{"id":"https://openalex.org/W2132214951","doi":"https://doi.org/10.1109/icassp.2002.5743652","title":"Robust speech recognition in Noisy Environments: The 2001 IBM spine evaluation system","display_name":"Robust speech recognition in Noisy Environments: The 2001 IBM spine evaluation system","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2132214951","doi":"https://doi.org/10.1109/icassp.2002.5743652","mag":"2132214951"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743652","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743652","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"IEEE International Conference on Acoustics Speech and Signal Processing","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/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"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"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, NY, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"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"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, NY, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019973376","display_name":"Lidia Mangu","orcid":null},"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"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lidia Mangu","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, NY, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109890066","display_name":"M. Padmanabhan","orcid":null},"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"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mukund Padmanabhan","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, NY, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072875068","display_name":"Ruhi Sarikaya","orcid":"https://orcid.org/0000-0003-2676-2831"},"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"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruhi Sarikaya","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, NY, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"I","last_page":"53"},"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/T10860","display_name":"Speech and Audio Processing","score":0.995199978351593,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7756891250610352},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7654668092727661},{"id":"https://openalex.org/keywords/voice","display_name":"Voice","score":0.6797695755958557},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6616412997245789},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.6172959208488464},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5863884687423706},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.559493362903595},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5460389852523804},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4771239757537842},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4376695156097412},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4341588020324707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4300648272037506},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42032143473625183},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33267149329185486},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10515522956848145}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7756891250610352},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7654668092727661},{"id":"https://openalex.org/C552089266","wikidata":"https://www.wikidata.org/wiki/Q494510","display_name":"Voice","level":2,"score":0.6797695755958557},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6616412997245789},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.6172959208488464},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5863884687423706},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.559493362903595},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5460389852523804},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4771239757537842},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4376695156097412},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4341588020324707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4300648272037506},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42032143473625183},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33267149329185486},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10515522956848145},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2002.5743652","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743652","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W48678258","https://openalex.org/W111666610","https://openalex.org/W196692374","https://openalex.org/W1596681162","https://openalex.org/W1599512239","https://openalex.org/W1648458398","https://openalex.org/W2002342963","https://openalex.org/W2009179928","https://openalex.org/W2058542017","https://openalex.org/W2088744964","https://openalex.org/W2090861223","https://openalex.org/W2104663520","https://openalex.org/W2106420626","https://openalex.org/W2106554350","https://openalex.org/W2124629003","https://openalex.org/W2129334286","https://openalex.org/W2158195707","https://openalex.org/W2594610113","https://openalex.org/W6607928866","https://openalex.org/W6635496631","https://openalex.org/W6650992335","https://openalex.org/W7005860293"],"related_works":["https://openalex.org/W2036753972","https://openalex.org/W1996861825","https://openalex.org/W2079621619","https://openalex.org/W2046280377","https://openalex.org/W4388535697","https://openalex.org/W2036128733","https://openalex.org/W1976086899","https://openalex.org/W4285526294","https://openalex.org/W2313188200","https://openalex.org/W1975015735"],"abstract_inverted_index":{"We":[0],"report":[1],"on":[2,74],"the":[3,8,18,29,60,65,67,88,99],"system":[4,30],"IBM":[5],"fielded":[6],"in":[7,22],"second":[9],"SPeech":[10],"In":[11],"Noisy":[12],"Environments":[13],"(SPINE-2)":[14],"evaluation,":[15,66],"conducted":[16],"by":[17],"Naval":[19],"Research":[20],"Laboratory":[21],"October":[23],"2001.":[24],"The":[25],"key":[26],"components":[27],"of":[28,41,64,69],"include":[31],"an":[32],"HMM-based":[33],"automatic":[34],"segmentation":[35],"module":[36],"using":[37],"a":[38,47,81],"novel":[39],"set":[40],"LDA-transformed":[42],"voicing":[43],"and":[44,80,90],"energy":[45],"features,":[46],"multiple-pass":[48],"decoding":[49],"strategy":[50],"that":[51,85],"uses":[52,86],"several":[53],"speaker-and":[54],"environment-normalization":[55],"operations":[56],"to":[57,94],"deal":[58],"with":[59],"highly":[61],"variable":[62],"acoustics":[63],"combination":[68],"hypotheses":[70],"from":[71],"decoders":[72],"operating":[73],"three":[75],"distinct":[76],"acoustic":[77],"feature":[78],"sets,":[79],"class-based":[82],"language":[83],"model":[84],"both":[87],"SPINE-1":[89],"SPINE-2":[91,101],"training":[92],"data":[93],"estimate":[95],"reliable":[96],"probabilities":[97],"for":[98],"new":[100],"vocabulary.":[102]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
