{"id":"https://openalex.org/W3094841848","doi":"https://doi.org/10.21437/interspeech.2020-1873","title":"An Investigation of Phone-Based Subword Units for End-to-End Speech Recognition","display_name":"An Investigation of Phone-Based Subword Units for End-to-End Speech Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3094841848","doi":"https://doi.org/10.21437/interspeech.2020-1873","mag":"3094841848"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1873","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1873","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":"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/A5101432591","display_name":"Weiran Wang","orcid":"https://orcid.org/0009-0000-0843-707X"},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiran Wang","raw_affiliation_strings":["Salesforce Research 575 High St, Palo Alto, CA 94301, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce Research 575 High St, Palo Alto, CA 94301, USA","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085034441","display_name":"Guangsen Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guangsen Wang","raw_affiliation_strings":["Salesforce Research 575 High St, Palo Alto, CA 94301, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce Research 575 High St, Palo Alto, CA 94301, USA","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064970996","display_name":"Aadyot Bhatnagar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aadyot Bhatnagar","raw_affiliation_strings":["Salesforce Research 575 High St, Palo Alto, CA 94301, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce Research 575 High St, Palo Alto, CA 94301, USA","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040821130","display_name":"Yingbo Zhou","orcid":"https://orcid.org/0000-0001-6034-9667"},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingbo Zhou","raw_affiliation_strings":["Salesforce Research 575 High St, Palo Alto, CA 94301, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce Research 575 High St, Palo Alto, CA 94301, USA","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032046813","display_name":"Caiming Xiong","orcid":"https://orcid.org/0000-0003-0349-8628"},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Caiming Xiong","raw_affiliation_strings":["Salesforce Research 575 High St, Palo Alto, CA 94301, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce Research 575 High St, Palo Alto, CA 94301, USA","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059955534","display_name":"Richard Socher","orcid":"https://orcid.org/0000-0002-3577-639X"},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Socher","raw_affiliation_strings":["Salesforce Research 575 High St, Palo Alto, CA 94301, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce Research 575 High St, Palo Alto, CA 94301, USA","institution_ids":["https://openalex.org/I4210155268"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210155268"],"apc_list":null,"apc_paid":null,"fwci":3.2505,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.93538566,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1778","last_page":"1782"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9958000183105469,"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/T10860","display_name":"Speech and Audio Processing","score":0.9955999851226807,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.8563610315322876},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7383097410202026},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7188287973403931},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6404924392700195},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2440425157546997},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10106205940246582}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8563610315322876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7383097410202026},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7188287973403931},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6404924392700195},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2440425157546997},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10106205940246582},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1873","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1873","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1489125746","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1593247906","https://openalex.org/W1736701665","https://openalex.org/W1915251500","https://openalex.org/W2102113734","https://openalex.org/W2121879602","https://openalex.org/W2158069733","https://openalex.org/W2193413348","https://openalex.org/W2327501763","https://openalex.org/W2395416438","https://openalex.org/W2520160253","https://openalex.org/W2521999726","https://openalex.org/W2538246917","https://openalex.org/W2603679025","https://openalex.org/W2766219058","https://openalex.org/W2782451907","https://openalex.org/W2787663903","https://openalex.org/W2799800213","https://openalex.org/W2888884590","https://openalex.org/W2899879954","https://openalex.org/W2905263927","https://openalex.org/W2913041008","https://openalex.org/W2936774411","https://openalex.org/W2938348542","https://openalex.org/W2962760690","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2963303028","https://openalex.org/W2963414781","https://openalex.org/W2963979492","https://openalex.org/W2972437137","https://openalex.org/W2972451902","https://openalex.org/W2972818416","https://openalex.org/W3008912312","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2061937230"],"abstract_inverted_index":{"Phones":[0],"and":[1,18],"their":[2,22],"context-dependent":[3],"variants":[4],"have":[5,20],"been":[6],"the":[7,29,61,64,73,98,134,138],"standard":[8],"modeling":[9,41],"units":[10,42],"for":[11,24,43,158],"conventional":[12,83],"speech":[13,45,160],"recognition":[14,26,95],"systems,":[15],"while":[16,141],"characters":[17],"subwords":[19],"demonstrated":[21],"effectiveness":[23],"end-to-end":[25,44],"systems.We":[27],"investigate":[28],"use":[30,62],"of":[31,63,75,137],"phone-based":[32,88,124],"subwords,":[33],"in":[34],"particular,":[35],"byte":[36],"pair":[37],"encoder":[38],"(BPE),":[39],"as":[40],"recognition.In":[46],"addition,":[47,101],"we":[48],"also":[49],"developed":[50],"multi-level":[51],"language":[52],"model-based":[53],"decoding":[54,143,150],"algorithms":[55],"based":[56],"on":[57,133],"a":[58,108],"pronunciation":[59],"dictionary.Besides":[60],"lexicon,":[65],"which":[66,115],"is":[67],"easily":[68],"available,":[69],"our":[70,123],"system":[71,126],"avoids":[72],"need":[74],"additional":[76],"expert":[77],"knowledge":[78],"or":[79],"processing":[80],"steps":[81],"from":[82],"systems.Experimental":[84],"results":[85],"show":[86],"that":[87],"BPEs":[89],"tend":[90],"to":[91,152],"yield":[92],"more":[93],"accurate":[94],"systems":[96],"than":[97],"character-based":[99,119],"counterpart.In":[100],"further":[102],"improvement":[103],"can":[104],"be":[105],"obtained":[106],"with":[107],"novel":[109],"one-pass":[110],"joint":[111,142,149],"beam":[112],"search":[113],"decoder,":[114],"efficiently":[116],"combines":[117],"phone-and":[118],"BPE":[120,125],"systems.For":[121],"Switchboard,":[122,148],"achieves":[127,144],"6.8%/14.4%":[128],"word":[129],"error":[130],"rate":[131],"(WER)":[132],"Switchboard/CallHome":[135],"portion":[136],"test":[139],"set":[140],"6.3%/13.3%WER.On":[145],"Fisher":[146],"+":[147],"leads":[151],"4.9%/9.5%":[153],"WER,":[154],"setting":[155],"new":[156],"milestones":[157],"telephony":[159],"recognition.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}