{"id":"https://openalex.org/W3198587774","doi":"https://doi.org/10.21437/interspeech.2021-1860","title":"SPGISpeech: 5,000 Hours of Transcribed Financial Audio for Fully Formatted End-to-End Speech Recognition","display_name":"SPGISpeech: 5,000 Hours of Transcribed Financial Audio for Fully Formatted End-to-End Speech Recognition","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198587774","doi":"https://doi.org/10.21437/interspeech.2021-1860","mag":"3198587774"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1860","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.02014.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005325892","display_name":"Patrick O\u2019Neill","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Patrick K. O\u2019Neill","raw_affiliation_strings":["Kensho Technologies, Cambridge MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kensho Technologies, Cambridge MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026088310","display_name":"Vitaly Lavrukhin","orcid":"https://orcid.org/0009-0006-7866-8301"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vitaly Lavrukhin","raw_affiliation_strings":["NVIDIA Technologies, Santa Clara CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Technologies, Santa Clara CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027823948","display_name":"Somshubra Majumdar","orcid":"https://orcid.org/0000-0001-5635-4893"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Somshubra Majumdar","raw_affiliation_strings":["NVIDIA Technologies, Santa Clara CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Technologies, Santa Clara CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005843015","display_name":"Vahid Noroozi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vahid Noroozi","raw_affiliation_strings":["NVIDIA Technologies, Santa Clara CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Technologies, Santa Clara CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074415592","display_name":"Yuekai Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuekai Zhang","raw_affiliation_strings":["Johns Hopkins University, Baltimore MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048403564","display_name":"Oleksii Kuchaiev","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oleksii Kuchaiev","raw_affiliation_strings":["NVIDIA Technologies, Santa Clara CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Technologies, Santa Clara CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040747392","display_name":"Jagadeesh Balam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jagadeesh Balam","raw_affiliation_strings":["NVIDIA Technologies, Santa Clara CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Technologies, Santa Clara CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085808471","display_name":"Yuliya Dovzhenko","orcid":"https://orcid.org/0000-0001-8345-6422"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuliya Dovzhenko","raw_affiliation_strings":["Kensho Technologies, Cambridge MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kensho Technologies, Cambridge MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089791575","display_name":"Keenan Freyberg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keenan Freyberg","raw_affiliation_strings":["Kensho Technologies, Cambridge MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kensho Technologies, Cambridge MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029018277","display_name":"Michael D. Shulman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael D. Shulman","raw_affiliation_strings":["Kensho Technologies, Cambridge MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kensho Technologies, Cambridge MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032957280","display_name":"Boris Ginsburg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":["NVIDIA Technologies, Santa Clara CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Technologies, Santa Clara CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Johns Hopkins University, Baltimore MD, USA","Carnegie Mellon University, Pittsburgh PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033043101","display_name":"Georg Kucsko","orcid":"https://orcid.org/0000-0002-4189-3154"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georg Kucsko","raw_affiliation_strings":["Kensho Technologies, Cambridge MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kensho Technologies, Cambridge MA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005325892"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1434","last_page":"1438"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9940999746322632,"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":0.9923999905586243,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.6976064443588257},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6521821022033691},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6304625272750854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1848827600479126}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6976064443588257},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6521821022033691},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6304625272750854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1848827600479126}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2021-1860","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"mag:3143186397","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2104.02014.pdf","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}],"best_oa_location":{"id":"mag:3143186397","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2104.02014.pdf","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},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W1995562189","https://openalex.org/W2101926813","https://openalex.org/W2166637769","https://openalex.org/W2189162242","https://openalex.org/W2297949011","https://openalex.org/W2404126548","https://openalex.org/W2406343628","https://openalex.org/W2741483887","https://openalex.org/W2749051922","https://openalex.org/W2880875857","https://openalex.org/W2963250244","https://openalex.org/W2974231335","https://openalex.org/W3011222885","https://openalex.org/W3015752032","https://openalex.org/W3023256384","https://openalex.org/W3030437843","https://openalex.org/W3097777922","https://openalex.org/W3101648800","https://openalex.org/W3153592532","https://openalex.org/W3160789530","https://openalex.org/W4287120025","https://openalex.org/W4295276571","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W3196421258","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2151749779","https://openalex.org/W2382290278","https://openalex.org/W2938107654"],"abstract_inverted_index":{"In":[0],"the":[1,51,98,104],"English":[2],"speech-to-text":[3],"(STT)":[4],"machine":[5],"learning":[6],"task,":[7],"acoustic":[8,52],"models":[9,77],"are":[10],"conventionally":[11],"trained":[12,78],"on":[13,79],"uncased":[14],"Latin":[15],"characters,":[16],"and":[17,25,38],"any":[18],"necessary":[19],"orthography":[20],"(such":[21],"as":[22,41],"capitalization,":[23],"punctuation,":[24],"denormalization":[26],"of":[27,82,85,93],"non-standard":[28],"words)":[29],"is":[30],"imputed":[31],"by":[32],"separate":[33],"post-processing":[34],"models.This":[35],"adds":[36],"complexity":[37],"limits":[39],"performance,":[40],"many":[42],"formatting":[43],"tasks":[44],"benefit":[45],"from":[46],"semantic":[47],"information":[48],"present":[49,74],"in":[50,56],"signal":[53],"but":[54],"absent":[55],"transcription.Here":[57],"we":[58,102],"propose":[59],"a":[60,80,91,95],"new":[61],"STT":[62,99],"task:":[63],"endto-end":[64],"neural":[65],"transcription":[66],"with":[67],"fully":[68],"formatted":[69],"text":[70],"for":[71,107],"target":[72],"labels.We":[73],"baseline":[75],"Conformer-based":[76],"corpus":[81,105],"5,000":[83],"hours":[84],"professionally":[86],"transcribed":[87],"earnings":[88],"calls,":[89],"achieving":[90],"CER":[92],"1.7.As":[94],"contribution":[96],"to":[97],"research":[100],"community,":[101],"release":[103],"free":[106],"noncommercial":[108],"use.":[109],"1":[110]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}
