{"id":"https://openalex.org/W4323536975","doi":"https://doi.org/10.1145/3568294.3580129","title":"Utilizing Prior Knowledge to Improve Automatic Speech Recognition in Human-Robot Interactive Scenarios","display_name":"Utilizing Prior Knowledge to Improve Automatic Speech Recognition in Human-Robot Interactive Scenarios","publication_year":2023,"publication_date":"2023-03-08","ids":{"openalex":"https://openalex.org/W4323536975","doi":"https://doi.org/10.1145/3568294.3580129"},"language":"en","primary_location":{"id":"doi:10.1145/3568294.3580129","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3568294.3580129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2023 ACM/IEEE International Conference on Human-Robot Interaction","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/A5066673544","display_name":"Pradip Pramanick","orcid":"https://orcid.org/0000-0002-0897-1835"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pradip Pramanick","raw_affiliation_strings":["TCS Research, Kolkata, India"],"raw_orcid":"https://orcid.org/0000-0002-0897-1835","affiliations":[{"raw_affiliation_string":"TCS Research, Kolkata, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045560127","display_name":"Chayan Sarkar","orcid":"https://orcid.org/0000-0003-4777-2086"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chayan Sarkar","raw_affiliation_strings":["TCS Research, Kolkata, India"],"raw_orcid":"https://orcid.org/0000-0003-4777-2086","affiliations":[{"raw_affiliation_string":"TCS Research, Kolkata, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5066673544"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3408,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62904312,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"471","last_page":"475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987000226974487,"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/T12031","display_name":"Speech and dialogue systems","score":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.8363480567932129},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7218048572540283},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6036868095397949},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5758600831031799},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5611128807067871},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5454218983650208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.540018618106842},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5340067148208618},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.4750785231590271},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46949151158332825},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.46796637773513794},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.45824524760246277},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.4384111166000366},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.43765169382095337},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.42816779017448425},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.41581523418426514},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35125958919525146}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8363480567932129},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7218048572540283},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6036868095397949},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5758600831031799},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5611128807067871},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5454218983650208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.540018618106842},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5340067148208618},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.4750785231590271},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46949151158332825},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.46796637773513794},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.45824524760246277},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.4384111166000366},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.43765169382095337},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.42816779017448425},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.41581523418426514},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35125958919525146},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3568294.3580129","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3568294.3580129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2023 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2099739380","https://openalex.org/W2531638282","https://openalex.org/W2593216051","https://openalex.org/W2889012072","https://openalex.org/W2914304175","https://openalex.org/W2963240019","https://openalex.org/W2972625221","https://openalex.org/W3000554245","https://openalex.org/W3004090558","https://openalex.org/W3022882149","https://openalex.org/W3034758614","https://openalex.org/W3100351271","https://openalex.org/W3103391829","https://openalex.org/W3112188842","https://openalex.org/W3116544769","https://openalex.org/W3131210852","https://openalex.org/W3135282443","https://openalex.org/W3182074706","https://openalex.org/W3198004110","https://openalex.org/W3211278025","https://openalex.org/W3216418166","https://openalex.org/W4294871822"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W2004087835","https://openalex.org/W2314871050"],"abstract_inverted_index":{"The":[0],"prolificacy":[1],"of":[2,18,54],"human-robot":[3],"interaction":[4],"not":[5],"only":[6],"depends":[7],"on":[8,51],"a":[9,76,95],"robot's":[10],"ability":[11],"to":[12,62,75],"understand":[13],"the":[14,19,27,44,52,55,81,84],"intent":[15],"and":[16,40],"content":[17],"human":[20],"utterance":[21],"but":[22],"also":[23],"gets":[24],"impacted":[25],"by":[26,57,80],"automatic":[28],"speech":[29],"recognition":[30],"(ASR)":[31],"system.":[32],"Modern":[33],"ASR":[34,47,65,109,122],"can":[35,67,73,105,119],"provide":[36],"highly":[37],"accurate":[38],"(grammatically":[39],"syntactically)":[41],"translation.":[42],"Yet,":[43],"general":[45],"purpose":[46],"often":[48],"misses":[49],"out":[50],"semantics":[53],"translation":[56,123],"incorrect":[58],"word":[59],"prediction":[60],"due":[61],"open-vocabulary":[63],"modeling.":[64],"inaccuracy":[66],"have":[68],"significant":[69],"repercussions":[70],"as":[71],"this":[72,98],"lead":[74],"completely":[77],"different":[78],"action":[79],"robot":[82],"in":[83,93,108],"real":[85],"world.":[86],"Can":[87],"any":[88],"prior":[89,103],"knowledge":[90,104],"be":[91,106],"helpful":[92],"such":[94],"scenario?":[96],"In":[97],"work,":[99],"we":[100,114],"explore":[101],"how":[102,116],"utilized":[107],"decoding.":[110],"Using":[111],"our":[112,117],"experiments,":[113],"demonstrate":[115],"system":[118],"significantly":[120],"improve":[121],"for":[124],"robotic":[125],"task":[126],"instruction.":[127]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
