],"The":[137],"first":[138],"their":[140],"kinds,":[141],"information,":[148],"baselines":[153],"designed":[155],"support":[157],"wide":[159],"variety":[160],"future":[162],"research.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-10-24T00:00:00"}