{"id":"https://openalex.org/W2290197534","doi":"https://doi.org/10.1109/asru.2015.7404848","title":"Acoustic modeling with neural graph embeddings","display_name":"Acoustic modeling with neural graph embeddings","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2290197534","doi":"https://doi.org/10.1109/asru.2015.7404848","mag":"2290197534"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2015.7404848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","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/A5000919546","display_name":"Yuzong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuzong Liu","raw_affiliation_strings":["Department of Electrical Engineering, University of Washington, Seattle, WA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Washington, Seattle, WA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050325468","display_name":"Katrin Kirchhoff","orcid":"https://orcid.org/0000-0002-6645-6030"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katrin Kirchhoff","raw_affiliation_strings":["Department of Electrical Engineering, University of Washington, Seattle, WA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Washington, Seattle, WA","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000919546"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":3.0201,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.92870458,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"10","issue":null,"first_page":"581","last_page":"588"},"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":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9977999925613403,"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/computer-science","display_name":"Computer science","score":0.7660393714904785},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5583634376525879},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5550193190574646},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5333951115608215},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5195612907409668},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5113365054130554},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5001814365386963},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48693621158599854},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.48168644309043884},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.467556357383728},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.46279028058052063},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.414470374584198},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4014604687690735},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.25307440757751465},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.14470282196998596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7660393714904785},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5583634376525879},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5550193190574646},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5333951115608215},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5195612907409668},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5113365054130554},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5001814365386963},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48693621158599854},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.48168644309043884},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.467556357383728},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.46279028058052063},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.414470374584198},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4014604687690735},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25307440757751465},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.14470282196998596},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/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/asru.2015.7404848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1606347560","https://openalex.org/W1984985727","https://openalex.org/W1996941442","https://openalex.org/W1998637406","https://openalex.org/W2012419652","https://openalex.org/W2026369565","https://openalex.org/W2047823992","https://openalex.org/W2053625667","https://openalex.org/W2071085454","https://openalex.org/W2110026675","https://openalex.org/W2110798204","https://openalex.org/W2112739286","https://openalex.org/W2120173366","https://openalex.org/W2130502756","https://openalex.org/W2132085065","https://openalex.org/W2134767644","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2156287497","https://openalex.org/W2160815625","https://openalex.org/W2293634267","https://openalex.org/W2394932179","https://openalex.org/W2405083174","https://openalex.org/W2405455920","https://openalex.org/W2405933695","https://openalex.org/W2916986993","https://openalex.org/W2963490782","https://openalex.org/W6631362777","https://openalex.org/W6636358008","https://openalex.org/W6676481782","https://openalex.org/W6679387265","https://openalex.org/W6679446029","https://openalex.org/W6680158167","https://openalex.org/W6696934422","https://openalex.org/W6713625614","https://openalex.org/W6713929101"],"related_works":["https://openalex.org/W151018310","https://openalex.org/W3081187864","https://openalex.org/W4380605396","https://openalex.org/W2803306015","https://openalex.org/W3133352777","https://openalex.org/W2008737763","https://openalex.org/W2784059283","https://openalex.org/W4319779560","https://openalex.org/W4385611764","https://openalex.org/W2519224033"],"abstract_inverted_index":{"Graph-based":[0],"learning":[1,8],"(GBL)":[2],"is":[3,28,42,55,67,91],"a":[4,31,84,98,114,141],"form":[5],"of":[6,48,74],"semi-supervised":[7],"that":[9,27],"has":[10],"been":[11],"successfully":[12],"exploited":[13],"in":[14,17,24,136],"acoustic":[15,50],"modeling":[16],"the":[18,45,64,75,88,110,127],"past.":[19],"It":[20],"utilizes":[21],"manifold":[22],"information":[23],"speech":[25,76,117],"data":[26,61],"represented":[29],"as":[30,131,133],"joint":[32],"similarity":[33,89],"graph":[34,90],"over":[35],"training":[36],"and":[37,63,123],"test":[38],"samples.":[39],"Typically,":[40],"GBL":[41,129],"used":[43,108],"at":[44,109],"output":[46],"level":[47,112],"an":[49],"classifier;":[51],"however,":[52],"this":[53,80,104],"setup":[54],"difficult":[56],"to":[57,59,113,126],"scale":[58],"large":[60],"sets,":[62],"graph-based":[65],"learner":[66],"not":[68],"optimized":[69],"jointly":[70],"with":[71],"other":[72],"components":[73],"recognition":[77],"system.":[78],"In":[79],"paper":[81],"we":[82],"explore":[83],"different":[85],"approach":[86,130],"where":[87],"first":[92],"embedded":[93],"into":[94],"continuous":[95],"space":[96],"using":[97],"neural":[99],"autoencoder.":[100],"Features":[101],"derived":[102],"from":[103],"encoding":[105],"are":[106],"then":[107],"input":[111],"standard":[115,128],"DNN-based":[116],"recognizer.":[118],"We":[119],"demonstrate":[120],"improved":[121],"scalability":[122],"performance":[124],"compared":[125],"well":[132],"significant":[134],"improvements":[135],"word":[137],"error":[138],"rate":[139],"on":[140],"medium-vocabulary":[142],"Switchboard":[143],"task.":[144]},"counts_by_year":[{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}