{"id":"https://openalex.org/W7213891715","doi":"https://doi.org/10.21437/interspeech.2026-1504","title":"Enhancing Audio Reasoning via Semantic Summary Prediction","display_name":"Enhancing Audio Reasoning via Semantic Summary Prediction","publication_year":2026,"publication_date":"2026-09-27","ids":{"openalex":"https://openalex.org/W7213891715","doi":"https://doi.org/10.21437/interspeech.2026-1504"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2026-1504","doi":"https://doi.org/10.21437/interspeech.2026-1504","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2026-1504","pdf_url":"https://www.isca-archive.org/interspeech_2026/bonzi26_interspeech.pdf","source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"Interspeech 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.isca-archive.org/interspeech_2026/bonzi26_interspeech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093111485","display_name":"Francesco Bonzi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]},{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Francesco Bonzi","raw_affiliation_strings":["Concordia University , Canada","Mila -Quebec AI Institute , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Concordia University , Canada","institution_ids":["https://openalex.org/I60158472"]},{"raw_affiliation_string":"Mila -Quebec AI Institute , Canada","institution_ids":["https://openalex.org/I4210164802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038687274","display_name":"Pooneh Mousavi","orcid":"https://orcid.org/0009-0007-5761-5988","observed_orcids":["https://orcid.org/0009-0007-5761-5988"]},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]},{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Pooneh Mousavi","raw_affiliation_strings":["Concordia University , Canada","Mila -Quebec AI Institute , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Concordia University , Canada","institution_ids":["https://openalex.org/I60158472"]},{"raw_affiliation_string":"Mila -Quebec AI Institute , Canada","institution_ids":["https://openalex.org/I4210164802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023830739","display_name":"Cem Subakan","orcid":"https://orcid.org/0000-0002-7593-6589","observed_orcids":["https://orcid.org/0000-0002-7593-6589"]},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]},{"id":"https://openalex.org/I43406934","display_name":"Universit\u00e9 Laval","ror":"https://ror.org/04sjchr03","country_code":"CA","type":"education","lineage":["https://openalex.org/I43406934"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Cem Subakan","raw_affiliation_strings":["Mila -Quebec AI Institute , Canada","Universit\u00e9 Laval , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mila -Quebec AI Institute , Canada","institution_ids":["https://openalex.org/I4210164802"]},{"raw_affiliation_string":"Universit\u00e9 Laval , Canada","institution_ids":["https://openalex.org/I43406934"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040811098","display_name":"Mirco Ravanelli","orcid":"https://orcid.org/0000-0002-3929-5526","observed_orcids":["https://orcid.org/0000-0002-3929-5526","https://orcid.org/0000-0001-8479-3121"]},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]},{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mirco Ravanelli","raw_affiliation_strings":["Concordia University , Canada","Mila -Quebec AI Institute , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Concordia University , Canada","institution_ids":["https://openalex.org/I60158472"]},{"raw_affiliation_string":"Mila -Quebec AI Institute , Canada","institution_ids":["https://openalex.org/I4210164802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0015,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92645399,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"5786","last_page":"5791"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.382099986076355,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.382099986076355,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.23430000245571136,"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/T10028","display_name":"Topic Modeling","score":0.19580000638961792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/large-audio-language-models","display_name":"large audio language models","score":0.8579999804496765},{"id":"https://openalex.org/keywords/chain-of-thought","display_name":"chain-of-thought","score":0.7730000019073486},{"id":"https://openalex.org/keywords/cosine-similarity-loss","display_name":"cosine similarity loss","score":0.8539999723434448},{"id":"https://openalex.org/keywords/sentence-bert-embeddings","display_name":"Sentence-BERT embeddings","score":0.8889999985694885},{"id":"https://openalex.org/keywords/zero-shot-reasoning","display_name":"zero-shot