{"id":"https://openalex.org/W4408353143","doi":"https://doi.org/10.1109/icassp49660.2025.10888790","title":"Evaluating Snippet Significance: A Framework for Audio and Text-Based Dialogue Summarization","display_name":"Evaluating Snippet Significance: A Framework for Audio and Text-Based Dialogue Summarization","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353143","doi":"https://doi.org/10.1109/icassp49660.2025.10888790"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5048384598","display_name":"Anderson Luiz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210106192","display_name":"Technische Hochschule Ingolstadt","ror":"https://ror.org/02bxzcy64","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210106192"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Anderson de Lima Luiz","raw_affiliation_strings":["Germany Technische Hochschule Ingolstadt,AImotion Bavaria,Ingolstadt, Bayern,Germany,85049"],"affiliations":[{"raw_affiliation_string":"Germany Technische Hochschule Ingolstadt,AImotion Bavaria,Ingolstadt, Bayern,Germany,85049","institution_ids":["https://openalex.org/I4210106192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116594402","display_name":"Raviteja Boddu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210106192","display_name":"Technische Hochschule Ingolstadt","ror":"https://ror.org/02bxzcy64","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210106192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Raviteja Boddu","raw_affiliation_strings":["Germany Technische Hochschule Ingolstadt,AImotion Bavaria,Ingolstadt, Bayern,Germany,85049"],"affiliations":[{"raw_affiliation_string":"Germany Technische Hochschule Ingolstadt,AImotion Bavaria,Ingolstadt, Bayern,Germany,85049","institution_ids":["https://openalex.org/I4210106192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040558849","display_name":"Munir Georges","orcid":"https://orcid.org/0000-0002-5542-149X"},"institutions":[{"id":"https://openalex.org/I4210106192","display_name":"Technische Hochschule Ingolstadt","ror":"https://ror.org/02bxzcy64","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210106192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Munir Georges","raw_affiliation_strings":["Germany Technische Hochschule Ingolstadt,AImotion Bavaria,Ingolstadt, Bayern,Germany,85049"],"affiliations":[{"raw_affiliation_string":"Germany Technische Hochschule Ingolstadt,AImotion Bavaria,Ingolstadt, Bayern,Germany,85049","institution_ids":["https://openalex.org/I4210106192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048384598"],"corresponding_institution_ids":["https://openalex.org/I4210106192"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02024915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9977999925613403,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9977999925613403,"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":0.9976999759674072,"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/T12031","display_name":"Speech and dialogue systems","score":0.9973999857902527,"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/snippet","display_name":"Snippet","score":0.9425443410873413},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.9420239925384521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8371514081954956},{"id":"https://openalex.org/keywords/multi-document-summarization","display_name":"Multi-document summarization","score":0.4317079782485962},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.41959941387176514},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4048405885696411},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3779125511646271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3233878016471863}],"concepts":[{"id":"https://openalex.org/C2777822670","wikidata":"https://www.wikidata.org/wiki/Q1120538","display_name":"Snippet","level":2,"score":0.9425443410873413},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9420239925384521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8371514081954956},{"id":"https://openalex.org/C134714966","wikidata":"https://www.wikidata.org/wiki/Q6934448","display_name":"Multi-document