{"id":"https://openalex.org/W1557371711","doi":"https://doi.org/10.1109/icassp.1982.1171425","title":"An analysis-by-synthesis approach for automatic time segmentation of speech signals","display_name":"An analysis-by-synthesis approach for automatic time segmentation of speech signals","publication_year":2005,"publication_date":"2005-03-24","ids":{"openalex":"https://openalex.org/W1557371711","doi":"https://doi.org/10.1109/icassp.1982.1171425","mag":"1557371711"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.1982.1171425","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1982.1171425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '82. 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/A5034260378","display_name":"Yeunung Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I74760111","display_name":"Texas Instruments (United States)","ror":"https://ror.org/03vsmv677","country_code":"US","type":"company","lineage":["https://openalex.org/I74760111"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yeunung Chen","raw_affiliation_strings":["Computer Science Laboratory, Central Research Laboratories, Texas Instruments, Inc., USA","Texas Instruments Incorporated, Dallas, Texas, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Laboratory, Central Research Laboratories, Texas Instruments, Inc., USA","institution_ids":["https://openalex.org/I74760111"]},{"raw_affiliation_string":"Texas Instruments Incorporated, Dallas, Texas, USA","institution_ids":["https://openalex.org/I74760111"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5034260378"],"corresponding_institution_ids":["https://openalex.org/I74760111"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06184589,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":null,"first_page":"1956","last_page":"1959"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9970999956130981,"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":0.9944000244140625,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7546426057815552},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7246670722961426},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6913968324661255},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6587284207344055},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.62935870885849},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.568168044090271},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.5380074381828308},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5323634147644043},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5121266841888428},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.49060502648353577},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4844058156013489},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4718962609767914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33945566415786743},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32560306787490845},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0733698308467865}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7546426057815552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7246670722961426},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6913968324661255},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6587284207344055},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.62935870885849},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.568168044090271},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.5380074381828308},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5323634147644043},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5121266841888428},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.49060502648353577},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4844058156013489},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4718962609767914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33945566415786743},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32560306787490845},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0733698308467865},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.1982.1171425","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1982.1171425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '82. IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1565967034","https://openalex.org/W1989337816","https://openalex.org/W2015428738","https://openalex.org/W2138054245"],"related_works":["https://openalex.org/W1542588102","https://openalex.org/W2496295964","https://openalex.org/W1589226984","https://openalex.org/W2910493550","https://openalex.org/W2151333624","https://openalex.org/W1984921740","https://openalex.org/W4319347033","https://openalex.org/W1572861854","https://openalex.org/W2336887028","https://openalex.org/W1842536210"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,73],"analysis-by-synthesis":[4],"speech":[5,14,40,66,71,94],"segmentation":[6,18],"algorithm.":[7],"The":[8,28],"approach":[9],"employs":[10],"a":[11,48,56,64],"variable-frame-length":[12],"LPC":[13,93],"synthesizer,":[15],"and":[16,81],"the":[17,25,60],"process":[19],"is":[20],"performed":[21],"by":[22],"constantly":[23],"monitoring":[24],"synthesis":[26],"output.":[27],"resulting":[29],"segments,":[30],"in":[31],"general,":[32],"do":[33],"not":[34],"correspond":[35],"to":[36,85],"elemental":[37],"units":[38,53],"of":[39,51,59,76],"such":[41],"as":[42],"phonemes,":[43],"but":[44],"rather":[45],"they":[46],"represent":[47],"minimum":[49],"number":[50],"acoustic":[52],"necessary":[54],"for":[55],"high-quality":[57],"reproduction":[58],"particular":[61],"utterance.":[62],"On":[63],"limited":[65],"data":[67],"base,":[68],"synthetic":[69],"continuous":[70],"with":[72,82],"average":[74],"rate":[75,92],"20":[77],"frames":[78,88],"per":[79,89],"second":[80,90],"quality":[83],"comparable":[84],"about":[86],"333":[87],"fixed":[91],"has":[95],"been":[96],"achieved.":[97]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}