{"id":"https://openalex.org/W2153495750","doi":"https://doi.org/10.1109/icassp.1986.1168558","title":"Visual characterization of speech spectrograms","display_name":"Visual characterization of speech spectrograms","publication_year":2005,"publication_date":"2005-03-24","ids":{"openalex":"https://openalex.org/W2153495750","doi":"https://doi.org/10.1109/icassp.1986.1168558","mag":"2153495750"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.1986.1168558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1986.1168558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5102984697","display_name":"Hong Leung","orcid":"https://orcid.org/0009-0002-5901-0863"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Leung","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science and Research Laboratory of Electronics, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science and Research Laboratory of Electronics, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109575396","display_name":"Victor W. Zue","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"V. Zue","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science and Research Laboratory of Electronics, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science and Research Laboratory of Electronics, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":1.0188,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.76685538,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"11","issue":null,"first_page":"2751","last_page":"2754"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9951000213623047,"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":0.9951000213623047,"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/T10534","display_name":"Structural Health Monitoring Techniques","score":0.9587000012397766,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11698","display_name":"Underwater Acoustics Research","score":0.9248999953269958,"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":0.9596370458602905},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.8646246194839478},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7073063850402832},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6551076173782349},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.579494297504425},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5293959975242615},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.5215415954589844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5106483101844788},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5009825229644775},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.49337711930274963},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38256239891052246},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.378882497549057}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9596370458602905},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.8646246194839478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7073063850402832},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6551076173782349},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.579494297504425},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5293959975242615},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.5215415954589844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5106483101844788},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5009825229644775},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.49337711930274963},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38256239891052246},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.378882497549057},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.1986.1168558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1986.1168558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W607079072","https://openalex.org/W1670129776","https://openalex.org/W1756736144","https://openalex.org/W1878581552","https://openalex.org/W2002312729","https://openalex.org/W2109863423","https://openalex.org/W2133155955","https://openalex.org/W2136419841","https://openalex.org/W2137089646","https://openalex.org/W6680297918"],"related_works":["https://openalex.org/W2025848302","https://openalex.org/W1975454382","https://openalex.org/W2799441357","https://openalex.org/W5449343","https://openalex.org/W2409530148","https://openalex.org/W2053642297","https://openalex.org/W4250508028","https://openalex.org/W2028715205","https://openalex.org/W2344358524","https://openalex.org/W2070513494"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,19,23,51,56],"system":[4,33],"that":[5,37,70],"applies":[6],"vision":[7],"techniques":[8],"to":[9,79],"extract":[10],"acoustic":[11,76],"patterns":[12,41],"in":[13],"the":[14,32,39,54,64,81],"speech":[15],"spectrogram.":[16],"By":[17],"processing":[18,72],"spectrographic":[20],"image":[21],"through":[22],"set":[24],"of":[25,53],"edge":[26],"detectors":[27],"and":[28,42,48],"combining":[29],"their":[30],"outputs,":[31],"obtains":[34],"two-dimensional":[35],"objects":[36],"characterize":[38],"formant":[40],"general":[43],"spectral":[44],"properties":[45],"for":[46],"vowels":[47],"consonants.":[49],"As":[50],"validation":[52],"approach,":[55],"limited":[57],"vowel":[58],"recognition":[59],"experiment":[60],"was":[61],"performed":[62],"on":[63],"\"object\"":[65],"spectrograms.":[66],"Preliminary":[67],"results":[68],"show":[69],"this":[71],"technique":[73],"retains":[74],"relevant":[75],"information":[77],"necessary":[78],"identify":[80],"underlying":[82],"phonetic":[83],"representation.":[84]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}