{"id":"https://openalex.org/W2659850037","doi":"https://doi.org/10.1109/icassp.2017.7953166","title":"Alternative networks for monolingual bottleneck features","display_name":"Alternative networks for monolingual bottleneck features","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2659850037","doi":"https://doi.org/10.1109/icassp.2017.7953166","mag":"2659850037"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5047770365","display_name":"William M. Hartmann","orcid":null},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Hartmann","raw_affiliation_strings":["Raytheon BBN Technologies, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Raytheon BBN Technologies, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033764781","display_name":"Roger Hsiao","orcid":"https://orcid.org/0000-0001-8638-4508"},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roger Hsiao","raw_affiliation_strings":["Raytheon BBN Technologies, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Raytheon BBN Technologies, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073006801","display_name":"Stavros Tsakalidis","orcid":null},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stavros Tsakalidis","raw_affiliation_strings":["Raytheon BBN Technologies, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Raytheon BBN Technologies, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1306686416"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":null,"first_page":"5290","last_page":"5294"},"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.8870847225189209},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8232991695404053},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6224960684776306},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6180458664894104},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.606907844543457},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5463207364082336},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.49618062376976013},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44566667079925537},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4173206686973572},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3827662765979767},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.23069339990615845}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8870847225189209},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8232991695404053},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6224960684776306},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6180458664894104},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.606907844543457},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5463207364082336},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.49618062376976013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44566667079925537},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4173206686973572},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3827662765979767},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.23069339990615845},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W98857008","https://openalex.org/W162588823","https://openalex.org/W1499864241","https://openalex.org/W1524333225","https://openalex.org/W1565198967","https://openalex.org/W1600744878","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1970890968","https://openalex.org/W1975550806","https://openalex.org/W1995562189","https://openalex.org/W2005708641","https://openalex.org/W2012897754","https://openalex.org/W2021167964","https://openalex.org/W2031804986","https://openalex.org/W2072349636","https://openalex.org/W2085628288","https://openalex.org/W2112739286","https://openalex.org/W2123237149","https://openalex.org/W2142694085","https://openalex.org/W2143612262","https://openalex.org/W2160815625","https://openalex.org/W2165712214","https://openalex.org/W2181607856","https://openalex.org/W2198724430","https://openalex.org/W2396672644","https://openalex.org/W2397947827","https://openalex.org/W2407922671","https://openalex.org/W2510459131","https://openalex.org/W2514805646","https://openalex.org/W2515737026","https://openalex.org/W2518591046","https://openalex.org/W2533125211","https://openalex.org/W6629930100","https://openalex.org/W6631362777","https://openalex.org/W6678292227","https://openalex.org/W6681071827","https://openalex.org/W6686045668","https://openalex.org/W6712271494","https://openalex.org/W6714027799"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138","https://openalex.org/W3013299381"],"abstract_inverted_index":{"While":[0],"recent":[1],"advances":[2],"in":[3,12,53],"deep":[4,89],"neural":[5],"networks":[6,41],"have":[7,16],"lead":[8],"to":[9,20,30,102],"significant":[10],"improvements":[11],"speech":[13],"recognition,":[14],"they":[15],"been":[17],"applied":[18],"mainly":[19],"acoustic":[21,49,111,120],"and":[22,37,47,56,75,91,96],"language":[23],"modeling.":[24],"We":[25],"instead":[26],"apply":[27],"the":[28,68,103],"models":[29],"bottleneck":[31,39],"feature":[32,40,57],"extraction.":[33],"Several":[34],"DNN,":[35],"CNN,":[36],"BLSTM-based":[38],"are":[42,59,62],"compared":[43,101],"using":[44,108,117],"both":[45,77],"DNN":[46,105,110],"BLSTM":[48,76,119],"models.":[50,121],"Multiple":[51],"variations":[52],"network":[54,86,106],"architecture":[55],"input":[58],"explored.":[60],"Results":[61],"reported":[63],"on":[64],"four":[65],"languages":[66],"from":[67],"IARPA":[69],"Babel":[70],"program.":[71],"The":[72,84],"shallow":[73],"CNN":[74,90],"improve":[78],"performance":[79],"by":[80,94,98],"a":[81,88,109],"similar":[82],"amount.":[83],"best":[85],"is":[87],"improves":[92],"WER":[93],"1.4%":[95],"ATWV":[97],"2%":[99],"absolute":[100],"baseline":[104],"when":[107,116],"model.":[112],"Relative":[113],"gains":[114],"hold":[115],"stronger":[118]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}