{"id":"https://openalex.org/W2886269827","doi":"https://doi.org/10.21437/interspeech.2011-407","title":"Continuous digits recognition leveraging invariant structure","display_name":"Continuous digits recognition leveraging invariant structure","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2886269827","doi":"https://doi.org/10.21437/interspeech.2011-407","mag":"2886269827"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-407","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},"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/A5028421346","display_name":"Masayuki Suzuki","orcid":"https://orcid.org/0000-0002-0436-1490"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masayuki Suzuki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021294422","display_name":"Gakuto Kurata","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gakuto Kurata","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083574298","display_name":"Masafumi Nishimura","orcid":"https://orcid.org/0000-0001-7633-9340"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masafumi Nishimura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"993","last_page":"996"},"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":0.9983999729156494,"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/T11309","display_name":"Music and Audio Processing","score":0.9965000152587891,"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/phone","display_name":"Phone","score":0.7574959993362427},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7411492466926575},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.7407776713371277},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7238450646400452},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6294249892234802},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5249122381210327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4369964897632599},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4187925457954407},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.331768274307251},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19672900438308716},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06626278162002563}],"concepts":[{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7574959993362427},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7411492466926575},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.7407776713371277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7238450646400452},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6294249892234802},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5249122381210327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4369964897632599},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4187925457954407},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.331768274307251},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19672900438308716},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06626278162002563},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2011-407","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.799.6374","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.799.6374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gavo.t.u-tokyo.ac.jp/%7Emine/paper/PDF/2011/INTERSPEECH_p993-996_t2011-8.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W281219303","https://openalex.org/W2098318492","https://openalex.org/W2124445791","https://openalex.org/W2151381157","https://openalex.org/W2156172072","https://openalex.org/W2164805947","https://openalex.org/W2410473521","https://openalex.org/W2945341140"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W2153098279","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861"],"abstract_inverted_index":{"Recently,":[0],"an":[1],"invariant":[2,23,66,92],"structure":[3,67],"of":[4,118],"speech":[5,46],"was":[6,25,51],"proposed,":[7],"where":[8],"the":[9,32,39,65,100,122],"inevitable":[10],"acoustic":[11],"variations":[12],"caused":[13],"by":[14,103],"non-linguistic":[15],"fac-tors":[16],"are":[17],"effectively":[18],"removed":[19],"from":[20],"speech.":[21],"The":[22],"struc-ture":[24],"applied":[26],"to":[27,44,63,82],"isolated":[28],"word":[29],"recognition":[30,47],"and":[31,98],"experi-mental":[33],"results":[34,112],"showed":[35],"good":[36],"performance.":[37],"However,":[38],"pre-vious":[40],"method":[41,62],"can\u2019t":[42],"apply":[43],"continuous":[45,69],"di-rectly":[48],"because":[49],"there":[50],"no":[52],"efficient":[53],"decoding":[54],"algorithm.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59,90],"propose":[60],"a":[61,74,114],"leverage":[64],"in":[68],"digits":[70],"recognition.":[71],"We":[72],"use":[73],"traditional":[75],"HMM-based":[76,124],"Automatic":[77],"Speech":[78],"Recognition":[79],"(ASR)":[80],"system":[81],"get":[83],"N-best":[84,101],"lists":[85,102],"with":[86],"phone":[87,96],"alignments.":[88],"Then":[89],"construct":[91],"structures":[93],"using":[94],"these":[95],"alignments":[97],"re-rank":[99],"investigating":[104],"which":[105],"hypothesis":[106],"is":[107],"structurally":[108],"more":[109],"valid.":[110],"Experimental":[111],"show":[113],"relative":[115],"WER":[116],"improvement":[117],"17.4":[119],"%":[120],"over":[121],"baseline":[123],"ASR":[125],"system.":[126]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}