{"id":"https://openalex.org/W4225328536","doi":"https://doi.org/10.1109/icassp43922.2022.9746577","title":"Time-Frequency and Geometric Analysis of Task-Dependent Learning in Raw Waveform Based Acoustic Models","display_name":"Time-Frequency and Geometric Analysis of Task-Dependent Learning in Raw Waveform Based Acoustic Models","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225328536","doi":"https://doi.org/10.1109/icassp43922.2022.9746577"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746577","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5083499838","display_name":"Devansh Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I110675161","display_name":"Infosys (India)","ror":"https://ror.org/03bs18y54","country_code":"IN","type":"company","lineage":["https://openalex.org/I110675161"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]},{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Devansh Gupta","raw_affiliation_strings":["IIIT Delhi,Infosys Centre for AI,India","Infosys Centre for AI, IIIT Delhi, India"],"affiliations":[{"raw_affiliation_string":"IIIT Delhi,Infosys Centre for AI,India","institution_ids":["https://openalex.org/I68891433","https://openalex.org/I119939252","https://openalex.org/I110675161"]},{"raw_affiliation_string":"Infosys Centre for AI, IIIT Delhi, India","institution_ids":["https://openalex.org/I68891433","https://openalex.org/I119939252","https://openalex.org/I110675161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075520691","display_name":"Vinayak Abrol","orcid":"https://orcid.org/0000-0001-8149-8151"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]},{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I110675161","display_name":"Infosys (India)","ror":"https://ror.org/03bs18y54","country_code":"IN","type":"company","lineage":["https://openalex.org/I110675161"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vinayak Abrol","raw_affiliation_strings":["IIIT Delhi,Infosys Centre for AI,India","Infosys Centre for AI, IIIT Delhi, India"],"affiliations":[{"raw_affiliation_string":"IIIT Delhi,Infosys Centre for AI,India","institution_ids":["https://openalex.org/I68891433","https://openalex.org/I119939252","https://openalex.org/I110675161"]},{"raw_affiliation_string":"Infosys Centre for AI, IIIT Delhi, India","institution_ids":["https://openalex.org/I68891433","https://openalex.org/I119939252","https://openalex.org/I110675161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5083499838"],"corresponding_institution_ids":["https://openalex.org/I110675161","https://openalex.org/I119939252","https://openalex.org/I68891433"],"apc_list":null,"apc_paid":null,"fwci":0.4155,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.55429864,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4323","last_page":"4327"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/computer-science","display_name":"Computer science","score":0.7384193539619446},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.7105613946914673},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5917566418647766},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5357344150543213},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5262764096260071},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4707382619380951},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45182085037231445},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4484793543815613},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.44189056754112244},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.4221884608268738},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.4159892201423645},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1319987177848816},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.10790812969207764},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10631906986236572}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7384193539619446},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7105613946914673},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5917566418647766},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5357344150543213},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5262764096260071},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4707382619380951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45182085037231445},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4484793543815613},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.44189056754112244},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4221884608268738},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.4159892201423645},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1319987177848816},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.10790812969207764},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10631906986236572},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746577","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6800000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W9143300","https://openalex.org/W1494198834","https://openalex.org/W1539128127","https://openalex.org/W1992008660","https://openalex.org/W1993882792","https://openalex.org/W2046056978","https://openalex.org/W2123045220","https://openalex.org/W2155273149","https://openalex.org/W2187585256","https://openalex.org/W2529943390","https://openalex.org/W2566781703","https://openalex.org/W2594633041","https://openalex.org/W2797583228","https://openalex.org/W2936802426","https://openalex.org/W2963510708","https://openalex.org/W2964052309","https://openalex.org/W2964218314","https://openalex.org/W2967606780","https://openalex.org/W2972717745","https://openalex.org/W2987999870","https://openalex.org/W3034892239","https://openalex.org/W3164680725","https://openalex.org/W3170179936","https://openalex.org/W4225674648","https://openalex.org/W4289494182","https://openalex.org/W4293861706","https://openalex.org/W6600345780","https://openalex.org/W6632160421","https://openalex.org/W6677995690","https://openalex.org/W6734194636","https://openalex.org/W6739575509","https://openalex.org/W6750665317","https://openalex.org/W6751758391","https://openalex.org/W6754819195","https://openalex.org/W7072093103"],"related_works":["https://openalex.org/W1974895211","https://openalex.org/W2176409448","https://openalex.org/W2129841057","https://openalex.org/W3040712279","https://openalex.org/W2367940508","https://openalex.org/W1820289435","https://openalex.org/W1927135183","https://openalex.org/W1596300871","https://openalex.org/W2890436937","https://openalex.org/W3090190000"],"abstract_inverted_index":{"End-to-end":[0],"raw-waveform":[1],"modelling":[2,52],"with":[3,107],"learnable":[4],"feature":[5,30],"extraction":[6],"front-ends":[7],"has":[8],"shown":[9],"promising":[10],"results":[11],"in":[12],"various":[13],"speech/audio":[14],"tasks.":[15,120],"Despite":[16],"its":[17],"varied":[18],"success,":[19],"there":[20],"have":[21],"not":[22],"been":[23],"many":[24],"attempts":[25],"to":[26,63,85],"understand":[27],"how":[28],"spectral/temporal":[29],"integration":[31],"from":[32],"raw":[33],"inputs":[34],"helps":[35],"recognize":[36],"task-dependent":[37],"information.":[38],"Towards":[39],"this":[40,42],"aim,":[41],"work":[43],"presents":[44],"data-dependent":[45],"and":[46,95,117],"data-independent":[47],"methods":[48,106],"for":[49],"understanding":[50],"the":[51,87,98,104],"behavior":[53],"of":[54,71,82,89,97,103,109],"acoustic":[55],"models.":[56],"The":[57,76],"first":[58],"method":[59,78],"employs":[60,79],"time-frequency":[61],"analysis":[62],"visualize":[64],"input-specific":[65],"response":[66],"spectra":[67],"as":[68],"a":[69],"function":[70],"short-time":[72],"front-end":[73],"block":[74],"processing.":[75],"second":[77],"geometric":[80],"properties":[81],"layer-wise":[83],"weights":[84],"quantify":[86],"impact":[88],"architectural":[90],"choices":[91],"on":[92,112],"signal":[93],"propagation":[94],"trainability":[96],"model.":[99],"We":[100],"demonstrate":[101],"potential":[102],"proposed":[105],"help":[108],"case":[110],"studies":[111],"speech":[113],"classification,":[114],"speaker":[115],"identification,":[116],"spoofing":[118],"classification":[119]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}