{"id":"https://openalex.org/W2901215769","doi":"https://doi.org/10.1186/s13636-018-0141-9","title":"Towards end-to-end speech recognition with transfer learning","display_name":"Towards end-to-end speech recognition with transfer learning","publication_year":2018,"publication_date":"2018-11-21","ids":{"openalex":"https://openalex.org/W2901215769","doi":"https://doi.org/10.1186/s13636-018-0141-9","mag":"2901215769"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-018-0141-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-018-0141-9","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-018-0141-9","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-018-0141-9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071178836","display_name":"Chu-Xiong Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chu-Xiong Qin","raw_affiliation_strings":["National Digital Switching System Engineering and Technological R&D Center, Zhengzhou, China","The State Key Laboratory of Integrated Services Networks, Xidian University, Xi\u2019an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Digital Switching System Engineering and Technological R&D Center, Zhengzhou, China","institution_ids":[]},{"raw_affiliation_string":"The State Key Laboratory of Integrated Services Networks, Xidian University, Xi\u2019an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101406895","display_name":"Dan Qu","orcid":"https://orcid.org/0000-0003-1688-4819"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dan Qu","raw_affiliation_strings":["National Digital Switching System Engineering and Technological R&D Center, Zhengzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Digital Switching System Engineering and Technological R&D Center, Zhengzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042409433","display_name":"Lianhai Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lian-Hai Zhang","raw_affiliation_strings":["National Digital Switching System Engineering and Technological R&D Center, Zhengzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Digital Switching System Engineering and Technological R&D Center, Zhengzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101406895"],"corresponding_institution_ids":[],"apc_list":{"value":1635,"currency":"USD","value_usd":1635},"apc_paid":{"value":1635,"currency":"USD","value_usd":1635},"fwci":3.3198,"has_fulltext":true,"cited_by_count":37,"citation_normalized_percentile":{"value":0.93643361,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"2018","issue":"1","first_page":null,"last_page":null},"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":0.9991000294685364,"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":0.9987000226974487,"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":0.810636043548584},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7558318376541138},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7329680919647217},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.7259950041770935},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6633976697921753},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6585369110107422},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.610135018825531},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5722788572311401},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45890799164772034},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4274168014526367},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4183601438999176},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.410851389169693},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3844977021217346},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.29001790285110474},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06607094407081604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.810636043548584},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7558318376541138},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7329680919647217},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.7259950041770935},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6633976697921753},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6585369110107422},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.610135018825531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5722788572311401},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45890799164772034},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4274168014526367},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4183601438999176},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.410851389169693},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3844977021217346},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.29001790285110474},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06607094407081604},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-018-0141-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-018-0141-9","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-018-0141-9","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:e6baaf3be1c748b7bdae31295baf694d","is_oa":true,"landing_page_url":"https://doaj.org/article/e6baaf3be1c748b7bdae31295baf694d","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":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2018, Iss 1, Pp 1-9 (2018)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-018-0141-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-018-0141-9","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-018-0141-9","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6000000238418579,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1506193899","display_name":null,"funder_award_id":"No. 61403415","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1589163256","display_name":null,"funder_award_id":"No. 61673395","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3644773272","display_name":null,"funder_award_id":"61403415","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4798291173","display_name":null,"funder_award_id":"162300410331","funder_id":"https://openalex.org/F4320323845","funder_display_name":"Natural Science Foundation of Henan Province"},{"id":"https://openalex.org/G5278036591","display_name":null,"funder_award_id":"61673395","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7148560424","display_name":null,"funder_award_id":"No. 162300410331","funder_id":"https://openalex.org/F4320323845","funder_display_name":"Natural Science Foundation of Henan Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323845","display_name":"Natural Science Foundation of Henan Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2901215769.pdf","grobid_xml":"https://content.openalex.org/works/W2901215769.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W398859631","https://openalex.org/W1494198834","https://openalex.org/W1586532344","https://openalex.org/W1815076433","https://openalex.org/W1922655562","https://openalex.org/W2025198378","https://openalex.org/W2071712938","https://openalex.org/W2090755665","https://openalex.org/W2102113734","https://openalex.org/W2125496931","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2168103112","https://openalex.org/W2170798597","https://openalex.org/W2193413348","https://openalex.org/W2294543795","https://openalex.org/W2327501763","https://openalex.org/W2513915424","https://openalex.org/W2526425061","https://openalex.org/W2530876040","https://openalex.org/W2551437525","https://openalex.org/W2558906580","https://openalex.org/W2559302184","https://openalex.org/W2593910181","https://openalex.org/W2593984700","https://openalex.org/W2595840341","https://openalex.org/W2606429533","https://openalex.org/W2627092829","https://openalex.org/W2739883972","https://openalex.org/W2759451230","https://openalex.org/W2949382160","https://openalex.org/W2949640717","https://openalex.org/W2953022181","https://openalex.org/W2962824709","https://openalex.org/W2962901777","https://openalex.org/W2963403664","https://openalex.org/W2964121744","https://openalex.org/W6623517193"],"related_works":["https://openalex.org/W80423236","https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1732468982","https://openalex.org/W1761388607","https://openalex.org/W4298148390","https://openalex.org/W80018097","https://openalex.org/W2964207879","https://openalex.org/W2100729928","https://openalex.org/W3181208372"],"abstract_inverted_index":{"A":[0],"transfer":[1,77],"learning-based":[2],"end-to-end":[3,86],"speech":[4,95],"recognition":[5,96],"approach":[6,19,79],"is":[7,31,45],"presented":[8],"in":[9,12],"two":[10],"levels":[11],"our":[13],"framework.":[14],"Firstly,":[15],"a":[16,53,105],"feature":[17],"extraction":[18],"combining":[20],"multilingual":[21],"deep":[22],"neural":[23,61],"network":[24],"(DNN)":[25],"training":[26],"with":[27,104],"matrix":[28],"factorization":[29],"algorithm":[30],"introduced":[32],"to":[33,47,92],"extract":[34],"high-level":[35],"features.":[36,69],"Secondly,":[37],"the":[38,48,67,75,81,93],"advantage":[39],"of":[40,58,66],"connectionist":[41],"temporal":[42],"classification":[43],"(CTC)":[44],"transferred":[46],"target":[49],"attention-based":[50],"model":[51,56],"through":[52],"joint":[54],"CTC-attention":[55],"composed":[57],"shallow":[59],"recurrent":[60],"networks":[62],"(RNNs)":[63],"on":[64],"top":[65],"proposed":[68,76],"The":[70],"experimental":[71],"results":[72],"show":[73],"that":[74],"learning":[78],"achieved":[80],"best":[82],"performance":[83],"among":[84],"all":[85],"methods":[87],"and":[88],"could":[89],"be":[90],"comparable":[91],"state-of-the-art":[94],"system":[97],"for":[98],"TIMIT":[99],"when":[100],"further":[101],"jointly":[102],"decoded":[103],"RNN":[106],"language":[107],"model.":[108]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}
