{"id":"https://openalex.org/W3006094508","doi":"https://doi.org/10.1109/icassp40776.2020.9053053","title":"Phoneme Boundary Detection Using Learnable Segmental Features","display_name":"Phoneme Boundary Detection Using Learnable Segmental Features","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3006094508","doi":"https://doi.org/10.1109/icassp40776.2020.9053053","mag":"3006094508"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5000406733","display_name":"Felix Kreuk","orcid":null},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Felix Kreuk","raw_affiliation_strings":["Bar-Ilan University, Ramat-Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Bar-Ilan University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080035574","display_name":"Yaniv Sheena","orcid":"https://orcid.org/0009-0006-4738-1260"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yaniv Sheena","raw_affiliation_strings":["Facebook Inc"],"affiliations":[{"raw_affiliation_string":"Facebook Inc","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008847407","display_name":"Joseph Keshet","orcid":"https://orcid.org/0000-0003-2332-5783"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Joseph Keshet","raw_affiliation_strings":["Bar-Ilan University, Ramat-Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Bar-Ilan University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005191803","display_name":"Yossi Adi","orcid":"https://orcid.org/0000-0003-2237-3898"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yossi Adi","raw_affiliation_strings":["Facebook AI Research"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5000406733"],"corresponding_institution_ids":["https://openalex.org/I13955877"],"apc_list":null,"apc_paid":null,"fwci":2.5186,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.91200315,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8089","last_page":"8093"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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/T10860","display_name":"Speech and Audio Processing","score":0.9976000189781189,"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/timit","display_name":"TIMIT","score":0.8343411684036255},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7972872257232666},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7177189588546753},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.6947633624076843},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.6212236285209656},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5648700594902039},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4571854770183563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45564988255500793},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.44349992275238037},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43613535165786743},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42817947268486023},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.4270179867744446},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3974452018737793},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08232730627059937},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07406297326087952},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07223048806190491},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.06944617629051208}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.8343411684036255},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7972872257232666},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7177189588546753},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.6947633624076843},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.6212236285209656},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5648700594902039},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4571854770183563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45564988255500793},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.44349992275238037},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43613535165786743},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42817947268486023},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4270179867744446},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3974452018737793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08232730627059937},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07406297326087952},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07223048806190491},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.06944617629051208},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W130754613","https://openalex.org/W1558402681","https://openalex.org/W1761091820","https://openalex.org/W2017814685","https://openalex.org/W2069732686","https://openalex.org/W2074394031","https://openalex.org/W2077828209","https://openalex.org/W2083904075","https://openalex.org/W2096270777","https://openalex.org/W2098363562","https://openalex.org/W2116656681","https://openalex.org/W2124343046","https://openalex.org/W2145410271","https://openalex.org/W2145678789","https://openalex.org/W2151244813","https://openalex.org/W2161914416","https://openalex.org/W2171752983","https://openalex.org/W2291022022","https://openalex.org/W2301095666","https://openalex.org/W2343041606","https://openalex.org/W2344888084","https://openalex.org/W2542955097","https://openalex.org/W2545132779","https://openalex.org/W2620638943","https://openalex.org/W2747874407","https://openalex.org/W2963137467","https://openalex.org/W2963795358","https://openalex.org/W3127686677","https://openalex.org/W6637748604","https://openalex.org/W6681658821","https://openalex.org/W6683825394","https://openalex.org/W6684765037","https://openalex.org/W6704862255","https://openalex.org/W6738767006","https://openalex.org/W6738773844","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W3119978414","https://openalex.org/W2114097550","https://openalex.org/W2766204198","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W1969408022"],"abstract_inverted_index":{"Phoneme":[0],"boundary":[1,48],"detection":[2],"plays":[3],"an":[4],"essential":[5],"first":[6],"step":[7],"for":[8,43],"a":[9,29,34,122,134],"variety":[10],"of":[11,46,88,97],"speech":[12,19],"processing":[13],"applications":[14],"such":[15,127],"as":[16,62,100],"speaker":[17],"diarization,":[18],"science,":[20],"keyword":[21],"spotting,":[22],"etc.":[23],"In":[24],"this":[25,105],"work,":[26],"we":[27,51],"propose":[28],"neural":[30],"architecture":[31],"coupled":[32],"with":[33],"parameterized":[35],"structured":[36],"loss":[37],"function":[38],"to":[39,78],"learn":[40],"segmental":[41],"representations":[42],"the":[44,56,66,73,79,95,119],"task":[45],"phoneme":[47],"detection.":[49],"First,":[50],"evaluated":[52],"our":[53],"model":[54,75,120],"when":[55],"spoken":[57],"phonemes":[58],"were":[59],"not":[60],"given":[61],"input.":[63],"Results":[64],"on":[65,121],"TIMIT":[67],"and":[68,82,90,103,125],"Buckeye":[69],"corpora":[70],"suggest":[71],"that":[72],"proposed":[74],"is":[76],"superior":[77],"baseline":[80],"models":[81],"reaches":[83],"state-of-the-art":[84],"performance":[85,110],"in":[86,109,133],"terms":[87],"F1":[89],"R-value.":[91],"We":[92,116],"further":[93],"explore":[94],"use":[96],"phonetic":[98,128],"transcription":[99],"additional":[101],"supervision":[102,129],"show":[104],"yields":[106],"minor":[107],"improvements":[108],"but":[111],"substantially":[112],"better":[113],"convergence":[114],"rates.":[115],"additionally":[117],"evaluate":[118],"He-brew":[123],"corpus":[124],"demonstrate":[126],"can":[130],"be":[131],"beneficial":[132],"multi-lingual":[135],"setting.":[136]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}