{"id":"https://openalex.org/W2167799069","doi":"https://doi.org/10.21437/interspeech.2004-567","title":"Modeling auxiliary features in tandem systems","display_name":"Modeling auxiliary features in tandem systems","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W2167799069","doi":"https://doi.org/10.21437/interspeech.2004-567","mag":"2167799069"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-567","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://publications.idiap.ch/downloads/reports/2004/mathew-icslp2004.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043551083","display_name":"Mathew Magimai.-Doss","orcid":"https://orcid.org/0000-0002-8714-1409"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Mathew Magimai Doss","raw_affiliation_strings":["Dalle Molle Institute for Artificial Intelligence, CH-1920, Martigny, Switzerland","Swiss Federal Institute of Technology (EPFL), CH-1015, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Artificial Intelligence, CH-1920, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Swiss Federal Institute of Technology (EPFL), CH-1015, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053319645","display_name":"Shajith Ikbal","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Shajith Ikbal","raw_affiliation_strings":["Dalle Molle Institute for Artificial Intelligence, CH-1920, Martigny, Switzerland","Swiss Federal Institute of Technology (EPFL), CH-1015, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Artificial Intelligence, CH-1920, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Swiss Federal Institute of Technology (EPFL), CH-1015, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031924030","display_name":"Todd Andrew Stephenson","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Todd Stephenson","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA 15213, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]},{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Herv\u00e9 Bourlard","raw_affiliation_strings":["Dalle Molle Institute for Artificial Intelligence, CH-1920, Martigny, Switzerland","Swiss Federal Institute of Technology (EPFL), CH-1015, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Artificial Intelligence, CH-1920, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Swiss Federal Institute of Technology (EPFL), CH-1015, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5043551083"],"corresponding_institution_ids":["https://openalex.org/I2614128279","https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":1.8501,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88395895,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1501","last_page":"1504"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9984999895095825,"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":0.998199999332428,"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/computer-science","display_name":"Computer science","score":0.7917424440383911},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7468953132629395},{"id":"https://openalex.org/keywords/tandem","display_name":"Tandem","score":0.6959084868431091},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6703653335571289},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5786067843437195},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5615564584732056},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5325331687927246},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5132898688316345},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47535771131515503},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.46661844849586487},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0815773606300354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7917424440383911},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7468953132629395},{"id":"https://openalex.org/C2777814067","wikidata":"https://www.wikidata.org/wiki/Q1752317","display_name":"Tandem","level":2,"score":0.6959084868431091},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6703653335571289},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5786067843437195},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5615564584732056},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5325331687927246},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5132898688316345},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47535771131515503},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46661844849586487},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0815773606300354},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2004-567","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.tind.io:83034","is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/magimai04a","pdf_url":"http://publications.idiap.ch/downloads/reports/2004/mathew-icslp2004.pdf","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:83034","is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/magimai04a","pdf_url":"http://publications.idiap.ch/downloads/reports/2004/mathew-icslp2004.pdf","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference proceedings"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4699999988079071,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G3483739497","display_name":"MULTI: MULTImodal Interaction and MULTImedia Data Mining","funder_award_id":"68231","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G3904623476","display_name":null,"funder_award_id":"National Center of Competence in Research (NCCR)","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G6492990292","display_name":null,"funder_award_id":"National Center of Competence in Re","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320331353","display_name":"National Center of Competence in Research Chemical Biology","ror":"https://ror.org/033f9yy33"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2167799069.pdf","grobid_xml":"https://content.openalex.org/works/W2167799069.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W159349026","https://openalex.org/W175821084","https://openalex.org/W206778388","https://openalex.org/W1484387534","https://openalex.org/W1493898446","https://openalex.org/W1553004968","https://openalex.org/W1560013842","https://openalex.org/W1561787993","https://openalex.org/W2090861223","https://openalex.org/W2110575115","https://openalex.org/W2157225271","https://openalex.org/W2157240849","https://openalex.org/W2165712214","https://openalex.org/W2384542382"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2736574136","https://openalex.org/W2373675101","https://openalex.org/W2038216521","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W894828327","https://openalex.org/W2136559180"],"abstract_inverted_index":{"Tandem":[0],"systems":[1,40],"transform":[2],"the":[3,61,99,104,108,122,127,161,164],"cepstral":[4,42,50,134],"features":[5,23,51,106,135],"into":[6],"posterior":[7],"probabilities":[8],"of":[9,55,63,110,163],"subword":[10],"units":[11],"using":[12,41],"artificial":[13],"neural":[14],"networks":[15],"(ANNs),":[16],"which":[17,114],"are":[18],"processed":[19],"to":[20,33,58,74,87,118],"form":[21],"input":[22],"for":[24],"conventional":[25,37],"speech":[26,38,64,95],"recognition":[27,39,65,96,152],"systems.":[28,66],"They":[29],"have":[30,46],"been":[31],"shown":[32,47],"perform":[34],"better":[35],"than":[36],"features.":[43,144,173],"Recent":[44],"studies":[45,146],"that":[48,160],"modelling":[49],"with":[52,133,142],"auxiliary":[53,76,89,105,143,172],"sources":[54,78],"knowledge":[56,77],"leads":[57],"improvement":[59],"in":[60,91,107],"performance":[62,162],"In":[67,98,121],"this":[68],"paper,":[69],"we":[70,102,125],"study":[71],"two":[72],"approaches":[73],"incorporate":[75],"such":[79],"as":[80,88],"pitch":[81],"frequency,":[82],"short-term":[83],"energy,":[84],"etc.":[85],"(referred":[86],"features),":[90],"a":[92,149],"tandem-based":[93],"automatic":[94],"system.":[97],"first":[100],"approach,":[101,124],"model":[103,139],"process":[109],"training":[111],"an":[112,130],"ANN,":[113],"is":[115],"later":[116],"used":[117],"extract":[119,126],"tandem-features.":[120],"second":[123],"tandem-features":[128],"from":[129],"ANN":[131],"trained":[132],"only":[136],"and":[137,156],"then":[138],"them":[140],"jointly":[141],"Recognition":[145],"conducted":[147],"on":[148],"connected":[150],"word":[151],"task":[153],"under":[154],"clean":[155],"noisy":[157],"conditions":[158],"show":[159],"tandem":[165],"system":[166],"can":[167],"be":[168],"improved":[169],"by":[170],"incorporating":[171]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
