{"id":"https://openalex.org/W3135294600","doi":"https://doi.org/10.1109/iscslp49672.2021.9362093","title":"An Investigation of Positional Encoding in Transformer-based End-to-end Speech Recognition","display_name":"An Investigation of Positional Encoding in Transformer-based End-to-end Speech Recognition","publication_year":2021,"publication_date":"2021-01-24","ids":{"openalex":"https://openalex.org/W3135294600","doi":"https://doi.org/10.1109/iscslp49672.2021.9362093","mag":"3135294600"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp49672.2021.9362093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362093","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069891577","display_name":"Fengpeng Yue","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengpeng Yue","raw_affiliation_strings":["Southern University of Science and Technology,Department of Computer Science and Engineering,Shenzhen,China","Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,Department of Computer Science and Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038062913","display_name":"Tom Ko","orcid":"https://orcid.org/0000-0002-5324-8961"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tom Ko","raw_affiliation_strings":["Southern University of Science and Technology,Department of Computer Science and Engineering,Shenzhen,China","Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,Department of Computer Science and Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3045169105"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/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/T10181","display_name":"Natural Language Processing Techniques","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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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":0.7590311765670776},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7220330834388733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5606572031974792},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5370079278945923},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5029286742210388},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4508476257324219},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4487234950065613},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4302799105644226},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4238133728504181},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37623587250709534},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07622495293617249}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7590311765670776},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7220330834388733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5606572031974792},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5370079278945923},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5029286742210388},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4508476257324219},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4487234950065613},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4302799105644226},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4238133728504181},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37623587250709534},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07622495293617249},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp49672.2021.9362093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362093","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1828163288","https://openalex.org/W1855892484","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2407080277","https://openalex.org/W2613904329","https://openalex.org/W2696967604","https://openalex.org/W2941814890","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2963403868","https://openalex.org/W2963925437","https://openalex.org/W2964089206","https://openalex.org/W2964121744","https://openalex.org/W2964265128","https://openalex.org/W2972818416","https://openalex.org/W3007328579","https://openalex.org/W3007625080","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6638575559","https://openalex.org/W6638749077","https://openalex.org/W6639156005","https://openalex.org/W6675365184","https://openalex.org/W6713762819","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6761563299","https://openalex.org/W6774500937"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W2151749779","https://openalex.org/W3008587939","https://openalex.org/W3196421258","https://openalex.org/W4387301579","https://openalex.org/W2763956190","https://openalex.org/W4400488565","https://openalex.org/W4235381733"],"abstract_inverted_index":{"In":[0,24,59,70],"the":[1,4,10,14,28,38,53,62,75,81,90,93,97,103,119],"Transformer":[2],"architecture,":[3],"model":[5],"does":[6],"not":[7],"intrinsically":[8],"learn":[9],"ordering":[11,31],"information":[12,32],"of":[13,30,40,49,77,83,88],"input":[15],"frames":[16],"and":[17,56],"tokens":[18],"due":[19],"to":[20,92,107],"its":[21,108],"self-attention":[22,98],"mechanism.":[23],"sequence-to-sequence":[25],"learning":[26],"tasks,":[27],"missing":[29],"is":[33,65],"explicitly":[34],"filled":[35],"up":[36],"by":[37,67],"use":[39,76],"positional":[41,51,63,68,78,85,120],"representation.":[42],"Currently,":[43],"there":[44],"are":[45],"two":[46],"major":[47],"ways":[48],"using":[50],"representation:":[52],"absolute":[54],"way":[55],"relative":[57,84],"way.":[58],"both":[60],"ways,":[61],"in-formation":[64],"represented":[66],"vector.":[69,86],"this":[71],"paper,":[72],"we":[73],"propose":[74],"matrix":[79],"in":[80,96],"context":[82],"Instead":[87],"adding":[89],"vectors":[91,95,105],"key":[94,104],"layer,":[99],"our":[100,116],"method":[101],"transforms":[102],"according":[106],"position.":[109],"Experiments":[110],"on":[111],"LibriSpeech":[112],"dataset":[113],"show":[114],"that":[115],"approach":[117],"outperforms":[118],"vector":[121],"approach.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}