{"id":"https://openalex.org/W2406482790","doi":"https://doi.org/10.21437/interspeech.2015-563","title":"Segmental conditional random fields with deep neural networks as acoustic models for first-pass word recognition","display_name":"Segmental conditional random fields with deep neural networks as acoustic models for first-pass word recognition","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2406482790","doi":"https://doi.org/10.21437/interspeech.2015-563","mag":"2406482790"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-563","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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/A5101319167","display_name":"Yanzhang He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanzhang He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056667180","display_name":"Eric Fosler\u2010Lussier","orcid":"https://orcid.org/0000-0001-8004-5169"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Fosler-Lussier","raw_affiliation_strings":["Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2640","last_page":"2644"},"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.791088342666626},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7637536525726318},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7142856121063232},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.6917890310287476},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5204882025718689},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5163889527320862},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5123251676559448},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5039369463920593},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.49187421798706055},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.47994282841682434},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.47132590413093567},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4699321687221527},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41918954253196716},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41591253876686096},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2884502708911896},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1476086676120758},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10690966248512268}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791088342666626},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7637536525726318},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7142856121063232},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.6917890310287476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5204882025718689},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5163889527320862},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5123251676559448},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5039369463920593},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.49187421798706055},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.47994282841682434},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.47132590413093567},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4699321687221527},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41918954253196716},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41591253876686096},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2884502708911896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1476086676120758},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10690966248512268},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-563","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1553004968","https://openalex.org/W1895481600","https://openalex.org/W1981678206","https://openalex.org/W1984541135","https://openalex.org/W2024539680","https://openalex.org/W2034961825","https://openalex.org/W2083393647","https://openalex.org/W2097207027","https://openalex.org/W2103945478","https://openalex.org/W2111535841","https://openalex.org/W2111732304","https://openalex.org/W2114016253","https://openalex.org/W2131033001","https://openalex.org/W2146502635","https://openalex.org/W2147880316","https://openalex.org/W2151660570","https://openalex.org/W2158188757","https://openalex.org/W2158575505","https://openalex.org/W2160815625","https://openalex.org/W2161213733","https://openalex.org/W2395342389","https://openalex.org/W2403307209","https://openalex.org/W2403708103","https://openalex.org/W2541627266"],"related_works":["https://openalex.org/W2163278254","https://openalex.org/W155708904","https://openalex.org/W1574213390","https://openalex.org/W2162582511","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306"],"abstract_inverted_index":{"Discriminative":[0],"segmental":[1,5],"models,":[2],"such":[3,29],"as":[4,30,71],"conditional":[6],"random":[7],"fields":[8],"(SCRFs),":[9],"have":[10],"been":[11,39],"successfully":[12],"applied":[13],"to":[14,21,65,94,108],"speech":[15],"recognition":[16],"recently":[17],"in":[18,90,119],"lattice":[19,36],"rescoring":[20],"integrate":[22],"detectors":[23],"across":[24],"different":[25],"levels":[26],"of":[27],"units,":[28],"phones":[31,96],"and":[32,87,138],"words.":[33],"However,":[34],"the":[35,55,72,110,116,126,144],"generation":[37],"has":[38],"constrained":[40],"by":[41],"a":[42,46,75,105,134,139],"baseline":[43],"decoder,":[44],"typically":[45],"frame-based":[47],"hybrid":[48,135],"HMMDNN":[49],"system,":[50],"which":[51],"still":[52],"suffers":[53],"from":[54],"well-known":[56],"frame":[57],"independent":[58],"assumption.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63],"propose":[64],"use":[66],"SCRFs":[67],"with":[68,100,115],"DNNs":[69],"directly":[70],"acoustic":[73,112],"model,":[74],"one-pass":[76],"unified":[77],"framework":[78],"that":[79],"can":[80],"utilize":[81,109],"local":[82],"phone":[83,85],"classifiers,":[84],"transitions":[86],"long-span":[88],"features,":[89],"direct":[91],"word":[92,121],"decoding":[93],"model":[95,113,118],"or":[97],"sub-phonetic":[98],"segments":[99],"variable":[101],"length.":[102],"We":[103],"describe":[104],"WFST-based":[106],"approach":[107],"proposed":[111],"efficiently":[114],"language":[117],"first-pass":[120],"recognition.":[122],"Our":[123],"evaluation":[124],"on":[125],"WSJ":[127],"corpus":[128],"shows":[129],"our":[130],"SCRF-DNN":[131],"system":[132,137,142],"outperforms":[133],"HMM-DNN":[136],"frame-level":[140],"CRF-DNN":[141],"using":[143],"same":[145],"label":[146],"space.":[147]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}