summarization","level":3,"score":0.4317079782485962},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.41959941387176514},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4048405885696411},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3779125511646271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3233878016471863}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311687","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1591607137","https://openalex.org/W2101105183","https://openalex.org/W2125336414","https://openalex.org/W2788701627","https://openalex.org/W2964051877","https://openalex.org/W2964243274","https://openalex.org/W2970419734","https://openalex.org/W4385987622","https://openalex.org/W4386058707","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6752724743","https://openalex.org/W6769627184","https://openalex.org/W6771915120","https://openalex.org/W6780218876","https://openalex.org/W6890460126"],"related_works":["https://openalex.org/W3164984162","https://openalex.org/W2104677027","https://openalex.org/W2902627734","https://openalex.org/W2112885393","https://openalex.org/W2065541085","https://openalex.org/W2785821657","https://openalex.org/W2173208124","https://openalex.org/W2568827738","https://openalex.org/W1990695371","https://openalex.org/W2365100044"],"abstract_inverted_index":{"The":[0,99,177],"extraction":[1,83],"and":[2,15,34,57,71,84,126,135,149,191,211,233],"summarization":[3,106,159,222],"of":[4,44,92,237],"key":[5],"information":[6],"from":[7,242],"dialogues":[8],"are":[9,37,183,195],"essential":[10],"for":[11,39,80,86,185,220],"improving":[12],"communication":[13],"tools":[14],"outcomes":[16],"across":[17,155],"various":[18],"domains.":[19],"Traditional":[20],"text-based":[21,167,199],"approaches":[22],"often":[23,196],"fail":[24],"to":[25,63,95,166,230,245],"capture":[26],"critical":[27],"auditory":[28,175,227],"cues":[29,228],"such":[30,132],"as":[31,133],"intonation,":[32],"pauses,":[33],"emphasis,":[35],"which":[36,194],"vital":[38],"understanding":[40,236],"the":[41,68,90,112,116,139,170],"full":[42],"context":[43,172],"spoken":[45],"interactions.":[46],"This":[47,214],"paper":[48],"introduces":[49],"a":[50,102,217,231],"novel":[51],"framework":[52,206],"that":[53,180,225],"independently":[54],"analyzes":[55],"text":[56,87],"audio":[58,81,181],"modalities,":[59,204],"assigning":[60],"significance":[61,162],"scores":[62,163],"dialogue":[64,221],"snippets.":[65],"Evaluations":[66],"on":[67,138],"AMI":[69,113],"[1]":[70,114],"ICSI":[72,140],"[2]":[73,141],"meeting":[74],"corpora":[75],"utilize":[76],"Wav2Vec":[77],"2.0":[78],"[3]":[79],"embedding":[82],"BERT":[85],"embeddings,":[88],"allowing":[89],"contributions":[91],"each":[93],"modality":[94],"be":[96],"thoroughly":[97],"examined.":[98],"method":[100],"demonstrates":[101],"significant":[103],"improvement":[104],"in":[105],"accuracy":[107],"over":[108],"text-only":[109],"models.":[110],"On":[111],"dataset,":[115,142],"proposed":[117],"approach":[118],"achieves":[119,144,160],"ROUGE-1":[120,145],"(0.94),":[121,125],"ROUGE-2":[122,147],"(0.93),":[123],"ROUGE-L":[124],"BLEU":[127,150],"(0.88),":[128],"outperforming":[129],"state-of-the-art":[130],"models":[131],"BART":[134],"PEGASUS.":[136],"Similarly,":[137],"it":[143],"(0.79),":[146],"(0.75),":[148],"(0.47),":[151],"showcasing":[152],"its":[153],"robustness":[154],"datasets.":[156],"Furthermore,":[157],"audio-based":[158],"higher":[161],"(94%)":[164],"compared":[165],"(89%),":[168],"highlighting":[169],"additional":[171],"provided":[173],"by":[174,198,223],"features.":[176],"findings":[178],"indicate":[179],"features":[182],"crucial":[184],"capturing":[186],"emotional":[187],"tone,":[188],"speaker":[189],"intent,":[190],"conversational":[192],"flow,":[193],"overlooked":[197],"methods.":[200],"By":[201],"integrating":[202],"both":[203],"this":[205],"produces":[207],"more":[208,234],"contextually":[209],"rich":[210],"accurate":[212],"summaries.":[213],"research":[215],"sets":[216],"new":[218],"benchmark":[219],"demonstrating":[224],"incorporating":[226],"leads":[229],"deeper":[232],"comprehensive":[235],"dialogues,":[238],"with":[239],"applications":[240],"ranging":[241],"virtual":[243],"meetings":[244],"educational":[246],"content":[247],"summarization.":[248]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}
