{"id":"https://openalex.org/W2554080800","doi":"https://doi.org/10.1109/iccp.2016.7737141","title":"Improving sentence-level alignment of speech with imperfect transcripts using utterance concatenation and VAD","display_name":"Improving sentence-level alignment of speech with imperfect transcripts using utterance concatenation and VAD","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2554080800","doi":"https://doi.org/10.1109/iccp.2016.7737141","mag":"2554080800"},"language":"en","primary_location":{"id":"doi:10.1109/iccp.2016.7737141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccp.2016.7737141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 12th International Conference on Intelligent Computer Communication and Processing (ICCP)","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/A5076973065","display_name":"Alexandru Moldovan","orcid":"https://orcid.org/0009-0003-6541-9689"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Alexandru Moldovan","raw_affiliation_strings":["Communications Department, Technical University of Cluj-Napoca"],"affiliations":[{"raw_affiliation_string":"Communications Department, Technical University of Cluj-Napoca","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018126799","display_name":"Adriana Stan","orcid":"https://orcid.org/0000-0003-2894-5770"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Adriana Stan","raw_affiliation_strings":["Communications Department, Technical University of Cluj-Napoca"],"affiliations":[{"raw_affiliation_string":"Communications Department, Technical University of Cluj-Napoca","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038722127","display_name":"Mircea Giurgiu","orcid":"https://orcid.org/0009-0007-9789-6083"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Mircea Giurgiu","raw_affiliation_strings":["Communications Department, Technical University of Cluj-Napoca"],"affiliations":[{"raw_affiliation_string":"Communications Department, Technical University of Cluj-Napoca","institution_ids":["https://openalex.org/I158333966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076973065"],"corresponding_institution_ids":["https://openalex.org/I158333966"],"apc_list":null,"apc_paid":null,"fwci":0.4284,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79663493,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"171","last_page":"174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991000294685364,"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":0.9965000152587891,"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/concatenation","display_name":"Concatenation (mathematics)","score":0.9282276630401611},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8689451813697815},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.8377408981323242},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.768375039100647},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.665673553943634},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5385692119598389},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5385658740997314},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5309350490570068},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5020284652709961},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4848659932613373},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.466043621301651},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.46037277579307556},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.09422588348388672}],"concepts":[{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.9282276630401611},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8689451813697815},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8377408981323242},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.768375039100647},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.665673553943634},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5385692119598389},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5385658740997314},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5309350490570068},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5020284652709961},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4848659932613373},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.466043621301651},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.46037277579307556},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.09422588348388672},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccp.2016.7737141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccp.2016.7737141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 12th International Conference on Intelligent Computer Communication and Processing (ICCP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2533495","https://openalex.org/W10731371","https://openalex.org/W47863446","https://openalex.org/W85707815","https://openalex.org/W943204654","https://openalex.org/W1245895196","https://openalex.org/W1500331947","https://openalex.org/W1516533146","https://openalex.org/W1517939602","https://openalex.org/W1970101118","https://openalex.org/W2015412875","https://openalex.org/W2105961775","https://openalex.org/W2107457864","https://openalex.org/W2181715383","https://openalex.org/W2250270880","https://openalex.org/W6600088033","https://openalex.org/W6600436803","https://openalex.org/W6601956741","https://openalex.org/W6603477829","https://openalex.org/W6624852173","https://openalex.org/W6630961876","https://openalex.org/W6685955031","https://openalex.org/W6691459416"],"related_works":["https://openalex.org/W2373577936","https://openalex.org/W3095575180","https://openalex.org/W2389596151","https://openalex.org/W4221148444","https://openalex.org/W4226054107","https://openalex.org/W4387678054","https://openalex.org/W2529301793","https://openalex.org/W4306784355","https://openalex.org/W2384121599","https://openalex.org/W1998701884"],"abstract_inverted_index":{"Preparing":[0],"data":[1],"for":[2,47],"speech":[3,72],"processing":[4],"applications":[5],"is":[6,54,92,103],"in":[7,84],"general":[8],"a":[9,18,36,62,107],"task":[10],"which":[11,48,67],"requires":[12],"expert":[13],"knowledge":[14],"and":[15,127],"takes":[16],"up":[17],"large":[19,108],"amount":[20],"of":[21,42,45,80,110],"time.":[22],"Therefore,":[23],"being":[24],"able":[25],"to":[26,70],"automate":[27],"as":[28,30],"much":[29],"possible":[31],"this":[32,57,116],"process":[33],"can":[34,142],"have":[35],"significant":[37],"impact":[38],"on":[39,124,130],"the":[40,43,52,100,149],"expansion":[41],"number":[44,109],"languages":[46],"spoken":[49],"interaction":[50],"with":[51,73],"machines":[53],"available.":[55],"In":[56],"paper":[58],"we":[59,97,118],"build":[60],"upon":[61],"previously":[63],"developed":[64,69],"tool,":[65],"ALISA,":[66],"was":[68],"align":[71],"imperfect":[74],"transcripts":[75],"using":[76],"only":[77],"10":[78],"minutes":[79],"manually":[81],"labelled":[82],"data,":[83],"any":[85],"alphabetic":[86],"language.":[87],"Although":[88],"its":[89],"error":[90],"rate":[91],"around":[93,144],"0.6%":[94],"at":[95],"word-level,":[96],"noticed":[98],"that":[99,138],"sentence-level":[101],"accuracy":[102],"drastically":[104],"affected":[105],"by":[106],"sentence-initial":[111],"word":[112],"deletions.":[113],"To":[114],"overcome":[115],"problem,":[117],"propose":[119],"two":[120],"methods:":[121],"one":[122,128],"based":[123,129],"utterance":[125],"concatenation,":[126],"voice":[131],"activity":[132],"detection":[133],"(VAD).":[134],"The":[135],"results":[136],"show":[137],"these":[139],"simple":[140],"methods":[141],"achieve":[143],"10%":[145],"relative":[146],"improvement":[147],"over":[148],"baseline":[150],"results.":[151]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}