{"id":"https://openalex.org/W3134157045","doi":"https://doi.org/10.1109/iscslp49672.2021.9362086","title":"Leveraging Text Data Using Hybrid Transformer-LSTM Based End-to-End ASR in Transfer Learning","display_name":"Leveraging Text Data Using Hybrid Transformer-LSTM Based End-to-End ASR in Transfer Learning","publication_year":2021,"publication_date":"2021-01-24","ids":{"openalex":"https://openalex.org/W3134157045","doi":"https://doi.org/10.1109/iscslp49672.2021.9362086","mag":"3134157045"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp49672.2021.9362086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://nur.nu.edu.kz/handle/123456789/17680","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034445480","display_name":"Zhiping Zeng","orcid":"https://orcid.org/0000-0002-6315-4408"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhiping Zeng","raw_affiliation_strings":["Huya AI, Guangzhou, China","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huya AI, Guangzhou, China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046222772","display_name":"Van Tung Pham","orcid":"https://orcid.org/0000-0002-2103-1901"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Van Tung Pham","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039696635","display_name":"Haihua Xu","orcid":"https://orcid.org/0000-0002-2220-8465"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haihua Xu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047310084","display_name":"Yerbolat Khassanov","orcid":"https://orcid.org/0000-0001-9422-6833"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I60559429","display_name":"Nazarbayev University","ror":"https://ror.org/052bx8q98","country_code":"KZ","type":"education","lineage":["https://openalex.org/I60559429"]}],"countries":["KZ","SG"],"is_corresponding":false,"raw_author_name":"Yerbolat Khassanov","raw_affiliation_strings":["ISSAI, Nazarbayev University, Kazakhstan","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ISSAI, Nazarbayev University, Kazakhstan","institution_ids":["https://openalex.org/I60559429"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102306089","display_name":"Chongjia Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chongjia Ni","raw_affiliation_strings":["Alibaba Group, Machine Intelligence Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Machine Intelligence Technology","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Alibaba Group, Machine Intelligence Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Machine Intelligence Technology","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0247,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78524738,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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":0.8057867288589478},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7504745721817017},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6101075410842896},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6029228568077087},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5785958170890808},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5206353068351746},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4942774772644043},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4857173562049866},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44860273599624634},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3736633062362671},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3438035249710083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8057867288589478},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7504745721817017},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6101075410842896},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6029228568077087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5785958170890808},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5206353068351746},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4942774772644043},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4857173562049866},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44860273599624634},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3736633062362671},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3438035249710083},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iscslp49672.2021.9362086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:nur.nu.edu.kz:123456789/15414","is_oa":false,"landing_page_url":"https://nur.nu.edu.kz/handle/123456789/15414","pdf_url":null,"source":{"id":"https://openalex.org/S4377196417","display_name":"Nazarbayev University Repository (Nazarbayev University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60559429","host_organization_name":"Nazarbayev