{"id":"https://openalex.org/W2044310744","doi":"https://doi.org/10.1109/espa.2012.6152444","title":"Improved parcel sorting by combining automatic speech and character recognition","display_name":"Improved parcel sorting by combining automatic speech and character recognition","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2044310744","doi":"https://doi.org/10.1109/espa.2012.6152444","mag":"2044310744"},"language":"en","primary_location":{"id":"doi:10.1109/espa.2012.6152444","doi":"https://doi.org/10.1109/espa.2012.6152444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/espa.2012.6152444","pdf_url":null,"source":{"id":"https://openalex.org/S7407113367","display_name":"IEEE International Conference on Emerging Signal Processing Applications (ESPA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Emerging Signal Processing Applications","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5074850775","display_name":"Amriteshwar Singh","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amriteshwar Singh","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), Department of Electrical Engineering, University of Texas at Dallas, Richardson, TX, USA","Center for Robust Speech Systems (CRSS), Department of Electrical Engineering, The University of Texas at Dallas, Richardson, Texas, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Department of Electrical Engineering, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Department of Electrical Engineering, The University of Texas at Dallas, Richardson, Texas, U.S.A","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111469714","display_name":"Abhijeet Sangwan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhijeet Sangwan","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), Department of Electrical Engineering, University of Texas at Dallas, Richardson, TX, USA","Center for Robust Speech Systems (CRSS), Department of Electrical Engineering, The University of Texas at Dallas, Richardson, Texas, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Department of Electrical Engineering, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Department of Electrical Engineering, The University of Texas at Dallas, Richardson, Texas, U.S.A","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), Department of Electrical Engineering, University of Texas at Dallas, Richardson, TX, USA","Center for Robust Speech Systems (CRSS), Department of Electrical Engineering, The University of Texas at Dallas, Richardson, Texas, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Department of Electrical Engineering, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Department of Electrical Engineering, The University of Texas at Dallas, Richardson, Texas, U.S.A","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.14898452,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"52","last_page":"55"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9984999895095825,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9984999895095825,"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/parcel-sorting","display_name":"parcel sorting","score":0.9670000076293945},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"optical character recognition","score":0.8019999861717224},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.9760000109672546},{"id":"https://openalex.org/keywords/multimodal-fusion","display_name":"multimodal fusion","score":0.9079999923706055},{"id":"https://openalex.org/keywords/levenshtein-distance","display_name":"Levenshtein distance","score":0.9990000128746033},{"id":"https://openalex.org/keywords/address-recognition","display_name":"address recognition","score":0.9340000152587891}],"concepts":[{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.886604905128479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8114483952522278},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.649949312210083},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.6453829407691956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5545006394386292},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4223731756210327},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.24215421080589294},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/espa.2012.6152444","doi":"https://doi.org/10.1109/espa.2012.6152444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/espa.2012.6152444","pdf_url":null,"source":{"id":"https://openalex.org/S7407113367","display_name":"IEEE International Conference on Emerging Signal Processing Applications (ESPA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Emerging Signal Processing Applications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W171088530","https://openalex.org/W1966070767","https://openalex.org/W2005008005","https://openalex.org/W2053101950","https://openalex.org/W2111643688","https://openalex.org/W2140902362","https://openalex.org/W2162272882"],"related_works":["https://openalex.org/W4414464326","https://openalex.org/W2142293706","https://openalex.org/W1973075426","https://openalex.org/W2316013181","https://openalex.org/W1514113192","https://openalex.org/W2006205543","https://openalex.org/W1964514397","https://openalex.org/W2166251458","https://openalex.org/W2169319923","https://openalex.org/W879720230"],"abstract_inverted_index":{"Automatic":[0],"postal":[1],"sorting":[2,41],"systems":[3,15],"have":[4],"traditionally":[5],"relied":[6],"on":[7,62,95,112,134],"optical":[8],"character":[9],"recognition":[10,46,156,189],"(OCR)":[11],"technology.":[12],"While":[13],"OCR":[14,50,64,75,92,97,114,127,170,182],"perform":[16],"well":[17],"for":[18,28,39],"flat":[19],"mail":[20],"items":[21],"such":[22],"as":[23],"envelopes,":[24],"the":[25,96,147],"performance":[26],"deteriorates":[27],"parcels.":[29,191],"In":[30],"this":[31],"study,":[32],"we":[33,81],"propose":[34],"a":[35,83,100,162],"new":[36],"multimodal":[37,58,149],"solution":[38,150],"parcel":[40],"which":[42,160],"combines":[43],"automatic":[44],"speech":[45,135],"(ASR)":[47],"technology":[48],"with":[49],"in":[51,140,190],"order":[52],"to":[53,90,186],"deliver":[54],"better":[55],"performance.":[56],"Our":[57,143],"approach":[59],"is":[60,104,132,161],"based":[61,88,111],"estimating":[63],"output":[65,73,115,119],"confidence,":[66],"and":[67,121,126,136,169,183],"then":[68],"optionally":[69],"using":[70],"ASR":[71,118,125,166,184],"system":[72,131],"when":[74],"results":[76],"show":[77,145],"low":[78],"confidence.":[79,93],"Particularly,":[80],"proposed":[82,130,148],"Levenshtein":[84],"edit":[85],"distance":[86],"(LED)":[87],"measure":[89],"compute":[91],"Based":[94],"confidence":[98],"measure,":[99],"dynamic":[101],"fusion":[102],"strategy":[103],"developed":[105],"that":[106,146,180],"forms":[107],"its":[108],"final":[109],"decision":[110],"(i)":[113],"alone,":[116,120],"(ii)":[117],"(iii)":[122],"combination":[123],"of":[124,158],"outputs.":[128],"The":[129],"evaluated":[133],"image":[137],"data":[138],"collected":[139],"real-world":[141],"conditions.":[142],"experiments":[144],"achieves":[151],"an":[152,177],"overall":[153],"zip":[154],"code":[155],"rate":[157],"90.2%,":[159],"substantial":[163],"improvement":[164],"over":[165],"alone":[167,171],"(81%)":[168],"(80.6%)":[172],"systems.":[173],"This":[174],"advancement":[175],"represents":[176],"important":[178],"contribution":[179],"leverages":[181],"technologies":[185],"improve":[187],"address":[188]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2016-06-24T00:00:00"}