{"id":"https://openalex.org/W3046609253","doi":"https://doi.org/10.21437/interspeech.2020-3074","title":"Multimodal Semi-Supervised Learning Framework for Punctuation Prediction in Conversational Speech","display_name":"Multimodal Semi-Supervised Learning Framework for Punctuation Prediction in Conversational Speech","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3046609253","doi":"https://doi.org/10.21437/interspeech.2020-3074","mag":"3046609253"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-3074","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-3074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.00702","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014130267","display_name":"Monica Sunkara","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Monica Sunkara","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004616142","display_name":"Srikanth Ronanki","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Srikanth Ronanki","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020261049","display_name":"Dhanush Bekal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dhanush Bekal","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050552820","display_name":"Sravan Bodapati","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sravan Bodapati","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050325468","display_name":"Katrin Kirchhoff","orcid":"https://orcid.org/0000-0002-6645-6030"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katrin Kirchhoff","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5014130267"],"corresponding_institution_ids":["https://openalex.org/I4210089985"],"apc_list":null,"apc_paid":null,"fwci":0.1371,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55179733,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"4911","last_page":"4915"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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":0.9975000023841858,"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/computer-science","display_name":"Computer science","score":0.7760158181190491},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.6452087759971619},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6429287195205688},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5978711247444153},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5819584131240845},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5540729761123657},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4478083550930023},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4367642104625702}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7760158181190491},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.6452087759971619},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6429287195205688},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5978711247444153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5819584131240845},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5540729761123657},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4478083550930023},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4367642104625702},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-3074","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-3074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.00702","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.00702","pdf_url":"https://arxiv.org/pdf/2008.00702","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"mag:3046609253","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2008.00702","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2008.00702","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.00702","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.00702","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.00702","pdf_url":"https://arxiv.org/pdf/2008.00702","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3046609253.pdf","grobid_xml":"https://content.openalex.org/works/W3046609253.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W61566120","https://openalex.org/W94670513","https://openalex.org/W97072897","https://openalex.org/W171402391","https://openalex.org/W1524333225","https://openalex.org/W1587490638","https://openalex.org/W1855892484","https://openalex.org/W2085628288","https://openalex.org/W2113851376","https://openalex.org/W2121879602","https://openalex.org/W2166116787","https://openalex.org/W2169187092","https://openalex.org/W2398104528","https://openalex.org/W2403334028","https://openalex.org/W2513522215","https://openalex.org/W2586117383","https://openalex.org/W2602427488","https://openalex.org/W2705373224","https://openalex.org/W2757416441","https://openalex.org/W2786179895","https://openalex.org/W2795109282","https://openalex.org/W2810621157","https://openalex.org/W2892009249","https://openalex.org/W2912817604","https://openalex.org/W2917128112","https://openalex.org/W2938722449","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2965885792","https://openalex.org/W2973049979","https://openalex.org/W3016199006","https://openalex.org/W3045571807"],"related_works":["https://openalex.org/W3129799391","https://openalex.org/W3089863108","https://openalex.org/W3201101490","https://openalex.org/W3129824274","https://openalex.org/W2943008652","https://openalex.org/W3197163313","https://openalex.org/W3193714551","https://openalex.org/W3094947935","https://openalex.org/W2250628345","https://openalex.org/W3015747801","https://openalex.org/W3121299949","https://openalex.org/W2573694925","https://openalex.org/W3015522062","https://openalex.org/W2964161387","https://openalex.org/W3207222250","https://openalex.org/W3096587983","https://openalex.org/W3180374548","https://openalex.org/W3003335331","https://openalex.org/W3139663406","https://openalex.org/W2990273193"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,58],"explore":[4,59],"a":[5],"multimodal":[6,46,62],"semi-supervised":[7,137],"learning":[8,14,138],"approach":[9,83,139],"for":[10],"punctuation":[11],"prediction":[12],"by":[13,113,140],"representations":[15],"from":[16],"large":[17],"amounts":[18],"of":[19,48,136,147,155],"unlabelled":[20],"audio":[21],"and":[22,44,52,64,86,100,157],"text":[23,158],"data.":[24],"Conventional":[25],"approaches":[26],"in":[27],"speech":[28,156],"processing":[29],"typically":[30],"use":[31],"forced":[32,69],"alignment":[33,70],"to":[34,40,110,123],"encoder":[35],"per":[36],"frame":[37],"acoustic":[38,51],"features":[39,43],"word":[41],"level":[42],"perform":[45],"fusion":[47,63],"the":[49,76,93,107,134,148,160],"resulting":[50],"lexical":[53],"representations.":[54],"As":[55],"an":[56,124],"alternative,":[57],"attention":[60],"based":[61,71],"compare":[65],"its":[66],"performance":[67],"with":[68,117],"fusion.":[72],"Experiments":[73],"conducted":[74],"on":[75,97,128,144,152],"Fisher":[77],"corpus":[78],"show":[79],"that":[80],"our":[81],"proposed":[82,161],"achieves":[84,121],"~6-9%":[85],"~3-4%":[87],"absolute":[88,165],"improvement":[89,127,166],"(F1":[90],"score)":[91],"over":[92,167],"baseline":[94,168],"BLSTM":[95],"model":[96,108,162],"reference":[98],"transcripts":[99],"ASR":[101,111,129],"outputs":[102],"respectively.":[103],"We":[104,131],"further":[105],"improve":[106],"robustness":[109],"errors":[112],"performing":[114,141],"data":[115],"augmentation":[116],"N-best":[118],"lists":[119],"which":[120],"up":[122],"additional":[125],"~2-6%":[126],"outputs.":[130],"also":[132],"demonstrate":[133],"effectiveness":[135],"ablation":[142],"study":[143],"various":[145],"sizes":[146],"corpus.":[149],"When":[150],"trained":[151],"1":[153],"hour":[154],"data,":[159],"achieved":[163],"~9-18%":[164],"model.":[169]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}