reasoning","score":0.7310000061988831},{"id":"https://openalex.org/keywords/audio-question-answering","display_name":"audio question answering","score":0.5720000267028809}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7484999895095825},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5799000263214111},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.536300003528595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5278000235557556},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.48820000886917114},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.46129998564720154},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.388700008392334},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36579999327659607},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3228999972343445},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.3149999976158142},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25920000672340393},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25679999589920044}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2026-1504","doi":"https://doi.org/10.21437/interspeech.2026-1504","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2026-1504","pdf_url":"https://www.isca-archive.org/interspeech_2026/bonzi26_interspeech.pdf","source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"Interspeech 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2609.20849","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.20849","pdf_url":"https://arxiv.org/pdf/2609.20849","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.20849","doi":"https://doi.org/10.48550/arxiv.2609.20849","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.20849","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2026-1504","doi":"https://doi.org/10.21437/interspeech.2026-1504","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2026-1504","pdf_url":"https://www.isca-archive.org/interspeech_2026/bonzi26_interspeech.pdf","source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"Interspeech 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331257","display_name":"Alliance de recherche num\u00e9rique du Canada","ror":"https://ror.org/010r6td27"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213891715.pdf","grobid_xml":"https://content.openalex.org/works/W7213891715.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W3101045333","https://openalex.org/W4311000453","https://openalex.org/W4312048190","https://openalex.org/W4387225729","https://openalex.org/W4387891768","https://openalex.org/W4404311027","https://openalex.org/W4406880404","https://openalex.org/W4409051416","https://openalex.org/W4414578469","https://openalex.org/W4414587667","https://openalex.org/W4414900360","https://openalex.org/W4415200519","https://openalex.org/W4415202956","https://openalex.org/W4415255153","https://openalex.org/W4416035790","https://openalex.org/W4416258585","https://openalex.org/W6910746321","https://openalex.org/W6929674484","https://openalex.org/W6948369276","https://openalex.org/W7092292794","https://openalex.org/W7140115484","https://openalex.org/W7148532570","https://openalex.org/W7148534712"],"related_works":["https://openalex.org/W7155062258","https://openalex.org/W7154497295","https://openalex.org/W4415334728","https://openalex.org/W7091106515","https://openalex.org/W7140088932","https://openalex.org/W7134905021","https://openalex.org/W6929674484","https://openalex.org/W7214794605","https://openalex.org/W7105506321","https://openalex.org/W7138876343"],"abstract_inverted_index":{"Large":[0],"Audio":[1,47],"Language":[2],"Models":[3],"(LALMs)":[4],"perform":[5],"well":[6],"on":[7,81],"complex":[8],"question":[9],"answering":[10],"but":[11],"often":[12],"show":[13,87],"a":[14,51,60,65],"reasoning":[15,30,79,90],"gap,":[16],"where":[17],"explicit":[18],"Chain-of-Thought":[19],"(CoT)":[20],"reduces":[21],"accuracy":[22],"compared":[23],"to":[24,95],"direct":[25],"answers.We":[26],"hypothesize":[27],"that":[28],"long":[29],"sequences":[31],"shift":[32],"attention":[33,94],"away":[34],"from":[35],"the":[36,56,69,74],"audio":[37,96],"input.To":[38],"address":[39],"this,":[40],"we":[41],"propose":[42],"SPARE":[43],"(Semantic":[44],"Prediction":[45],"for":[46],"REasoning),":[48],"which":[49],"introduces":[50],"register":[52],"token":[53],"aligned":[54],"with":[55,64,73,85],"final":[57],"conclusion":[58],"using":[59],"cosine":[61],"similarity":[62],"loss":[63],"Sentence-BERT":[66],"embedding.This":[67],"conditions":[68],"model's":[70],"latent":[71],"space":[72],"target":[75],"semantic":[76],"goal":[77],"before":[78],"begins.Experiments":[80],"MMAU":[82],"and":[83,91],"MMAR":[84],"SALMONN":[86],"improved":[88],"zeroshot":[89],"stronger":[92],"early":[93],"without":[97],"additional":[98],"inference":[99],"cost.":[100]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-09-22T00:00:00"}