{"id":"https://openalex.org/W2126048084","doi":"https://doi.org/10.1109/icassp.2011.5947602","title":"Amplitude modulation spectrogram based features for robust speech recognition in noisy and reverberant environments","display_name":"Amplitude modulation spectrogram based features for robust speech recognition in noisy and reverberant environments","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2126048084","doi":"https://doi.org/10.1109/icassp.2011.5947602","mag":"2126048084"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5071286568","display_name":"Niko Moritz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Niko Moritz","raw_affiliation_strings":["Fraunhofer IDMT - Project Group Hearing, Speech and Audio Technology, Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IDMT - Project Group Hearing, Speech and Audio Technology, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009092572","display_name":"J\u00f6rn Anem\u00fcller","orcid":"https://orcid.org/0000-0001-5564-5795"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jorn Anemuller","raw_affiliation_strings":["Medical Physics, Dept. of Physics, Carl-von-Ossietzky University Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"Medical Physics, Dept. of Physics, Carl-von-Ossietzky University Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076869895","display_name":"Birger Kollmeier","orcid":"https://orcid.org/0000-0001-8584-4779"},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Birger Kollmeier","raw_affiliation_strings":["Fraunhofer IDMT - Project Group Hearing, Speech and Audio Technology, Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IDMT - Project Group Hearing, Speech and Audio Technology, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210138578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5071286568"],"corresponding_institution_ids":["https://openalex.org/I4210138578"],"apc_list":null,"apc_paid":null,"fwci":1.8358,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.8630787,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"60","issue":null,"first_page":"5492","last_page":"5495"},"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":0.9994999766349792,"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/T11698","display_name":"Underwater Acoustics Research","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8831619024276733},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6824691295623779},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6670663356781006},{"id":"https://openalex.org/keywords/amplitude-modulation","display_name":"Amplitude modulation","score":0.6363915205001831},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.6091034412384033},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5969722270965576},{"id":"https://openalex.org/keywords/frequency-modulation","display_name":"Frequency modulation","score":0.5696085691452026},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5426713228225708},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5292524695396423},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.5276338458061218},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.48697957396507263},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.47380393743515015},{"id":"https://openalex.org/keywords/amplitude","display_name":"Amplitude","score":0.4612741470336914},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45559099316596985},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4535263180732727},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4251900613307953},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4184103012084961},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.3798835277557373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3591632843017578},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.2574070692062378},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25567418336868286},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.19542637467384338},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1749328374862671},{"id":"https://openalex.org/keywords/radio-frequency","display_name":"Radio frequency","score":0.1182246208190918},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09088107943534851},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.08481153845787048},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06356042623519897}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8831619024276733},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6824691295623779},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6670663356781006},{"id":"https://openalex.org/C201905106","wikidata":"https://www.wikidata.org/wiki/Q183755","display_name":"Amplitude modulation","level":4,"score":0.6363915205001831},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.6091034412384033},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5969722270965576},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.5696085691452026},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5426713228225708},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5292524695396423},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.5276338458061218},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.48697957396507263},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.47380393743515015},{"id":"https://openalex.org/C180205008","wikidata":"https://www.wikidata.org/wiki/Q159190","display_name":"Amplitude","level":2,"score":0.4612741470336914},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45559099316596985},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4535263180732727},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4251900613307953},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4184103012084961},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.3798835277557373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3591632843017578},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.2574070692062378},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25567418336868286},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.19542637467384338},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1749328374862671},{"id":"https://openalex.org/C74064498","wikidata":"https://www.wikidata.org/wiki/Q3396184","display_name":"Radio frequency","level":2,"score":0.1182246208190918},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09088107943534851},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.08481153845787048},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06356042623519897},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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":2,"locations":[{"id":"doi:10.1109/icassp.2011.5947602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/373082","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/373082","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W77052981","https://openalex.org/W164832740","https://openalex.org/W1480055486","https://openalex.org/W1971332722","https://openalex.org/W1994396704","https://openalex.org/W1999686891","https://openalex.org/W2041638389","https://openalex.org/W2046331056","https://openalex.org/W2075012882","https://openalex.org/W2097705421","https://openalex.org/W2137075158","https://openalex.org/W2151484683","https://openalex.org/W2165333179","https://openalex.org/W6603155125"],"related_works":["https://openalex.org/W2120540196","https://openalex.org/W3095343173","https://openalex.org/W2381036744","https://openalex.org/W2288135719","https://openalex.org/W2323749021","https://openalex.org/W2533590149","https://openalex.org/W2901989338","https://openalex.org/W82005754","https://openalex.org/W2334448276","https://openalex.org/W3210733254"],"abstract_inverted_index":{"In":[0,63],"this":[1,64],"contribution":[2],"we":[3],"present":[4],"a":[5,25,81,117],"feature":[6],"extraction":[7],"method":[8],"that":[9,31,49,96,112],"relies":[10],"on":[11,90],"the":[12,21,32,50,54,66,123],"modulation-spectral":[13],"analysis":[14,40,71],"of":[15,20,53,68,85,122],"amplitude":[16,38],"fluctuations":[17],"within":[18],"sub-bands":[19],"acoustic":[22],"spectrum":[23,56],"by":[24],"STFT.":[26],"The":[27,76],"experimental":[28],"results":[29],"indicate":[30],"optimal":[33],"temporal":[34],"filter":[35],"extension":[36],"for":[37,60,87],"modulation":[39,55,97],"is":[41,46,74,94],"around":[42],"310":[43],"ms.":[44],"It":[45],"also":[47],"demonstrated":[48],"phase":[51],"information":[52],"contains":[57],"important":[58],"cues":[59],"speech":[61],"recognition.":[62],"context,":[65],"advantage":[67],"an":[69],"odd":[70],"basis":[72],"function":[73],"considered.":[75],"best":[77],"presented":[78],"features":[79,98,110],"reached":[80],"total":[82],"relative":[83],"improvement":[84],"53.5%":[86],"clean-condition":[88],"training":[89],"Aurora-2.":[91],"Furthermore,":[92],"it":[93],"shown":[95],"are":[99],"more":[100],"robust":[101],"against":[102],"room":[103],"reverberation":[104],"than":[105],"conventional":[106],"cepstral":[107],"and":[108,111],"dynamic":[109],"they":[113],"strongly":[114],"benefit":[115],"from":[116],"high":[118],"early-to-late":[119],"energy":[120],"ratio":[121],"characteristic":[124],"RIR.":[125]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
