{"id":"https://openalex.org/W1948738941","doi":"https://doi.org/10.1109/icassp.2003.1198717","title":"Robust speech recognition using features based on zero crossings with peak amplitudes","display_name":"Robust speech recognition using features based on zero crossings with peak amplitudes","publication_year":2003,"publication_date":"2003-10-08","ids":{"openalex":"https://openalex.org/W1948738941","doi":"https://doi.org/10.1109/icassp.2003.1198717","mag":"1948738941"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198717","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198717","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5089528872","display_name":"Bojana Gaji\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"B. Gajic","raw_affiliation_strings":["Department of Telecommunications, Norwegian University of Science and Techn., Trondheim, Norway","Dept. of Telecommun.., Norwegian Univ. of Sci. & Technol., Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Telecommunications, Norwegian University of Science and Techn., Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]},{"raw_affiliation_string":"Dept. of Telecommun.., Norwegian Univ. of Sci. & Technol., Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046089538","display_name":"Kuldip K. Paliwal","orcid":"https://orcid.org/0000-0002-3553-3662"},"institutions":[{"id":"https://openalex.org/I11701301","display_name":"Griffith University","ror":"https://ror.org/02sc3r913","country_code":"AU","type":"education","lineage":["https://openalex.org/I11701301"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"K.K. Paliwal","raw_affiliation_strings":["Griffith University, School of Microelectronic Engineering, Brisbane, Australia","Griffith University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Griffith University, School of Microelectronic Engineering, Brisbane, Australia","institution_ids":["https://openalex.org/I11701301"]},{"raw_affiliation_string":"Griffith University","institution_ids":["https://openalex.org/I11701301"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8585,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.91499299,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"64"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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/T11309","display_name":"Music and Audio Processing","score":0.9923999905586243,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8377853035926819},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.8099229335784912},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6984490156173706},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6882137060165405},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6872199177742004},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5993822813034058},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5753352046012878},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5062941312789917},{"id":"https://openalex.org/keywords/biometrics","display_name":"Biometrics","score":0.47389617562294006},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4628064036369324},{"id":"https://openalex.org/keywords/amplitude","display_name":"Amplitude","score":0.4603310823440552},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4520461857318878},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15740835666656494}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8377853035926819},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8099229335784912},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6984490156173706},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6882137060165405},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6872199177742004},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5993822813034058},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5753352046012878},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5062941312789917},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.47389617562294006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4628064036369324},{"id":"https://openalex.org/C180205008","wikidata":"https://www.wikidata.org/wiki/Q159190","display_name":"Amplitude","level":2,"score":0.4603310823440552},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4520461857318878},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15740835666656494},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2003.1198717","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198717","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},{"id":"pmh:oai:research-repository.griffith.edu.au:10072/1784","is_oa":false,"landing_page_url":"http://hdl.handle.net/10072/1784","pdf_url":null,"source":{"id":"https://openalex.org/S7407064376","display_name":"Griffith Research Online","issn_l":null,"issn":null,"is_oa":false,"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":null,"raw_type":"Conference output"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W105804906","https://openalex.org/W638670559","https://openalex.org/W1643320849","https://openalex.org/W2155104508","https://openalex.org/W2155776568","https://openalex.org/W2158483598","https://openalex.org/W4231354308","https://openalex.org/W6604257673"],"related_works":["https://openalex.org/W2076845124","https://openalex.org/W2183964146","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W1996690921","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2138847091"],"abstract_inverted_index":{"The":[0,32,61,80],"paper":[1],"presents":[2],"an":[3],"extensive":[4],"study":[5,33],"of":[6,29,48,82,86,102,119],"zero":[7],"crossings":[8],"with":[9],"peak":[10],"amplitudes":[11],"(ZCPA)":[12],"features,":[13],"that":[14],"have":[15],"earlier":[16],"been":[17],"shown":[18],"to":[19,111,123],"outperform":[20],"both":[21],"conventional":[22],"and":[23,50,71,90],"auditory-based":[24],"features":[25,52,108,121],"in":[26,40,57,93,106],"the":[27,65,100],"presence":[28],"additive":[30],"noise.":[31],"starts":[34],"by":[35,45],"optimizing":[36],"different":[37,58],"parameters":[38],"involved":[39],"ZCPA":[41,49,94,107,120],"feature":[42,67,95],"computation,":[43],"followed":[44],"a":[46,83,113],"comparison":[47],"MFCC":[51,124],"on":[53,75],"two":[54,66],"recognition":[55],"tasks":[56],"background":[59],"conditions.":[60],"main":[62],"differences":[63],"between":[64],"types":[68],"are":[69,78],"identified,":[70],"their":[72],"individual":[73],"effects":[74],"ASR":[76],"performance":[77],"evaluated.":[79],"importance":[81],"proper":[84],"choice":[85],"analysis":[87],"frame":[88],"lengths":[89],"filter":[91],"bandwidths":[92],"extraction":[96],"is":[97,109],"demonstrated.":[98],"Furthermore,":[99],"use":[101],"dominant":[103],"frequency":[104],"information":[105],"found":[110],"be":[112],"major":[114],"reason":[115],"for":[116],"increased":[117],"robustness":[118],"compared":[122],"features.":[125]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-09-02T18:50:13.731487","created_date":"2025-10-10T00:00:00"}