University","host_organization_lineage":["https://openalex.org/I60559429"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing Iscslp 2021, Hong Kong, January 2021","raw_type":"Conference Proceedings"},{"id":"pmh:oai:nur.nu.edu.kz:123456789/17680","is_oa":true,"landing_page_url":"https://nur.nu.edu.kz/handle/123456789/17680","pdf_url":null,"source":{"id":"https://openalex.org/S4377196417","display_name":"Nazarbayev University Repository (Nazarbayev University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60559429","host_organization_name":"Nazarbayev University","host_organization_lineage":["https://openalex.org/I60559429"],"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":null,"raw_type":"/dk/atira/pure/researchoutput/researchoutputtypes/contributiontobookanthology/conference"}],"best_oa_location":{"id":"pmh:oai:nur.nu.edu.kz:123456789/17680","is_oa":true,"landing_page_url":"https://nur.nu.edu.kz/handle/123456789/17680","pdf_url":null,"source":{"id":"https://openalex.org/S4377196417","display_name":"Nazarbayev University Repository (Nazarbayev University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60559429","host_organization_name":"Nazarbayev University","host_organization_lineage":["https://openalex.org/I60559429"],"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":null,"raw_type":"/dk/atira/pure/researchoutput/researchoutputtypes/contributiontobookanthology/conference"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1915251500","https://openalex.org/W1978660892","https://openalex.org/W2025198378","https://openalex.org/W2102113734","https://openalex.org/W2194775991","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2526425061","https://openalex.org/W2769437540","https://openalex.org/W2886180730","https://openalex.org/W2888539709","https://openalex.org/W2892009249","https://openalex.org/W2939757332","https://openalex.org/W2962780374","https://openalex.org/W2963292011","https://openalex.org/W2964045208","https://openalex.org/W2964213727","https://openalex.org/W2972818416","https://openalex.org/W2973072704","https://openalex.org/W3007328579","https://openalex.org/W4385245566","https://openalex.org/W6675365184","https://openalex.org/W6713762819","https://openalex.org/W6728030952","https://openalex.org/W6739901393","https://openalex.org/W6746041127","https://openalex.org/W6754299077","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W4206178588","https://openalex.org/W4287635093","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W2119113516","https://openalex.org/W3037446006","https://openalex.org/W4287752972","https://openalex.org/W3037482713"],"abstract_inverted_index":{"In":[0],"this":[1,21],"work,":[2],"we":[3,23,117,132],"study":[4],"leveraging":[5],"extra":[6,56,85,150],"text":[7,57,151],"data":[8,58,79],"to":[9,60,178],"improve":[10],"low-":[11],"resource":[12],"end-to-end":[13],"ASR":[14,161],"under":[15],"cross-lingual":[16],"transfer":[17,125],"learning":[18,126],"setting.":[19],"To":[20],"end,":[22],"extend":[24],"the":[25,43,49,61,90,94,141,145,149,158,169],"prior":[26],"work":[27],"[1],":[28],"and":[29,80,181],"propose":[30],"a":[31,81],"hybrid":[32,171],"Transformer-LSTM":[33],"based":[34],"architecture.":[35],"This":[36],"architecture":[37,92,97,172],"not":[38,167],"only":[39],"takes":[40],"advantage":[41],"of":[42,48,84,144],"highly":[44],"effective":[45],"encoding":[46],"capacity":[47],"Transformer":[50,160,182],"network":[51],"but":[52,166],"also":[53],"benefits":[54],"from":[55,115,127],"due":[59],"LSTM-based":[62,96],"independent":[63],"language":[64],"model":[65,147,156],"network.":[66],"We":[67],"conduct":[68],"experiments":[69],"on":[70],"our":[71,154],"in-house":[72],"Malay":[73],"corpus":[74],"which":[75],"contains":[76],"limited":[77,111],"labeled":[78,112],"large":[82],"amount":[83],"text.":[86],"Results":[87],"show":[88],"that":[89],"proposed":[91,170],"outperforms":[93,157],"previous":[95],"[1]":[98],"by":[99,124,139],"24.2%":[100],"relative":[101,121,136,163],"word":[102],"error":[103],"rate":[104],"(WER)":[105],"when":[106],"both":[107,179],"are":[108],"trained":[109],"using":[110],"data.":[113,152],"Starting":[114],"this,":[116],"obtain":[118,133],"further":[119],"25.4%":[120],"WER":[122,137],"reduction":[123,138],"another":[128],"resource-rich":[129],"language.":[130],"Moreover,":[131],"additional":[134],"13.6%":[135],"boosting":[140],"LSTM":[142,180],"decoder":[143],"transferred":[146],"with":[148],"Overall,":[153],"best":[155],"vanilla":[159],"by11.9%":[162],"WER.":[164],"Last":[165],"least,":[168],"offers":[173],"much":[174],"faster":[175],"inference":[176],"compared":[177],"architectures.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":5}],"updated_date":"2026-08-09T07:27:16.801131","created_date":"2025-10-10T00:00:00"}