{"id":"https://openalex.org/W4408352549","doi":"https://doi.org/10.1109/icassp49660.2025.10887983","title":"Target word activity detector: An approach to obtain ASR word boundaries without lexicon","display_name":"Target word activity detector: An approach to obtain ASR word boundaries without lexicon","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352549","doi":"https://doi.org/10.1109/icassp49660.2025.10887983"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113968312","display_name":"Sunit Sivasankaran","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sunit Sivasankaran","raw_affiliation_strings":["One Microsoft Way,Microsoft Speech and Language Group,Redmond,WA,USA"],"affiliations":[{"raw_affiliation_string":"One Microsoft Way,Microsoft Speech and Language Group,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090360853","display_name":"Eric Sun","orcid":"https://orcid.org/0000-0001-8805-9864"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Sun","raw_affiliation_strings":["One Microsoft Way,Microsoft Speech and Language Group,Redmond,WA,USA"],"affiliations":[{"raw_affiliation_string":"One Microsoft Way,Microsoft Speech and Language Group,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["One Microsoft Way,Microsoft Speech and Language Group,Redmond,WA,USA"],"affiliations":[{"raw_affiliation_string":"One Microsoft Way,Microsoft Speech and Language Group,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070676743","display_name":"Yan Huang","orcid":"https://orcid.org/0000-0001-7607-9585"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Huang","raw_affiliation_strings":["One Microsoft Way,Microsoft Speech and Language Group,Redmond,WA,USA"],"affiliations":[{"raw_affiliation_string":"One Microsoft Way,Microsoft Speech and Language Group,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101875418","display_name":"Jing Pan","orcid":"https://orcid.org/0000-0002-5178-2247"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Pan","raw_affiliation_strings":["One Microsoft Way,Microsoft Speech and Language Group,Redmond,WA,USA"],"affiliations":[{"raw_affiliation_string":"One Microsoft Way,Microsoft Speech and Language Group,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5113968312"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02010055,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9297000169754028,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9297000169754028,"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/lexicon","display_name":"Lexicon","score":0.7996015548706055},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7759850025177002},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7367834448814392},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5919775366783142},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5315929055213928},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5249100923538208},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.481625497341156},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23236340284347534},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.05558332800865173}],"concepts":[{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.7996015548706055},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7759850025177002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7367834448814392},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5919775366783142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5315929055213928},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5249100923538208},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.481625497341156},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23236340284347534},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.05558332800865173},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2144499799","https://openalex.org/W2157331557","https://openalex.org/W2327501763","https://openalex.org/W2962760690","https://openalex.org/W2963158258","https://openalex.org/W2963211739","https://openalex.org/W2963970535","https://openalex.org/W3016010032","https://openalex.org/W3016167541","https://openalex.org/W3025260599","https://openalex.org/W3094667432","https://openalex.org/W3095311338","https://openalex.org/W3096524176","https://openalex.org/W3097777922","https://openalex.org/W3161873870","https://openalex.org/W3197777440","https://openalex.org/W3207815550","https://openalex.org/W3211278025","https://openalex.org/W3212886388","https://openalex.org/W4210811812","https://openalex.org/W4372259977","https://openalex.org/W4385822753","https://openalex.org/W4388017359","https://openalex.org/W4391021542","https://openalex.org/W4391021781","https://openalex.org/W4402112361","https://openalex.org/W6679434410"],"related_works":["https://openalex.org/W2140536630","https://openalex.org/W3195005284","https://openalex.org/W2391730868","https://openalex.org/W4394659737","https://openalex.org/W2759814045","https://openalex.org/W2118055728","https://openalex.org/W4399756845","https://openalex.org/W1831473261","https://openalex.org/W4293870971","https://openalex.org/W2296205523"],"abstract_inverted_index":{"Obtaining":[0],"word":[1,57,66,79],"timestamp":[2],"information":[3,81],"from":[4,68],"end-to-end":[5],"(E2E)":[6],"ASR":[7,75,106],"models":[8],"remains":[9],"challenging":[10],"due":[11],"to":[12,40,55,89],"the":[13],"lack":[14],"of":[15,92],"explicit":[16],"time":[17],"alignment":[18,80],"during":[19,82],"training.":[20,83],"This":[21],"issue":[22],"is":[23],"further":[24],"complicated":[25],"in":[26],"multilingual":[27,105],"models.":[28],"Existing":[29],"methods,":[30],"either":[31],"rely":[32],"on":[33,61,109],"lexicons":[34],"or":[35],"introduce":[36],"additional":[37,97],"tokens,":[38],"leading":[39],"scalability":[41],"issues":[42],"and":[43,72,112],"increased":[44],"computational":[45],"costs.":[46],"In":[47],"this":[48],"work,":[49],"we":[50],"propose":[51],"a":[52,73,104,117],"new":[53],"approach":[54,102],"estimate":[56],"boundaries":[58],"without":[59,94],"relying":[60],"lexicons.":[62],"Our":[63,84],"method":[64,86],"leverages":[65],"embeddings":[67],"sub-word":[69],"token":[70],"units":[71],"pretrained":[74],"model,":[76],"requiring":[77],"only":[78],"proposed":[85],"can":[87],"scale-up":[88],"any":[90,96],"number":[91],"languages":[93,111],"incurring":[95],"cost.":[98],"We":[99],"validate":[100],"our":[101],"using":[103],"model":[107],"trained":[108],"five":[110],"demonstrate":[113],"its":[114],"effectiveness":[115],"against":[116],"strong":[118],"baseline.":[119]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}