{"id":"https://openalex.org/W4392904390","doi":"https://doi.org/10.1109/icassp48485.2024.10446337","title":"An Empirical Study on the Impact of Positional Encoding in Transformer-Based Monaural Speech Enhancement","display_name":"An Empirical Study on the Impact of Positional Encoding in Transformer-Based Monaural Speech Enhancement","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904390","doi":"https://doi.org/10.1109/icassp48485.2024.10446337"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5042675934","display_name":"Qiquan Zhang","orcid":"https://orcid.org/0000-0001-5089-6317"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Qiquan Zhang","raw_affiliation_strings":["University of New South,School of Electrical Engineering and Telecommunications,Wales,Australia","School of Electrical Engineering and Telecommunications, University of New South, Wales, Australia"],"affiliations":[{"raw_affiliation_string":"University of New South,School of Electrical Engineering and Telecommunications,Wales,Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"School of Electrical Engineering and Telecommunications, University of New South, Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675868","display_name":"Ge Meng","orcid":"https://orcid.org/0000-0002-7205-5532"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Meng Ge","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore","Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057187503","display_name":"Hongxu Zhu","orcid":"https://orcid.org/0000-0001-6257-7065"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hongxu Zhu","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore","Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028116210","display_name":"Eliathamby Ambikairajah","orcid":"https://orcid.org/0000-0003-4673-6534"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Eliathamby Ambikairajah","raw_affiliation_strings":["University of New South,School of Electrical Engineering and Telecommunications,Wales,Australia","School of Electrical Engineering and Telecommunications, University of New South, Wales, Australia"],"affiliations":[{"raw_affiliation_string":"University of New South,School of Electrical Engineering and Telecommunications,Wales,Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"School of Electrical Engineering and Telecommunications, University of New South, Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085593755","display_name":"Qi Song","orcid":"https://orcid.org/0009-0007-5833-3210"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Song","raw_affiliation_strings":["Alibaba Group,China","Alibaba Group, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031088292","display_name":"Zhaoheng Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210118911","display_name":"META Group","ror":"https://ror.org/027ng0s03","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210118911"]},{"id":"https://openalex.org/I4210140397","display_name":"Metrica (United States)","ror":"https://ror.org/031ffw737","country_code":"US","type":"company","lineage":["https://openalex.org/I4210140397"]}],"countries":["IT","US"],"is_corresponding":false,"raw_author_name":"Zhaoheng Ni","raw_affiliation_strings":["Meta,United States","Meta, United States"],"affiliations":[{"raw_affiliation_string":"Meta,United States","institution_ids":["https://openalex.org/I4210118911","https://openalex.org/I4210140397"]},{"raw_affiliation_string":"Meta, United States","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen,China","Department of Electrical and Computer Engineering, National University of Singapore, Singapore","The Chinese University of Hong Kong, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5042675934"],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":5.821,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.96834205,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1001","last_page":"1005"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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":0.9965999722480774,"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/transformer","display_name":"Transformer","score":0.6831220984458923},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6716461777687073},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5490883588790894},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4713658392429352},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4673609733581543},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.43882185220718384},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.4331085681915283},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4324767291545868},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3341825604438782},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12478438019752502}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6831220984458923},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6716461777687073},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5490883588790894},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4713658392429352},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4673609733581543},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.43882185220718384},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.4331085681915283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4324767291545868},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3341825604438782},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12478438019752502},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331102","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W1506438021","https://openalex.org/W1522301498","https://openalex.org/W1897240248","https://openalex.org/W2038484192","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2121973264","https://openalex.org/W2144404214","https://openalex.org/W2159202424","https://openalex.org/W2219249508","https://openalex.org/W2291877678","https://openalex.org/W2396174604","https://openalex.org/W2516001803","https://openalex.org/W2539238457","https://openalex.org/W2678916739","https://openalex.org/W2792764867","https://openalex.org/W2896457183","https://openalex.org/W2914067823","https://openalex.org/W2950962438","https://openalex.org/W2962866211","https://openalex.org/W2971417062","https://openalex.org/W2991361823","https://openalex.org/W3016129867","https://openalex.org/W3017350693","https://openalex.org/W3026111682","https://openalex.org/W3095820034","https://openalex.org/W3097030750","https://openalex.org/W3132954452","https://openalex.org/W3197822518","https://openalex.org/W3214515055","https://openalex.org/W4221162870","https://openalex.org/W4253928870","https://openalex.org/W4288089799","https://openalex.org/W4296069339","https://openalex.org/W4312271884","https://openalex.org/W4372265870","https://openalex.org/W4385245566","https://openalex.org/W4385822988","https://openalex.org/W6631190155","https://openalex.org/W6688816777","https://openalex.org/W6749825310","https://openalex.org/W6755207826","https://openalex.org/W6769627184","https://openalex.org/W6790758941","https://openalex.org/W6837860888"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2045506488","https://openalex.org/W1983045063","https://openalex.org/W4321794819","https://openalex.org/W2072124114","https://openalex.org/W2944394647","https://openalex.org/W1543248128"],"abstract_inverted_index":{"Transformer":[0,47,77],"architecture":[1],"has":[2],"enabled":[3],"recent":[4],"progress":[5],"in":[6,31,113],"speech":[7,43,91],"enhancement.":[8],"Since":[9],"Transformers":[10,24],"are":[11],"position-agostic,":[12],"positional":[13,39,60,79,104,139],"encoding":[14,40,61,80,105],"is":[15,106],"the":[16,27,76,111,131,136,147],"de":[17],"facto":[18],"standard":[19],"component":[20],"used":[21],"to":[22,25],"enable":[23],"distinguish":[26],"order":[28],"of":[29,138],"elements":[30],"a":[32,54,114,128],"sequence.":[33],"However,":[34],"it":[35],"remains":[36],"unclear":[37],"how":[38],"exactly":[41],"impacts":[42],"enhancement":[44,92],"based":[45],"on":[46],"architectures.":[48],"In":[49,127,141],"this":[50],"paper,":[51],"we":[52,143],"perform":[53],"comprehensive":[55],"empirical":[56],"study":[57],"evaluating":[58],"five":[59],"methods,":[62],"i.e.,":[63],"Sinusoidal":[64],"and":[65,85,97],"learned":[66],"absolute":[67],"position":[68,125,149,152],"embedding":[69],"(APE),":[70],"T5-RPE,":[71],"KERPLE,":[72],"as":[73,75],"well":[74],"without":[78],"(No-Pos),":[81],"across":[82],"both":[83],"causal":[84,115,120],"noncausal":[86,129],"configurations.":[87],"We":[88],"conduct":[89],"extensive":[90],"experiments,":[93],"involving":[94],"spectral":[95],"mapping":[96],"masking":[98],"methods.":[99],"Our":[100],"findings":[101],"establish":[102],"that":[103,119,145],"not":[107],"quite":[108],"helpful":[109],"for":[110],"models":[112,132],"configuration,":[116,130],"which":[117],"indicates":[118],"attention":[121],"may":[122],"implicitly":[123],"incorporate":[124],"information.":[126],"significantly":[133],"benefit":[134],"from":[135],"use":[137],"encoding.":[140],"addition,":[142],"find":[144],"among":[146],"four":[148],"embeddings,":[150],"relative":[151],"embeddings":[153],"outperform":[154],"APEs.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}