{"id":"https://openalex.org/W2747078529","doi":"https://doi.org/10.21437/interspeech.2017-1064","title":"Frame and Segment Level Recurrent Neural Networks for Phone Classification","display_name":"Frame and Segment Level Recurrent Neural Networks for Phone Classification","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2747078529","doi":"https://doi.org/10.21437/interspeech.2017-1064","mag":"2747078529"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1064","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/A5024388037","display_name":"Martin Ratajczak","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Martin Ratajczak","raw_affiliation_strings":["Institute of Signal Processing and Speech Communication (4420)"],"affiliations":[{"raw_affiliation_string":"Institute of Signal Processing and Speech Communication (4420)","institution_ids":["https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051794439","display_name":"Sebastian Tschiatschek","orcid":"https://orcid.org/0000-0002-2592-0108"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sebastian Tschiatschek","raw_affiliation_strings":["Microsoft Research#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research#TAB#","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015798259","display_name":"Franz Pernkopf","orcid":"https://orcid.org/0000-0002-6356-3367"},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Franz Pernkopf","raw_affiliation_strings":["Institute of Signal Processing and Speech Communication (4420)"],"affiliations":[{"raw_affiliation_string":"Institute of Signal Processing and Speech Communication (4420)","institution_ids":["https://openalex.org/I4210121626"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5024388037"],"corresponding_institution_ids":["https://openalex.org/I4210121626"],"apc_list":null,"apc_paid":null,"fwci":0.7801,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79380962,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1318","last_page":"1322"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9980999827384949,"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":0.9970999956130981,"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/recurrent-neural-network","display_name":"Recurrent neural network","score":0.8301472067832947},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8254286050796509},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.7015461325645447},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6424033045768738},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6253963112831116},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.6067515015602112},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5762622952461243},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5114740133285522},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4858393371105194},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47525784373283386},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.46959415078163147},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.45547863841056824},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41923922300338745},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.416140079498291},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36174142360687256},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06638133525848389}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8301472067832947},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8254286050796509},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.7015461325645447},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6424033045768738},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6253963112831116},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.6067515015602112},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5762622952461243},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5114740133285522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4858393371105194},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47525784373283386},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.46959415078163147},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.45547863841056824},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41923922300338745},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.416140079498291},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36174142360687256},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06638133525848389},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2017-1064","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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/W80018097"],"abstract_inverted_index":{"We":[0],"introduce":[2],"a":[4,107,125],"simple":[6],"and":[8,14],"efficient":[10],"frame":[12,69,86],"segment":[16,77],"levelRNN":[18],"model":[20,133],"(FS-RNN)":[22],"for":[23,130],"phone":[25,121],"classification.":[27],"It":[30],"processesthe":[31],"input":[32,67,75],"atframe":[33],"levelandsegment":[34],"levelby":[35],"bidirectional":[36],"gatedRNNs.":[37],"This":[41],"type":[43,105],"of":[45,85,94],"processing":[47],"is":[49],"important":[51],"to":[53],"exploit":[55],"the(temporal)":[57],"information":[58],"more":[59],"effectively":[60],"compared":[61],"to(i)mod-els":[62],"which":[63,72],"solely":[64],"process":[65,73],"the":[66,74,92,95,99,119,131,137,144],"at":[68],"level":[70,78,87],"and(ii)mod-els":[71],"on":[76,118],"using":[79],"features":[80],"ob-tained":[81],"by":[82],"heuristic":[83],"aggregation":[84],"features.":[88],"Further-more,":[89],"we":[90,114,141],"incorporated":[91],"activations":[93],"last":[96],"hidden":[97],"layerof":[98],"FS-RNN":[100,132],"as":[101],"an":[102],"additional":[103],"feature":[104],"in":[106],"neural":[108],"higher-order":[109],"CRF":[110],"(NHO-CRF).":[111],"In":[112],"experiments,":[113],"demonstrated":[115],"ex-cellent":[116],"performance":[117,126],"TIMIT":[120],"classification":[122],"task,":[123],"re-porting":[124],"of13.8%phone":[127],"error":[128],"rate":[129],"and11.9%when":[134],"combined":[135],"with":[136],"NHO-CRF.":[138],"Inboth":[139],"cases":[140],"significantly":[142],"exceeded":[143],"state-of-the-art":[145],"perfor-mance.":[146]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}