{"id":"https://openalex.org/W4387869517","doi":"https://doi.org/10.1109/mlsp55844.2023.10285893","title":"Underwater Acoustic Signal Classification using Hierarchical Audio Transformer with Noisy Input","display_name":"Underwater Acoustic Signal Classification using Hierarchical Audio Transformer with Noisy Input","publication_year":2023,"publication_date":"2023-09-17","ids":{"openalex":"https://openalex.org/W4387869517","doi":"https://doi.org/10.1109/mlsp55844.2023.10285893"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp55844.2023.10285893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp55844.2023.10285893","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5104177790","display_name":"Quoc Thinh Vo","orcid":null},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Quoc Thinh Vo","raw_affiliation_strings":["Drexel University,Department of Electrical and Computer Engineering,Philadelphia,PA,USA","Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"Drexel University,Department of Electrical and Computer Engineering,Philadelphia,PA,USA","institution_ids":["https://openalex.org/I72816309"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102000970","display_name":"David K. Han","orcid":"https://orcid.org/0000-0001-5055-5408"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David K. Han","raw_affiliation_strings":["Drexel University,Department of Electrical and Computer Engineering,Philadelphia,PA,USA","Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"Drexel University,Department of Electrical and Computer Engineering,Philadelphia,PA,USA","institution_ids":["https://openalex.org/I72816309"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5104177790"],"corresponding_institution_ids":["https://openalex.org/I72816309"],"apc_list":null,"apc_paid":null,"fwci":1.587,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.82514249,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11698","display_name":"Underwater Acoustics Research","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"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/T11698","display_name":"Underwater Acoustics Research","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9944999814033508,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9901999831199646,"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/underwater","display_name":"Underwater","score":0.8356525301933289},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7540407180786133},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7026301026344299},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5605352520942688},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5303034782409668},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4508993327617645},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4492458701133728},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44082820415496826},{"id":"https://openalex.org/keywords/ambient-noise-level","display_name":"Ambient noise level","score":0.42775386571884155},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4108086824417114},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35184329748153687},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33358633518218994},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.29328906536102295},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2010575532913208},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1553477942943573},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.14477717876434326},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13631901144981384}],"concepts":[{"id":"https://openalex.org/C98083399","wikidata":"https://www.wikidata.org/wiki/Q3246517","display_name":"Underwater","level":2,"score":0.8356525301933289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7540407180786133},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7026301026344299},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5605352520942688},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5303034782409668},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4508993327617645},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4492458701133728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44082820415496826},{"id":"https://openalex.org/C205312793","wikidata":"https://www.wikidata.org/wiki/Q16002801","display_name":"Ambient noise level","level":3,"score":0.42775386571884155},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4108086824417114},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35184329748153687},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33358633518218994},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.29328906536102295},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2010575532913208},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1553477942943573},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.14477717876434326},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13631901144981384},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp55844.2023.10285893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp55844.2023.10285893","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/14","score":0.8700000047683716,"display_name":"Life below water"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2030214786","https://openalex.org/W2111432826","https://openalex.org/W2112796928","https://openalex.org/W2127623958","https://openalex.org/W2172000360","https://openalex.org/W2466903746","https://openalex.org/W2765407302","https://openalex.org/W2903741778","https://openalex.org/W2903926094","https://openalex.org/W2936774411","https://openalex.org/W2980216782","https://openalex.org/W2997818084","https://openalex.org/W3089280383","https://openalex.org/W3110726247","https://openalex.org/W3120421331","https://openalex.org/W3138516171","https://openalex.org/W3157525179","https://openalex.org/W3176726540","https://openalex.org/W3196974791","https://openalex.org/W3198035615","https://openalex.org/W3205475937","https://openalex.org/W3206996142","https://openalex.org/W4225139539","https://openalex.org/W4306814790","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6745136726","https://openalex.org/W6802510933","https://openalex.org/W6845577938"],"related_works":["https://openalex.org/W4388412763","https://openalex.org/W1999583034","https://openalex.org/W3217214504","https://openalex.org/W3168963531","https://openalex.org/W2591930867","https://openalex.org/W2953138830","https://openalex.org/W2773822314","https://openalex.org/W3176162126","https://openalex.org/W2891537746","https://openalex.org/W2611397005"],"abstract_inverted_index":{"Classifying":[0],"different":[1],"acoustic":[2],"sources":[3],"has":[4,34],"been":[5,35],"a":[6],"challenge":[7],"in":[8,18,40,45,99],"underwater":[9,63],"environment":[10,20],"due":[11,23],"to":[12,24,37,76],"the":[13,25,69,77,84,90],"difficulties":[14],"of":[15,27,71,89],"acquiring":[16],"data":[17],"ocean":[19],"and":[21,60,81],"also":[22,95],"variety":[26],"background":[28],"noise":[29,101],"it":[30],"poses.":[31],"Self-attention":[32],"mechanism":[33],"shown":[36],"be":[38],"effective":[39],"various":[41],"machine":[42],"learning":[43],"tasks":[44],"challenging":[46],"environments":[47],"with":[48],"sparse":[49],"dataset.":[50],"An":[51],"audio":[52],"transformer,":[53],"designed":[54],"for":[55,62],"air":[56],"acoustics,":[57],"was":[58],"modified":[59],"adapted":[61],"sound":[64],"classification":[65,92],"task.":[66],"We":[67,94],"demonstrate":[68],"effectiveness":[70],"our":[72],"method":[73,86],"by":[74],"applying":[75],"shipsEar":[78],"dataset":[79],"[1],":[80],"show":[82,96],"that":[83],"proposed":[85],"outperforms":[87],"some":[88],"latest":[91],"methods.":[93],"its":[97],"robustness":[98],"high":[100],"environments.":[102]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}