{"id":"https://openalex.org/W7148356296","doi":"https://doi.org/10.1109/asru65441.2025.11434788","title":"Benchmarking Rotary Position Embeddings for Automatic Speech Recognition","display_name":"Benchmarking Rotary Position Embeddings for Automatic Speech Recognition","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148356296","doi":"https://doi.org/10.1109/asru65441.2025.11434788"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434788","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434788","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (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/A5003030422","display_name":"Shucong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Shucong Zhang","raw_affiliation_strings":["AI Center, Samsung,Cambridge,UK"],"affiliations":[{"raw_affiliation_string":"AI Center, Samsung,Cambridge,UK","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089505434","display_name":"Titouan Parcollet","orcid":"https://orcid.org/0000-0003-0672-1346"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Titouan Parcollet","raw_affiliation_strings":["AI Center, Samsung,Cambridge,UK"],"affiliations":[{"raw_affiliation_string":"AI Center, Samsung,Cambridge,UK","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132807857","display_name":"Rogier Van Dalen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rogier Van Dalen","raw_affiliation_strings":["AI Center, Samsung,Cambridge,UK"],"affiliations":[{"raw_affiliation_string":"AI Center, Samsung,Cambridge,UK","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087701164","display_name":"Sourav Bhattacharya","orcid":"https://orcid.org/0000-0001-9670-5264"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sourav Bhattacharya","raw_affiliation_strings":["AI Center, Samsung,Cambridge,UK"],"affiliations":[{"raw_affiliation_string":"AI Center, Samsung,Cambridge,UK","institution_ids":["https://openalex.org/I4210117523"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003030422"],"corresponding_institution_ids":["https://openalex.org/I4210117523"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87556307,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8479999899864197,"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":0.8479999899864197,"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":0.06700000166893005,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.04450000077486038,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6241999864578247},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6000999808311462},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5485000014305115},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5471000075340271},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42340001463890076},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.4108999967575073},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.39309999346733093},{"id":"https://openalex.org/keywords/ranging","display_name":"Ranging","score":0.39070001244544983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7508000135421753},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6621000170707703},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6241999864578247},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6000999808311462},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5485000014305115},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5471000075340271},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42340001463890076},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.39070001244544983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38769999146461487},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2506999969482422},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.25040000677108765},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434788","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434788","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2526425061","https://openalex.org/W2962780374","https://openalex.org/W2964110616","https://openalex.org/W3097777922","https://openalex.org/W3119308075","https://openalex.org/W3142589538","https://openalex.org/W3197478142","https://openalex.org/W4225293011","https://openalex.org/W4297727296","https://openalex.org/W4385245566","https://openalex.org/W4388979610","https://openalex.org/W4392903704","https://openalex.org/W4401042382","https://openalex.org/W4402112522","https://openalex.org/W4415433581","https://openalex.org/W7133227460"],"related_works":[],"abstract_inverted_index":{"Self-attention":[0],"relies":[1],"on":[2,51],"positional":[3],"embeddings":[4,12],"to":[5,27,58,98,134],"encode":[6],"input":[7,28,48],"order.":[8],"Relative":[9],"Position":[10],"(RelPos)":[11],"are":[13,121],"widely":[14],"used":[15],"in":[16,80,112],"Automatic":[17],"Speech":[18],"Recognition":[19],"(ASR).":[20],"However,":[21,77],"RelPos":[22],"has":[23],"quadratic":[24],"time":[25,57,129],"complexity":[26],"length":[29],"and":[30,109,115],"is":[31,71,130,138],"often":[32],"incompatible":[33],"with":[34,74,92],"fast":[35],"GPU":[36],"implementations":[37],"of":[38],"attention.":[39,76],"In":[40],"contrast,":[41],"Rotary":[42],"Positional":[43],"Embedding":[44],"(RoPE)":[45],"rotates":[46],"each":[47],"vector":[49],"based":[50],"its":[52,78],"absolute":[53],"position,":[54],"taking":[55],"linear":[56],"sequence":[59],"length,":[60],"implicitly":[61],"encoding":[62],"relative":[63],"distances":[64],"through":[65],"self-attention":[66],"dot":[67],"products.":[68],"Thus,":[69],"it":[70],"usually":[72],"compatible":[73],"efficient":[75],"use":[79],"ASR":[81,90,118],"remains":[82],"underexplored.":[83],"This":[84],"work":[85],"evaluates":[86],"RoPE":[87],"across":[88],"diverse":[89],"tasks":[91],"training":[93,128],"data":[94],"ranging":[95],"from":[96],"100":[97],"50,000":[99],"hours,":[100],"covering":[101],"various":[102],"speech":[103],"types":[104],"(read,":[105],"spontaneous,":[106],"clean,":[107],"noisy)":[108],"different":[110],"accents":[111],"both":[113],"streaming":[114],"non-streaming":[116],"settings.":[117],"error":[119],"rates":[120],"similar":[122],"or":[123],"better":[124],"than":[125],"RelPos,":[126],"while":[127],"reduced":[131],"by":[132],"up":[133],"$21":[135],"\\%$.":[136],"Code":[137],"available":[139],"via":[140],"the":[141],"SpeechBrain":[142],"toolkit.":[143]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}