{"id":"https://openalex.org/W4415433463","doi":"https://doi.org/10.21437/interspeech.2025-1021","title":"Spectrotemporal Modulation: Efficient and Interpretable Feature Representation for Classifying Speech, Music, and Environmental Sounds","display_name":"Spectrotemporal Modulation: Efficient and Interpretable Feature Representation for Classifying Speech, Music, and Environmental Sounds","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433463","doi":"https://doi.org/10.21437/interspeech.2025-1021"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1021","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.23509","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012364691","display_name":"Andrew Chang","orcid":"https://orcid.org/0000-0001-6745-4435"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Andrew Chang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078871137","display_name":"Yike Li","orcid":"https://orcid.org/0009-0008-5204-970X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yike Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027526258","display_name":"Iran R. Roman","orcid":"https://orcid.org/0000-0003-3781-7244"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iran R. Roman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5033417964","display_name":"David Poeppel","orcid":"https://orcid.org/0000-0003-0184-163X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Poeppel","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5012364691"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3709843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"216","last_page":"220"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9298999905586243,"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":0.9298999905586243,"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/representation","display_name":"Representation (politics)","score":0.7080000042915344},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6754000186920166},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6388000249862671},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.48969998955726624},{"id":"https://openalex.org/keywords/natural-sounds","display_name":"Natural sounds","score":0.4300000071525574},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3813000023365021},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.3619000017642975},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3488999903202057}],"concepts":[{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.7080000042915344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7008000016212463},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6754000186920166},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.671500027179718},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6388000249862671},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.48969998955726624},{"id":"https://openalex.org/C2780646970","wikidata":"https://www.wikidata.org/wiki/Q6980787","display_name":"Natural sounds","level":2,"score":0.4300000071525574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4023999869823456},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.3619000017642975},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.3452000021934509},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.34450000524520874},{"id":"https://openalex.org/C3020799230","wikidata":"https://www.wikidata.org/wiki/Q160289","display_name":"Auditory perception","level":3,"score":0.3319000005722046},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C173201364","wikidata":"https://www.wikidata.org/wiki/Q897410","display_name":"Brain\u2013computer interface","level":3,"score":0.2996000051498413},{"id":"https://openalex.org/C2780297895","wikidata":"https://www.wikidata.org/wiki/Q18676","display_name":"Auditory cortex","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27300000190734863},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2653999924659729},{"id":"https://openalex.org/C96199812","wikidata":"https://www.wikidata.org/wiki/Q2145290","display_name":"Mental representation","level":3,"score":0.25360000133514404},{"id":"https://openalex.org/C2992441837","wikidata":"https://www.wikidata.org/wiki/Q7362","display_name":"Human ear","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.25200000405311584}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-1021","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.23509","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.23509","pdf_url":"https://arxiv.org/pdf/2505.23509","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.23509","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.23509","pdf_url":"https://arxiv.org/pdf/2505.23509","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7279642215","display_name":null,"funder_award_id":"F32DC018205","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"}],"funders":[{"id":"https://openalex.org/F4320309445","display_name":"Leon Levy Foundation","ror":"https://ror.org/033hnyq61"},{"id":"https://openalex.org/F4320314698","display_name":"GRAMMY Museum Foundation","ror":null},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415433463.pdf","grobid_xml":"https://content.openalex.org/works/W4415433463.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Audio":[0],"DNNs":[1,68],"have":[2],"demonstrated":[3],"impressive":[4],"performance":[5,53],"on":[6,32],"various":[7],"machine":[8,86,107],"listening":[9,108],"tasks;":[10],"however,":[11],"most":[12],"of":[13,54,65,106,117],"their":[14],"representations":[15],"are":[16,78],"computationally":[17],"costly":[18],"and":[19,74,85,96,109,119,128],"uninterpretable,":[20],"leaving":[21],"room":[22],"for":[23,81,100,114],"optimization.":[24],"Here,":[25],"we":[26],"propose":[27],"a":[28,37],"novel":[29],"approach":[30],"centered":[31],"spectrotemporal":[33],"modulation":[34],"(STM)":[35],"features,":[36],"signal":[38],"processing":[39],"method":[40],"that":[41,64,91],"mimics":[42],"the":[43,47,104],"neurophysiological":[44],"representation":[45,99],"in":[46],"human":[48,83],"auditory":[49,120],"cortex.":[50],"The":[51],"classification":[52],"our":[55],"STM-based":[56],"model,":[57],"without":[58],"any":[59],"pretraining,":[60],"is":[61,93],"comparable":[62],"to":[63],"pretrained":[66],"audio":[67,101,126],"across":[69],"diverse":[70],"naturalistic":[71],"speech,":[72],"music,":[73],"environmental":[75],"sounds,":[76],"which":[77],"essential":[79],"categories":[80],"both":[82],"cognition":[84],"perception.":[87],"These":[88],"results":[89],"show":[90],"STM":[92],"an":[94],"efficient":[95],"interpretable":[97],"feature":[98],"classification,":[102],"advancing":[103],"development":[105],"unlocking":[110],"exciting":[111],"new":[112],"possibilities":[113],"basic":[115],"understanding":[116],"speech":[118],"sciences,":[121],"as":[122,124],"well":[123],"developing":[125],"BCI":[127],"cognitive":[129],"computing.":[130]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-23T00:00:00"}