{"id":"https://openalex.org/W1984758399","doi":"https://doi.org/10.1109/icassp.2002.5743718","title":"Robust phoneme discrimination using acoustic waveforms","display_name":"Robust phoneme discrimination using acoustic waveforms","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W1984758399","doi":"https://doi.org/10.1109/icassp.2002.5743718","mag":"1984758399"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743718","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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":"IEEE International Conference on Acoustics Speech and Signal Processing","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/A5056805951","display_name":"Zoran Cvetkovi\u0107","orcid":"https://orcid.org/0000-0002-5128-5099"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zoran Cvetkovic","raw_affiliation_strings":["AT and T Laboratories, Shannon Laboratory, Florham Park, NJ, USA","AT&T Shannon Laboratory, Florham Park, New Jersey, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT and T Laboratories, Shannon Laboratory, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Shannon Laboratory, Florham Park, New Jersey, USA","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047173758","display_name":"Baltasar Beferull\u2010Lozano","orcid":"https://orcid.org/0000-0002-0902-6245"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baltasar Beferull-Lozano","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA","University of Southern California, Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001227061","display_name":"Andreas Buja","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Buja","raw_affiliation_strings":["AT and T Laboratories, Shannon Laboratory, Florham Park, NJ, USA","AT&T Shannon Laboratory, Florham Park, New Jersey, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT and T Laboratories, Shannon Laboratory, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Shannon Laboratory, Florham Park, New Jersey, USA","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3296,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.43199316,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"I","last_page":"317"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9950000047683716,"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":0.9950000047683716,"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":0.9940000176429749,"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":0.9700000286102295,"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/timit","display_name":"TIMIT","score":0.8627538681030273},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6496022939682007},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6401652097702026},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5824418663978577},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5764541625976562},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.5559513568878174},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5035778880119324},{"id":"https://openalex.org/keywords/white-noise","display_name":"White noise","score":0.5017945766448975},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.47337621450424194},{"id":"https://openalex.org/keywords/linear-subspace","display_name":"Linear subspace","score":0.4211184084415436},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4153406620025635},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.4135028123855591},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33129847049713135},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29887694120407104},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.28248530626296997}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.8627538681030273},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6496022939682007},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6401652097702026},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5824418663978577},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5764541625976562},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.5559513568878174},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5035778880119324},{"id":"https://openalex.org/C112633086","wikidata":"https://www.wikidata.org/wiki/Q381287","display_name":"White noise","level":2,"score":0.5017945766448975},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.47337621450424194},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.4211184084415436},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4153406620025635},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4135028123855591},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33129847049713135},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29887694120407104},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.28248530626296997},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2002.5743718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743718","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/f2ab5d73-f001-4450-a4a2-e45429be3421","is_oa":false,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/f2ab5d73-f001-4450-a4a2-e45429be3421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Cvetkovic , Z , Beferull-Lozano , B & Buja , A 2002 , Robust phoneme discrimination using acoustic waveforms . in 2002 IEEE International Conference On Acoustics, Speech, And Signal Processing, Proceedings . N/A edn , vol. 1 , International Conference on Acoustics Speech and Signal Processing (ICASSP) , Piscataway, N.J. , pp. 317-320 , IEEE International Conference on Acoustics, Speech, and Signal Processing , United Kingdom , 13/05/2002 . https://doi.org/10.1109/ICASSP.2002.5743718","raw_type":"contributionToPeriodical"}],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W1560013842","https://openalex.org/W4243915041"],"related_works":["https://openalex.org/W80423236","https://openalex.org/W2391321755","https://openalex.org/W3164669818","https://openalex.org/W2487162673","https://openalex.org/W2949110394","https://openalex.org/W2896134808","https://openalex.org/W2793211469","https://openalex.org/W2949152769","https://openalex.org/W4289378085","https://openalex.org/W2071055957"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,48],"study":[3],"of":[4,6,9,18,21,24,39,51,55,81],"separability":[5],"acoustic":[7,22],"waveforms":[8,23,58],"speech":[10],"at":[11,32],"phoneme":[12],"level.":[13],"The":[14],"analyzed":[15],"data":[16,29,85,88],"consist":[17],"64ms":[19],"segments":[20],"individual":[25],"phonemes":[26,72,82],"from":[27],"TIMIT":[28],"base,":[30],"sampled":[31],"16kHz.":[33],"For":[34],"each":[35],"phoneme,":[36],"by":[37],"means":[38],"principal":[40],"component":[41],"analysis,":[42],"we":[43,77],"identify":[44],"subspaces":[45],"which":[46],"contain":[47],"given":[49],"proportion":[50],"the":[52,56,74,103,115],"total":[53],"energy":[54],"available":[57],"in":[59,63,73,90],"time-domain,":[60],"and":[61,86],"also":[62],"spectral-magnitude":[64],"domain.":[65],"In":[66],"order":[67],"to":[68,96,99,112,119],"assess":[69],"separation":[70],"between":[71],"two":[75],"domains,":[76],"perform":[78],"pairwise":[79],"classification":[80,104,117],"on":[83,87,106],"clean":[84],"immersed":[89],"white":[91],"additive":[92,113],"Gaussian":[93],"noise":[94,100],"up":[95],"0dB":[97],"signal":[98],"ratio.":[101],"While":[102],"based":[105],"spectral":[107],"magnitudes":[108],"exhibits":[109],"high":[110],"sensitivity":[111],"noise,":[114],"time-domain":[116],"proves":[118],"be":[120],"very":[121],"robust.":[122]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}