{"id":"https://openalex.org/W2111157186","doi":"https://doi.org/10.1109/icassp.2006.1661453","title":"Frequency-Warping Invariant Features for Automatic Speech Recognition","display_name":"Frequency-Warping Invariant Features for Automatic Speech Recognition","publication_year":2006,"publication_date":"2006-08-02","ids":{"openalex":"https://openalex.org/W2111157186","doi":"https://doi.org/10.1109/icassp.2006.1661453","mag":"2111157186"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1661453","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1661453","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","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/A5063948113","display_name":"Alfred Mertins","orcid":"https://orcid.org/0000-0001-5718-577X"},"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":"A. Mertins","raw_affiliation_strings":["Signal Processing Group, Department of Physics, University of Oldenburg, Oldenburg, Germany","Signal Processing Group, University of Oldenburg, Department of Physics, 26111 Oldenburg, Germany. Email: alfred.mertins@uni-oldenburg.de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Processing Group, Department of Physics, University of Oldenburg, Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]},{"raw_affiliation_string":"Signal Processing Group, University of Oldenburg, Department of Physics, 26111 Oldenburg, Germany. Email: alfred.mertins@uni-oldenburg.de","institution_ids":["https://openalex.org/I129877168"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032124578","display_name":"Jan Rademacher","orcid":null},"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":"J. Rademacher","raw_affiliation_strings":["Signal Processing Group, Department of Physics, University of Oldenburg, Oldenburg, Germany","Dept. of Phys., Oldenburg Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Processing Group, Department of Physics, University of Oldenburg, Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]},{"raw_affiliation_string":"Dept. of Phys., Oldenburg Univ","institution_ids":["https://openalex.org/I129877168"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I129877168"],"apc_list":null,"apc_paid":null,"fwci":0.7328,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.6892129,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"5","issue":null,"first_page":"V","last_page":"1025"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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":0.9987999796867371,"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/vocal-tract","display_name":"Vocal tract","score":0.817920446395874},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7600184082984924},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7160280346870422},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.7110328674316406},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.6691682934761047},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.659750759601593},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.638131320476532},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5986403226852417},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.585186779499054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5588292479515076},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5292555689811707},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4828263223171234},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.48139452934265137},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3230394423007965},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.27760377526283264},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20370632410049438},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1515388786792755}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.817920446395874},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7600184082984924},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7160280346870422},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.7110328674316406},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.6691682934761047},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.659750759601593},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.638131320476532},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5986403226852417},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.585186779499054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5588292479515076},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5292555689811707},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4828263223171234},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.48139452934265137},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3230394423007965},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.27760377526283264},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20370632410049438},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1515388786792755},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2006.1661453","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1661453","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.302.4429","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.302.4429","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.isip.uni-luebeck.de/uploads/tx_wapublications/Mertins-Icassp06.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"},{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W164170074","https://openalex.org/W1480487340","https://openalex.org/W2077804127","https://openalex.org/W2101789093","https://openalex.org/W2104559592","https://openalex.org/W2116988482","https://openalex.org/W2117419877","https://openalex.org/W2135346934","https://openalex.org/W2164931619","https://openalex.org/W6606695357"],"related_works":["https://openalex.org/W2335896301","https://openalex.org/W2012393389","https://openalex.org/W1482212662","https://openalex.org/W2333240621","https://openalex.org/W2100012411","https://openalex.org/W3006618853","https://openalex.org/W3162157266","https://openalex.org/W2253066076","https://openalex.org/W2162084437","https://openalex.org/W1997579527"],"abstract_inverted_index":{"Based":[0],"on":[1,46],"the":[2,47],"well-known":[3],"relationship":[4],"between":[5,57],"vocal":[6,21],"tract":[7,22],"length":[8,23],"(VTL)":[9],"variation":[10],"and":[11,43,53,59,82],"linear":[12],"frequency":[13],"warping,":[14],"we":[15],"present":[16],"a":[17,37],"method":[18],"for":[19,69],"generating":[20],"invariant":[24],"(VTLI)":[25],"features.":[26],"These":[27],"features":[28,35,81],"are":[29,77,84],"computed":[30],"as":[31],"translation":[32],"invariant,":[33],"correlation-type":[34],"in":[36],"log-frequency":[38],"domain.":[39],"In":[40],"phoneme":[41],"classification":[42],"recognition":[44],"experiments":[45],"TIMIT":[48],"database,":[49],"their":[50],"discrimination":[51],"capabilities":[52],"robustness":[54],"to":[55,64],"mismatches":[56],"training":[58],"test":[60],"conditions":[61],"turned":[62],"out":[63],"be":[65],"considerably":[66],"better":[67],"than":[68],"Mel-frequency":[70],"cepstral":[71],"coefficients":[72],"(MFCCs).":[73],"The":[74],"best":[75],"results":[76],"obtained":[78],"when":[79],"VTLI":[80],"MFCCs":[83],"combined":[85]},"counts_by_year":[{"year":2014,"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"}