{"id":"https://openalex.org/W2552023628","doi":"https://doi.org/10.1109/spcom.2016.7746673","title":"Analysis of hierarchical bottleneck framework for improved phoneme recognition","display_name":"Analysis of hierarchical bottleneck framework for improved phoneme recognition","publication_year":2016,"publication_date":"2016-06-01","ids":{"openalex":"https://openalex.org/W2552023628","doi":"https://doi.org/10.1109/spcom.2016.7746673","mag":"2552023628"},"language":"en","primary_location":{"id":"doi:10.1109/spcom.2016.7746673","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom.2016.7746673","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on Signal Processing and Communications (SPCOM)","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/A5022610118","display_name":"Mohammadi Zaki","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Mohammadi Zaki","raw_affiliation_strings":["Indian Institute of Science (IISc), Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science (IISc), Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030912143","display_name":"Hardik B. Sailor","orcid":"https://orcid.org/0000-0001-6872-5153"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani Institute of Information and Communication Technology","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hardik B. Sailor","raw_affiliation_strings":["Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar, India"],"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043002276","display_name":"Hemant A. Patil","orcid":"https://orcid.org/0000-0002-4068-2005"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani Institute of Information and Communication Technology","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant A. Patil","raw_affiliation_strings":["Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, Gujarat, IN"],"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, Gujarat, IN","institution_ids":["https://openalex.org/I98389781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022610118"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07928528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"69","issue":null,"first_page":"1","last_page":"5"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/bottleneck","display_name":"Bottleneck","score":0.9566503763198853},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8661993741989136},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7726539373397827},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5961884260177612},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5821338295936584},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5396282076835632},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.42932796478271484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4079035818576813},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38656172156333923},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.27531808614730835}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.9566503763198853},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8661993741989136},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7726539373397827},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5961884260177612},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5821338295936584},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5396282076835632},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.42932796478271484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4079035818576813},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38656172156333923},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27531808614730835},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/spcom.2016.7746673","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom.2016.7746673","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on Signal Processing and Communications (SPCOM)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.iisc.ac.in:56161","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196309","display_name":"NOT FOUND REPOSITORY (Indian Institute of Science Bangalore)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceedings"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W169882265","https://openalex.org/W190289757","https://openalex.org/W811578723","https://openalex.org/W1508165687","https://openalex.org/W1524333225","https://openalex.org/W1553004968","https://openalex.org/W1975138161","https://openalex.org/W2012897754","https://openalex.org/W2016084804","https://openalex.org/W2072349636","https://openalex.org/W2077804127","https://openalex.org/W2095635231","https://openalex.org/W2100932383","https://openalex.org/W2103372210","https://openalex.org/W2125534887","https://openalex.org/W2132196975","https://openalex.org/W2146194791","https://openalex.org/W2165712214","https://openalex.org/W2167458787","https://openalex.org/W2187089797","https://openalex.org/W6606983177","https://openalex.org/W6607679263","https://openalex.org/W6631362777","https://openalex.org/W6653316155","https://openalex.org/W6674924752"],"related_works":["https://openalex.org/W3134920593","https://openalex.org/W2153098279","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W36113703","https://openalex.org/W2340308015","https://openalex.org/W2413040788"],"abstract_inverted_index":{"In":[0,28,115],"this":[1,88,133],"paper,":[2],"an":[3],"attempt":[4],"is":[5],"made":[6],"to":[7,67,78],"examine":[8],"and":[9,15,32,50,97],"evaluate":[10],"the":[11,16,30,84,90],"effect":[12],"of":[13,47,124],"bottleneck":[14,18,31,34,51],"hierarchical":[17,33,49],"(HBN)":[19],"framework":[20,35,106],"in":[21,59,102,122],"MLP-based":[22],"Automatic":[23],"Speech":[24],"Recognition":[25,62],"(ASR)":[26],"systems.":[27],"particular,":[29],"are":[36,53,93,100],"analyzed":[37],"using":[38],"Volterra":[39],"series.":[40],"Experiments":[41],"on":[42,111,128],"several":[43],"architectures":[44,81],"with":[45,107,132],"incorporation":[46],"systematic":[48],"properties":[52],"done.":[54],"We":[55],"obtain":[56],"significant":[57],"increase":[58],"%":[60,109,130],"Phone":[61],"Accuracy":[63],"(PRA)":[64],"as":[65,83],"compared":[66],"traditional":[68],"cepstral":[69],"features":[70,99],"based":[71],"Hidden":[72],"Markov":[73],"Model":[74],"(HMM)":[75],"acoustic":[76,98],"modeling":[77],"more":[79],"complex":[80],"such":[82],"HBN":[85,105],"framework.":[86],"To":[87],"extent,":[89],"best":[91],"results":[92],"achieved":[94],"when":[95],"tandem":[96],"combined":[101],"a":[103,119],"deep":[104],"73.72":[108],"PRA":[110,131],"entire":[112],"TIMIT":[113],"database.":[114],"addition,":[116],"we":[117],"observe":[118],"relative":[120],"drop":[121],"dependence":[123],"language":[125],"model":[126],"(LM)":[127],"final":[129],"proposed":[134],"architecture.":[135]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}