{"id":"https://openalex.org/W7148402482","doi":"https://doi.org/10.1109/asru65441.2025.11434675","title":"Analysis of Domain Shift across ASR Architectures via TTS-Enabled Separation of Target Domain and Acoustic Conditions","display_name":"Analysis of Domain Shift across ASR Architectures via TTS-Enabled Separation of Target Domain and Acoustic Conditions","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148402482","doi":"https://doi.org/10.1109/asru65441.2025.11434675"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434675","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434675","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/A5050968038","display_name":"Tina Raissi","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Tina Raissi","raw_affiliation_strings":["RWTH Aachen University,Machine Learning and Human Language Technology Group,Aachen,Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Machine Learning and Human Language Technology Group,Aachen,Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063680910","display_name":"Nick Rossenbach","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nick Rossenbach","raw_affiliation_strings":["RWTH Aachen University AppTek GmbH,Machine Learning and Human Language Technology Group,Aachen,Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University AppTek GmbH,Machine Learning and Human Language Technology Group,Aachen,Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088968292","display_name":"Ralf Schl\u00fcter","orcid":"https://orcid.org/0000-0003-2839-9247"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf Schl\u00fcter","raw_affiliation_strings":["RWTH Aachen University AppTek GmbH,Machine Learning and Human Language Technology Group,Aachen,Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University AppTek GmbH,Machine Learning and Human Language Technology Group,Aachen,Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050968038"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.76213466,"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/T10271","display_name":"Seismic Imaging and Inversion Techniques","score":0.14110000431537628,"subfield":{"id":"https://openalex.org/subfields/1908","display_name":"Geophysics"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10271","display_name":"Seismic Imaging and Inversion Techniques","score":0.14110000431537628,"subfield":{"id":"https://openalex.org/subfields/1908","display_name":"Geophysics"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.1316000074148178,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.08669999986886978,"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/domain","display_name":"Domain (mathematical analysis)","score":0.5496000051498413},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4068000018596649},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.3991999924182892},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.3718999922275543},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.35670000314712524},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3425000011920929}],"concepts":[{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5496000051498413},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5342000126838684},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3833000063896179},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.35670000314712524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3555000126361847},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3425000011920929},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3325999975204468},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.314300000667572},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2987000048160553},{"id":"https://openalex.org/C3018256011","wikidata":"https://www.wikidata.org/wiki/Q898987","display_name":"Separation method","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C51432778","wikidata":"https://www.wikidata.org/wiki/Q1259145","display_name":"Independent component analysis","level":2,"score":0.258899986743927}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434675","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434675","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":[{"id":"https://openalex.org/F4320321408","display_name":"Ministry of Education","ror":"https://ror.org/01p262204"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1972845249","https://openalex.org/W2009150118","https://openalex.org/W2046932483","https://openalex.org/W2127141656","https://openalex.org/W2158069733","https://openalex.org/W2170212447","https://openalex.org/W2962728618","https://openalex.org/W2962784628","https://openalex.org/W2963587345","https://openalex.org/W3008174054","https://openalex.org/W3015995734","https://openalex.org/W3016234571","https://openalex.org/W3025870691","https://openalex.org/W3095376166","https://openalex.org/W3097777922","https://openalex.org/W3160551958","https://openalex.org/W3193461931","https://openalex.org/W3196869722","https://openalex.org/W3197661863","https://openalex.org/W3198439131","https://openalex.org/W3202419788","https://openalex.org/W3205201903","https://openalex.org/W4224518768","https://openalex.org/W4230900352","https://openalex.org/W4315700168","https://openalex.org/W4319862408","https://openalex.org/W4319862418","https://openalex.org/W4319862474","https://openalex.org/W4385807407","https://openalex.org/W4385822992","https://openalex.org/W4388017359","https://openalex.org/W4388983788","https://openalex.org/W4391021730","https://openalex.org/W4392903749","https://openalex.org/W4400900236","https://openalex.org/W4402111971","https://openalex.org/W4403653713","https://openalex.org/W4403653755","https://openalex.org/W4408356075","https://openalex.org/W7131786799"],"related_works":[],"abstract_inverted_index":{"We":[0,58],"analyze":[1],"automatic":[2],"speech":[3],"recognition":[4],"(ASR)":[5],"modeling":[6,29,125],"choices":[7,126],"under":[8,91,103],"domain":[9,41,49,61,68,92,104],"mismatch,":[10],"comparing":[11],"classic":[12,116],"modular":[13,117],"and":[14,36,63,118],"novel":[15,119],"sequence-to-sequence":[16],"(seq2seq)":[17],"architectures.":[18],"Across":[19],"the":[20,72,80,108,113],"different":[21],"ASR":[22,86],"architectures,":[23],"we":[24,46],"examine":[25],"a":[26,52],"spectrum":[27],"of":[28,84],"choices,":[30],"including":[31],"label":[32],"units,":[33],"context":[34],"length,":[35],"topology.":[37],"To":[38,75],"isolate":[39],"language":[40,65],"effects":[42],"from":[43],"acoustic":[44,73],"variation,":[45],"synthesize":[47],"target":[48,60],"audio":[50],"using":[51],"text-to-speech":[53],"system":[54],"trained":[55],"on":[56],"LibriSpeech.":[57],"incorporate":[59],"ngram":[62],"neural":[64],"models":[66],"for":[67],"adaptation":[69],"without":[70],"retraining":[71],"model.":[74],"our":[76],"knowledge,":[77],"this":[78],"is":[79,123],"first":[81],"controlled":[82],"comparison":[83],"optimized":[85],"systems":[87],"across":[88],"state-of-the-art":[89],"architectures":[90],"shift,":[93,105],"offering":[94],"insights":[95],"into":[96],"their":[97],"generalization.":[98],"The":[99],"results":[100],"show":[101],"that,":[102],"rather":[106],"than":[107],"decoder":[109],"architecture":[110],"choice":[111],"or":[112],"distinction":[114],"between":[115],"seq2seq":[120],"models,":[121],"it":[122],"specific":[124],"that":[127],"influence":[128],"performance.":[129]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-04-03T00:00:00"}