{"id":"https://openalex.org/W2993042001","doi":"https://doi.org/10.1109/bigmm.2019.00-26","title":"Automatic Speech Recognition for Real Time Systems","display_name":"Automatic Speech Recognition for Real Time Systems","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2993042001","doi":"https://doi.org/10.1109/bigmm.2019.00-26","mag":"2993042001"},"language":"en","primary_location":{"id":"doi:10.1109/bigmm.2019.00-26","doi":"https://doi.org/10.1109/bigmm.2019.00-26","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigmm.2019.00-26","pdf_url":null,"source":{"id":"https://openalex.org/S4306422666","display_name":"IEEE International Conference on Multimedia Big Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Fifth International Conference on Multimedia Big Data (BigMM)","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/A5070060944","display_name":"Ranjodh Singh","orcid":"https://orcid.org/0000-0002-3651-5415","observed_orcids":["https://orcid.org/0000-0002-3651-5415"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ranjodh Singh","raw_affiliation_strings":["Humonics Global Pvt. Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Humonics Global Pvt. Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003400894","display_name":"Hemant N. Yadav","orcid":"https://orcid.org/0000-0003-3057-1456","observed_orcids":["https://orcid.org/0000-0003-3057-1456"]},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant Yadav","raw_affiliation_strings":["MIDAS Lab, IIIT, Delhi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIDAS Lab, IIIT, Delhi","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013833501","display_name":"Mohit Sharma","orcid":"https://orcid.org/0000-0002-6045-9716","observed_orcids":["https://orcid.org/0000-0002-6045-9716","https://orcid.org/0000-0003-1924-6222"]},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mohit Sharma","raw_affiliation_strings":["MIDAS Lab, IIIT, Delhi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIDAS Lab, IIIT, Delhi","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049434280","display_name":"Sandeep Gosain","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sandeep Gosain","raw_affiliation_strings":["Humonics Global Pvt. Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Humonics Global Pvt. Ltd","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079357056","display_name":"Rajiv Ratn Shah","orcid":"https://orcid.org/0000-0003-1028-9373","observed_orcids":["https://orcid.org/0000-0003-1028-9373"]},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajiv Ratn Shah","raw_affiliation_strings":["MIDAS Lab, IIIT, Delhi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIDAS Lab, IIIT, Delhi","institution_ids":["https://openalex.org/I119939252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2868,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.58334302,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"189","last_page":"198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T12031","display_name":"Speech and dialogue systems","score":0.0,"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":0.0,"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/speech-recognition","display_name":"speech recognition","score":0.9940000176429749},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"domain adaptation","score":0.7749999761581421},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.7559999823570251},{"id":"https://openalex.org/keywords/limited-training-data","display_name":"limited training data","score":0.6119999885559082},{"id":"https://openalex.org/keywords/voice-commands","display_name":"voice commands","score":0.6660000085830688},{"id":"https://openalex.org/keywords/interactive-voice-response","display_name":"interactive voice response","score":0.5899999737739563},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"word error rate","score":0.8169999718666077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8206875324249268},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7466834187507629},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6705657243728638},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6274648904800415},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6014806032180786},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5051851868629456},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.49054330587387085},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.45606696605682373},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.44020721316337585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4228101968765259},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34467431902885437},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3136129379272461},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigmm.2019.00-26","doi":"https://doi.org/10.1109/bigmm.2019.00-26","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigmm.2019.00-26","pdf_url":null,"source":{"id":"https://openalex.org/S4306422666","display_name":"IEEE International Conference on Multimedia Big Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Fifth International Conference on Multimedia Big Data (BigMM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W179875071","https://openalex.org/W182831726","https://openalex.org/W1494198834","https://openalex.org/W1498436455","https://openalex.org/W1524333225","https://openalex.org/W1553469512","https://openalex.org/W1565144712","https://openalex.org/W1631260214","https://openalex.org/W1710082047","https://openalex.org/W1877570817","https://openalex.org/W1922655562","https://openalex.org/W1924770834","https://openalex.org/W1999965501","https://openalex.org/W2002342963","https://openalex.org/W2047481787","https://openalex.org/W2064675550","https://openalex.org/W2090861223","https://openalex.org/W2102113734","https://openalex.org/W2116777898","https://openalex.org/W2125529971","https://openalex.org/W2125838338","https://openalex.org/W2127141656","https://openalex.org/W2130131176","https://openalex.org/W2145077480","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2293634267","https://openalex.org/W2580662672","https://openalex.org/W2584271190","https://openalex.org/W2587486463","https://openalex.org/W2892490883","https://openalex.org/W2899771611","https://openalex.org/W2963435138","https://openalex.org/W6629815555"],"related_works":["https://openalex.org/W2765889516","https://openalex.org/W3107474891","https://openalex.org/W2415731916","https://openalex.org/W2778699561","https://openalex.org/W1445015017","https://openalex.org/W2920938200","https://openalex.org/W4280550577","https://openalex.org/W2783208898","https://openalex.org/W2898044248","https://openalex.org/W2767097019"],"abstract_inverted_index":{"Automatic":[0],"Speech":[1],"Recognition":[2],"(ASR)":[3],"systems":[4,23,77],"have":[5],"proven":[6],"to":[7,12,16,32,56,70,131],"be":[8,33],"a":[9],"useful":[10],"tool":[11],"perform":[13,71],"various":[14],"day":[15,17],"operations":[18],"when":[19],"used":[20],"along":[21],"with":[22,52,99],"like":[24],"Personal":[25],"AI":[26],"Assistants.":[27],"Various":[28],"industries":[29],"require":[30],"ASR":[31,94],"trained":[34,78],"in":[35,85],"their":[36],"domains.":[37],"Music":[38],"on":[39,73,79,106,115],"Demand":[40],"(MoD),":[41],"over":[42],"IVR,":[43],"is":[44,68],"one":[45],"such":[46],"industry":[47],"where":[48],"the":[49,53,66,93,100,112,126],"user":[50],"interacts":[51],"dialogue":[54],"system":[55],"play":[57],"music":[58],"using":[59],"voice":[60],"commands":[61],"only.":[62],"Domain":[63],"adaptation":[64],"of":[65,125],"model":[67,114],"expected":[69],"well":[72],"this":[74],"domain":[75],"as":[76],"public":[80],"datasets":[81],"are":[82],"very":[83,89,119],"generic":[84],"nature":[86],"and":[87,104,122],"not":[88],"domain-specific.":[90],"To":[91],"train":[92],"for":[95],"MoD,":[96],"we":[97,128],"experiment":[98],"HMM-based":[101],"classical":[102],"approach":[103],"DeepSpeech2":[105,113],"Voxforge":[107],"dataset.":[108],"We":[109],"then":[110],"fine-tune":[111],"MoD":[116],"data.":[117],"With":[118],"limited":[120],"data":[121],"little":[123],"finetuning":[124],"model,":[127],"were":[129],"able":[130],"achieve":[132],"14.727%":[133],"Word":[134],"Error":[135],"Rate":[136],"(WER).":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}