{"id":"https://openalex.org/W7165630366","doi":"https://doi.org/10.48550/arxiv.2606.22020","title":"What Do Neural Networks Learn for TDOA Estimation? A Cross-Architecture Probing Study","display_name":"What Do Neural Networks Learn for TDOA Estimation? A Cross-Architecture Probing Study","publication_year":2026,"publication_date":"2026-06-20","ids":{"openalex":"https://openalex.org/W7165630366","doi":"https://doi.org/10.48550/arxiv.2606.22020"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.22020","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22020","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.22020","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114223204","display_name":"Yaozhong Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang, Yaozhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139149550","display_name":"Jiang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080269657","display_name":"Runwu Shi","orcid":"https://orcid.org/0000-0001-9097-9619"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Runwu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071399636","display_name":"Takeshi Ashizawa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashizawa, Takeshi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139170971","display_name":"Benjamin Yen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yen, Benjamin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139178087","display_name":"Kazuhiro Nakadai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nakadai, Kazuhiro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.3077000081539154,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.3077000081539154,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/T11739","display_name":"Microwave Imaging and Scattering Analysis","score":0.22339999675750732,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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/T11038","display_name":"Advanced SAR Imaging Techniques","score":0.09220000356435776,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.7261999845504761},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6295999884605408},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5860000252723694},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5317000150680542},{"id":"https://openalex.org/keywords/multilateration","display_name":"Multilateration","score":0.4952000081539154},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4867999851703644},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.39169999957084656}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7261999845504761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6854000091552734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6345000267028809},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6295999884605408},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5860000252723694},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5317000150680542},{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.4952000081539154},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4867999851703644},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4339999854564667},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.39169999957084656},{"id":"https://openalex.org/C3832189","wikidata":"https://www.wikidata.org/wiki/Q8588916","display_name":"Models of neural computation","level":3,"score":0.3327000141143799},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.27549999952316284},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26600000262260437}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.22020","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22020","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.22020","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22020","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Neural":[0],"networks":[1,72,118],"outperform":[2],"classical":[3,96,114],"GCC-PHAT":[4],"for":[5],"Time-Difference-of-Arrival":[6],"(TDOA)":[7],"estimation":[8],"in":[9],"noise":[10],"and":[11,39,44,58,97],"reverberation,":[12],"yet":[13],"their":[14],"internal":[15],"strategy":[16],"remains":[17,111],"unexplored.":[18],"To":[19],"uncover":[20],"it,":[21],"we":[22],"turn":[23],"GCC-PHAT's":[24],"mathematical":[25],"steps":[26],"into":[27],"diagnostic":[28],"targets,":[29],"probing":[30],"hidden":[31],"layers":[32],"of":[33,66],"three":[34],"architectures":[35,57],"(MLP,":[36],"CNN,":[37],"Transformer)":[38],"complementing":[40],"with":[41],"gradient":[42],"attribution":[43],"causal":[45],"frequency":[46,76],"masking.":[47],"We":[48],"find":[49],"that":[50,78],"cross-power":[51],"computation":[52],"consistently":[53],"emerges":[54],"across":[55],"all":[56],"conditions,":[59],"while":[60],"PHAT":[61,88,110],"whitening,":[62],"the":[63,112],"defining":[64],"step":[65],"GCC-PHAT,":[67],"fails":[68],"to":[69],"emerge.":[70],"Instead,":[71],"learn":[73],"a":[74],"magnitude-aware":[75],"weighting":[77],"preserves":[79],"per-frequency":[80],"reliability":[81],"information":[82,90],"discarded":[83],"by":[84,122],"PHAT.":[85],"This":[86],"makes":[87],"an":[89],"bottleneck:":[91],"removing":[92],"it":[93],"from":[94],"both":[95],"neural":[98],"GCC":[99],"pipelines":[100],"improves":[101],"performance":[102],"under":[103],"additive":[104],"noise.":[105],"On":[106],"real-world":[107],"reverberant":[108],"data,":[109],"best":[113],"weighting,":[115],"but":[116],"end-to-end":[117],"achieve":[119],"lower":[120],"error":[121],"learning":[123],"data-adaptive":[124],"weighting.":[125]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-24T00:00:00"}