{"id":"https://openalex.org/W3134920593","doi":"https://doi.org/10.1109/access.2021.3064197","title":"Towards Constructing HMM Structure for Speech Recognition With Deep Neural Fenonic Baseform Growing","display_name":"Towards Constructing HMM Structure for Speech Recognition With Deep Neural Fenonic Baseform Growing","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3134920593","doi":"https://doi.org/10.1109/access.2021.3064197","mag":"3134920593"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3064197","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3064197","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2021.3064197","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101983249","display_name":"Lujun Li","orcid":"https://orcid.org/0000-0002-0641-3178"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Lujun Li","raw_affiliation_strings":["Chair of Human-Machine Communication, Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-0641-3178","affiliations":[{"raw_affiliation_string":"Chair of Human-Machine Communication, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035094320","display_name":"Tobias Watzel","orcid":"https://orcid.org/0000-0002-3552-3325"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Watzel","raw_affiliation_strings":["Chair of Human-Machine Communication, Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3552-3325","affiliations":[{"raw_affiliation_string":"Chair of Human-Machine Communication, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079663771","display_name":"Ludwig K\u00fcrzinger","orcid":"https://orcid.org/0000-0001-5312-3870"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ludwig Kurzinger","raw_affiliation_strings":["Chair of Human-Machine Communication, Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Human-Machine Communication, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039092855","display_name":"Gerhard Rigoll","orcid":"https://orcid.org/0000-0003-1096-1596"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Rigoll","raw_affiliation_strings":["Chair of Human-Machine Communication, Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1096-1596","affiliations":[{"raw_affiliation_string":"Chair of Human-Machine Communication, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101983249"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1751,"currency":"EUR","value_usd":1888},"fwci":0.1399,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.52367505,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"9","issue":null,"first_page":"39098","last_page":"39110"},"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":0.9991999864578247,"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":0.9988999962806702,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.9435415267944336},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.853960394859314},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8134248852729797},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6535995006561279},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5983330607414246},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5195370316505432},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.49259501695632935},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48048701882362366}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9435415267944336},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.853960394859314},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8134248852729797},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6535995006561279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5983330607414246},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5195370316505432},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.49259501695632935},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48048701882362366},{"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":3,"locations":[{"id":"doi:10.1109/access.2021.3064197","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3064197","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:0cf60d7c0001499fb9d762877da5be96","is_oa":true,"landing_page_url":"https://doaj.org/article/0cf60d7c0001499fb9d762877da5be96","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 39098-39110 (2021)","raw_type":"article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1662832","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1662832","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3064197","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3064197","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W87145177","https://openalex.org/W854541894","https://openalex.org/W1447019041","https://openalex.org/W1494198834","https://openalex.org/W1502648924","https://openalex.org/W1522301498","https://openalex.org/W1523854128","https://openalex.org/W1524333225","https://openalex.org/W1611176049","https://openalex.org/W1836465849","https://openalex.org/W1989226853","https://openalex.org/W2007321142","https://openalex.org/W2035789797","https://openalex.org/W2093364307","https://openalex.org/W2095705004","https://openalex.org/W2098808520","https://openalex.org/W2102113734","https://openalex.org/W2102770307","https://openalex.org/W2112739286","https://openalex.org/W2115092814","https://openalex.org/W2122496126","https://openalex.org/W2127141656","https://openalex.org/W2131342762","https://openalex.org/W2134523851","https://openalex.org/W2136722020","https://openalex.org/W2137919556","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2187089797","https://openalex.org/W2251321385","https://openalex.org/W2327501763","https://openalex.org/W2402146185","https://openalex.org/W2407080277","https://openalex.org/W2759451230","https://openalex.org/W2789246472","https://openalex.org/W2884171506","https://openalex.org/W2888867175","https://openalex.org/W2903799412","https://openalex.org/W2916986993","https://openalex.org/W2936774411","https://openalex.org/W2949117887","https://openalex.org/W2963217176","https://openalex.org/W2963403868","https://openalex.org/W2964121744","https://openalex.org/W2967068017","https://openalex.org/W2972320711","https://openalex.org/W2972937794","https://openalex.org/W2981857663","https://openalex.org/W3008525923","https://openalex.org/W3015726069","https://openalex.org/W3103005696","https://openalex.org/W3127686677","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6628424771","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6631496692","https://openalex.org/W6638667902","https://openalex.org/W6639288305","https://openalex.org/W6674330103","https://openalex.org/W6675365184","https://openalex.org/W6691770337","https://openalex.org/W6712930963","https://openalex.org/W6713762819","https://openalex.org/W6739901393","https://openalex.org/W6757084628","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W3134920593","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W2153098279","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2071828724","https://openalex.org/W1909151225","https://openalex.org/W1987783679"],"abstract_inverted_index":{"For":[0,62],"decades,":[1],"acoustic":[2],"models":[3],"in":[4],"speech":[5,145],"recognition":[6,146],"systems":[7,147],"pivot":[8],"on":[9,46,74,117],"Hidden":[10],"Markov":[11],"Models":[12],"(HMMs),":[13],"e.g.,":[14],"Gaussian":[15],"Mixture":[16],"Model-HMM":[17],"system,":[18,22],"Deep":[19,75],"Neural":[20,76],"Network-HMM":[21],"etc.,":[23],"and":[24,89,120,134],"achieve":[25],"remarkable":[26],"results.":[27],"However,":[28],"the":[29,34,39,47,63,82,97,108,125,131,135],"popular":[30],"HMM":[31,48,83,98,127],"model":[32],"is":[33,86],"three-state":[35],"left-to-right":[36],"structure,":[37,84],"without":[38,104],"superiority":[40],"certainty.":[41],"There":[42],"are":[43],"multiple":[44],"studies":[45],"structure\u2019s":[49],"optimization,":[50],"but":[51],"none":[52],"of":[53,110],"them":[54],"addresses":[55],"this":[56,66,93],"problem":[57],"leveraging":[58],"deep":[59],"learning":[60],"algorithms.":[61],"first":[64],"time,":[65],"paper":[67],"proposes":[68],"a":[69],"new":[70],"training":[71],"method":[72,95],"based":[73],"Fenonic":[77],"Baseform":[78],"Growing":[79],"to":[80],"optimize":[81],"which":[85],"concisely":[87],"designed":[88],"computationally":[90],"cheap.":[91],"Moreover,":[92],"data-driven":[94],"customizes":[96],"structure":[99,128],"for":[100],"each":[101],"phone":[102],"precisely":[103],"external":[105],"assumptions":[106],"concerning":[107],"number":[109],"states":[111],"or":[112],"transition":[113],"patterns.":[114],"Experimental":[115],"results":[116],"both":[118,130],"TIMIT":[119],"TEDliumv2":[121],"corpora":[122],"indicate":[123],"that":[124],"proposed":[126],"improves":[129,143],"monophone":[132],"system":[133,137],"triphone":[136],"substantially.":[138],"Besides,":[139],"its":[140],"adoption":[141],"further":[142],"state-of-the-art":[144],"with":[148],"remarkably":[149],"reduced":[150],"parameters.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}