{"id":"https://openalex.org/W1533680413","doi":"https://doi.org/10.21437/interspeech.2008-123","title":"A comparison of broad phonetic and acoustic units for noise robust segment-based phonetic recognition","display_name":"A comparison of broad phonetic and acoustic units for noise robust segment-based phonetic recognition","publication_year":2008,"publication_date":"2008-09-22","ids":{"openalex":"https://openalex.org/W1533680413","doi":"https://doi.org/10.21437/interspeech.2008-123","mag":"1533680413"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2008-123","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"},"type":"conference-paper","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/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tara N. Sainath","raw_affiliation_strings":["IBM (United States), Armonk, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109575396","display_name":"Victor W. Zue","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Victor Zue","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5036,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.5705387,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2378","last_page":"2381"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.8234409093856812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7976549863815308},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6740814447402954},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6593837141990662},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6038017868995667},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.47198373079299927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4361639618873596},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.41618987917900085},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40037381649017334},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3386608362197876},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31936782598495483},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10935753583908081}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.8234409093856812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7976549863815308},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6740814447402954},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6593837141990662},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6038017868995667},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.47198373079299927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4361639618873596},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.41618987917900085},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40037381649017334},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3386608362197876},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31936782598495483},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10935753583908081},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2008-123","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","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":9,"referenced_works":["https://openalex.org/W181056519","https://openalex.org/W573069471","https://openalex.org/W1610605641","https://openalex.org/W1802969839","https://openalex.org/W1957665339","https://openalex.org/W2083393647","https://openalex.org/W2111732304","https://openalex.org/W2138615112","https://openalex.org/W2162436288"],"related_works":["https://openalex.org/W1974738623","https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2340308015","https://openalex.org/W2083296885","https://openalex.org/W2121652828"],"abstract_inverted_index":{"In":[0,76],"this":[1],"paper,":[2],"we":[3,44,78],"compare":[4],"speech":[5,65],"recognition":[6],"performance":[7],"using":[8],"broad":[9],"phoneticallyand":[10],"acoustically-motivated":[11],"units":[12],"as":[13],"a":[14,18,29,67,72],"pre-processor":[15],"in":[16,61,89,98],"designing":[17],"novel":[19],"noise":[20,100],"robust":[21],"landmark":[22],"detection":[23],"and":[24,49,71],"segmentation":[25,51],"algorithm.":[26],"We":[27],"introduce":[28],"cluster":[30,37],"evaluation":[31],"method":[32,70,83],"to":[33],"measure":[34],"acoustic":[35,48,82],"unit":[36],"quality.":[38],"On":[39],"the":[40,47,62,81,93],"noisy":[41],"TIMIT":[42],"task,":[43],"find":[45,79],"that":[46,80],"phonetic":[50,94],"approaches":[52],"offer":[53],"significant":[54],"improvements":[55],"over":[56],"two":[57],"baseline":[58],"methods":[59],"used":[60],"SUMMIT":[63],"segment-based":[64],"recognizer,":[66],"sinusoidal":[68],"model":[69],"spectral":[73],"change":[74],"approach.":[75],"addition,":[77],"has":[84],"much":[85],"faster":[86,97],"computation":[87],"time":[88],"stationary":[90],"noises,":[91],"while":[92],"approach":[95],"is":[96],"non-stationary":[99],"conditions.":[101]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}