{"id":"https://openalex.org/W193119429","doi":"https://doi.org/10.21437/interspeech.2011-97","title":"Analysis and comparison of recent MLP features for LVCSR systems","display_name":"Analysis and comparison of recent MLP features for LVCSR systems","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W193119429","doi":"https://doi.org/10.21437/interspeech.2011-97","mag":"193119429"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-97","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-97","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/192685","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061495800","display_name":"Fabio Valente","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Fabio Valente","raw_affiliation_strings":["IDIAP research institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043551083","display_name":"Mathew Magimai.-Doss","orcid":"https://orcid.org/0000-0002-8714-1409"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mathew Magimai-Doss","raw_affiliation_strings":["IDIAP research institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100757620","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0002-5812-6744"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["SRI, International;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1245","last_page":"1248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9955000281333923,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9919999837875366,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8683373928070068},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.7576590776443481},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7147936820983887},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6746640801429749},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.650855302810669},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5757091641426086},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5453940033912659},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5090884566307068},{"id":"https://openalex.org/keywords/tandem","display_name":"Tandem","score":0.5090486407279968},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5088253617286682},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.45034804940223694},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41965189576148987},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.4157177209854126},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3517652153968811},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2755786180496216}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8683373928070068},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7576590776443481},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7147936820983887},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6746640801429749},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.650855302810669},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5757091641426086},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5453940033912659},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5090884566307068},{"id":"https://openalex.org/C2777814067","wikidata":"https://www.wikidata.org/wiki/Q1752317","display_name":"Tandem","level":2,"score":0.5090486407279968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5088253617286682},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.45034804940223694},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41965189576148987},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.4157177209854126},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3517652153968811},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2755786180496216},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2011-97","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-97","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.646.3750","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.646.3750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/papers/2011/Valente_INTERSPEECH_2011.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:192685","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192685","pdf_url":null,"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":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:192685","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192685","pdf_url":null,"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":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W30072984","https://openalex.org/W103244930","https://openalex.org/W1522045018","https://openalex.org/W1920478749","https://openalex.org/W2012897754","https://openalex.org/W2071489795","https://openalex.org/W2096215262","https://openalex.org/W2165712214","https://openalex.org/W2167513360","https://openalex.org/W2167763959"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W2373577936","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2888091758","https://openalex.org/W2134209752","https://openalex.org/W2163874654","https://openalex.org/W1494724239"],"abstract_inverted_index":{"MLP":[0],"based":[1],"front-ends":[2,103,130],"have":[3],"evolved":[4],"in":[5,8,86,124],"different":[6,32],"ways":[7],"re-cent":[9],"years":[10],"beyond":[11,48],"the":[12,29,38,49,55,65,119,132],"seminal":[13],"TANDEM-PLP":[14,112],"features.":[15],"This":[16],"paper":[17,56],"aims":[18],"at":[19],"providing":[20],"a":[21],"fair":[22],"comparison":[23],"of":[24,31,40,59,78,88],"these":[25,60],"recent":[26],"pro-gresses":[27],"including":[28],"use":[30,39],"long/short":[33],"temporal":[34],"in-puts":[35],"(PLP,MRASTA,wLP-TRAPS,DCT-TRAPS)":[36],"and":[37,82,92],"complex":[41],"architectures":[42],"(bottleneck,":[43],"hierarchy,":[44],"multistream)":[45],"that":[46,97],"go":[47],"conventional":[50,66],"three":[51],"layer":[52],"MLP.":[53],"Furthermore,":[54],"identifies":[57],"which":[58],"actually":[61],"provide":[62,154],"advantages":[63],"over":[64],"TANDEM-PLP.":[67,146],"The":[68,147],"investigation":[69],"is":[70],"car-ried":[71],"on":[72],"an":[73],"LVCSR":[74],"task":[75],"for":[76],"recognition":[77],"Mandarin":[79],"Broadcast":[80],"speech":[81],"results":[83],"are":[84],"analyzed":[85],"terms":[87],"Character":[89],"Error":[90],"Rate":[91],"phonetic":[93],"confusions.":[94],"Results":[95],"reveal":[96],"as":[98],"stand":[99],"alone":[100],"features,":[101,128],"multistream":[102],"can":[104],"outperform":[105],"by":[106,115,136],"10":[107],"%":[108,138,143],"con-ventional":[109],"MFCC":[110,127],"while":[111],"only":[113],"improve":[114],"1":[116],"%.":[117],"On":[118],"other":[120],"hand,":[121],"when":[122],"used":[123],"concatenation":[125],"with":[126],"hierarchical/bottleneck":[129],"reduce":[131],"character":[133],"error":[134],"rate":[135],"+18":[137],"relative":[139,144],"compared":[140],"to":[141],"+14":[142],"from":[145],"various":[148],"input":[149],"long-term":[150],"representations":[151],"re-cently":[152],"developed":[153],"comparable":[155],"performances.":[156]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}