{"id":"https://openalex.org/W1999850543","doi":"https://doi.org/10.1109/cip.2012.6232918","title":"Combined-order hidden Markov models for reverberation-robust speech recognition","display_name":"Combined-order hidden Markov models for reverberation-robust speech recognition","publication_year":2012,"publication_date":"2012-05-01","ids":{"openalex":"https://openalex.org/W1999850543","doi":"https://doi.org/10.1109/cip.2012.6232918","mag":"1999850543"},"language":"en","primary_location":{"id":"doi:10.1109/cip.2012.6232918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cip.2012.6232918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 3rd International Workshop on Cognitive Information Processing (CIP)","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/A5090454997","display_name":"Roland Maas","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Roland Maas","raw_affiliation_strings":["Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany","[Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"[Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany]","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079468553","display_name":"Sujan R. Kotha","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sujan R. Kotha","raw_affiliation_strings":["Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany","[Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"[Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany]","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057078484","display_name":"Armin Sehr","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Armin Sehr","raw_affiliation_strings":["Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany","[Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"[Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany]","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068787682","display_name":"Walter Kellermann","orcid":"https://orcid.org/0000-0002-6501-3174"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Walter Kellermann","raw_affiliation_strings":["Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany","[Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"[Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany]","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I181369854"],"apc_list":null,"apc_paid":null,"fwci":0.488,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57961165,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"39","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/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/T11309","display_name":"Music and Audio Processing","score":0.9965000152587891,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.9411237239837646},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6949831247329712},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6893166303634644},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6103711128234863},{"id":"https://openalex.org/keywords/hidden-semi-markov-model","display_name":"Hidden semi-Markov model","score":0.5712597966194153},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.5639809966087341},{"id":"https://openalex.org/keywords/maximum-entropy-markov-model","display_name":"Maximum-entropy Markov model","score":0.5415956377983093},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.4669880270957947},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43508094549179077},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4212374687194824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41875821352005005},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.3901917040348053},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2632949948310852},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08800280094146729}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9411237239837646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6949831247329712},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6893166303634644},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6103711128234863},{"id":"https://openalex.org/C64939953","wikidata":"https://www.wikidata.org/wiki/Q3859882","display_name":"Hidden semi-Markov model","level":5,"score":0.5712597966194153},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.5639809966087341},{"id":"https://openalex.org/C196956702","wikidata":"https://www.wikidata.org/wiki/Q6795829","display_name":"Maximum-entropy Markov model","level":5,"score":0.5415956377983093},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.4669880270957947},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43508094549179077},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4212374687194824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41875821352005005},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3901917040348053},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2632949948310852},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08800280094146729},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cip.2012.6232918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cip.2012.6232918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 3rd International Workshop on Cognitive Information Processing (CIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6299999952316284}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W172635372","https://openalex.org/W1683056191","https://openalex.org/W1833981795","https://openalex.org/W2049633694","https://openalex.org/W2064218608","https://openalex.org/W2088007127","https://openalex.org/W2096837052","https://openalex.org/W2117325244","https://openalex.org/W2125838338","https://openalex.org/W2142416747","https://openalex.org/W2148898720","https://openalex.org/W3129711340","https://openalex.org/W4205130185","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W2382132287","https://openalex.org/W2161328464","https://openalex.org/W2379333870","https://openalex.org/W3113307220","https://openalex.org/W1542903750","https://openalex.org/W3164302780","https://openalex.org/W1510894296","https://openalex.org/W4250171007","https://openalex.org/W4385889111","https://openalex.org/W2361306765"],"abstract_inverted_index":{"In":[0],"this":[1],"contribution,":[2],"the":[3,15,19,32,59,68,71,77,94],"concept":[4],"of":[5,34,65],"combined-order":[6],"hidden":[7,46],"Markov":[8,17,47,79],"models":[9],"(CO-HMMs)":[10],"is":[11,27,81],"introduced":[12],"by":[13,83],"joining":[14],"first-order":[16,78],"and":[18,29],"second-order":[20],"conditional":[21],"independence":[22],"assumption.":[23],"The":[24,108],"proposed":[25],"approach":[26],"motivated":[28],"evaluated":[30],"in":[31,53,63,114,120,124],"context":[33],"reverberation-robust":[35],"automatic":[36],"speech":[37],"recognition.":[38],"Two":[39],"predecessor-dependent":[40],"output":[41],"probability":[42],"density":[43],"functions":[44],"per":[45],"model":[48],"(HMM)":[49],"state":[50,72],"are":[51],"employed":[52],"order":[54],"to":[55,76,105,128],"explicitly":[56],"cope":[57],"with":[58],"high":[60],"inter-frame":[61],"correlation":[62],"presence":[64],"reverberation.":[66],"At":[67],"same":[69],"time,":[70],"duration":[73],"modeling":[74],"related":[75],"assumption":[80],"addressed":[82],"a":[84,106,112],"recently":[85],"published":[86],"training":[87],"procedure":[88],"based":[89],"on":[90],"hard":[91],"alignment":[92],"having":[93],"significant":[95],"advantage":[96],"that":[97],"any":[98],"conventional":[99,129],"HMM":[100],"can":[101],"be":[102],"efficiently":[103],"updated":[104],"CO-HMM.":[107],"experimental":[109],"results":[110],"show":[111],"reduction":[113],"average":[115],"entropy":[116],"as":[117,119],"well":[118],"word":[121],"error":[122],"rate":[123],"reverberant":[125],"environments":[126],"compared":[127],"HMMs.":[130]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}