{"id":"https://openalex.org/W2162436288","doi":"https://doi.org/10.1109/icassp.2006.1660073","title":"A Sinusoidal Model Approach to Acoustic Landmark Detection and Segmentation for Robust Segment-Based Speech Recognition","display_name":"A Sinusoidal Model Approach to Acoustic Landmark Detection and Segmentation for Robust Segment-Based Speech Recognition","publication_year":2006,"publication_date":"2006-08-02","ids":{"openalex":"https://openalex.org/W2162436288","doi":"https://doi.org/10.1109/icassp.2006.1660073","mag":"2162436288"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1660073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660073","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/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T.N. Sainath","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4405258931"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114018312","display_name":"Timothy J. Hazen","orcid":"https://orcid.org/0009-0006-1413-9590"},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T.J. Hazen","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4405258931"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4405258931"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"525"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9998999834060669,"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":0.9998000264167786,"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/segmentation","display_name":"Segmentation","score":0.8444448709487915},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7839311361312866},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6312642693519592},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6059812307357788},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5831145644187927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.580328106880188},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.5716005563735962},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5693602561950684},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4430842995643616},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.4422972500324249},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.43078961968421936},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.36139625310897827},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20018959045410156}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8444448709487915},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7839311361312866},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6312642693519592},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6059812307357788},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5831145644187927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.580328106880188},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.5716005563735962},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5693602561950684},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4430842995643616},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.4422972500324249},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.43078961968421936},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.36139625310897827},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20018959045410156},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2006.1660073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660073","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:10.1.1.154.8581","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.154.8581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sls.csail.mit.edu/sls/publications/2006/sainath_icassp06.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1974387177","https://openalex.org/W2071828724","https://openalex.org/W2080921589","https://openalex.org/W2083393647","https://openalex.org/W2111732304","https://openalex.org/W2141549354","https://openalex.org/W2151484683","https://openalex.org/W2159459410","https://openalex.org/W2164764235"],"related_works":["https://openalex.org/W2185902295","https://openalex.org/W2103507220","https://openalex.org/W3144569342","https://openalex.org/W3011384228","https://openalex.org/W4313052709","https://openalex.org/W2945274617","https://openalex.org/W3199300986","https://openalex.org/W4298131179","https://openalex.org/W2375430703","https://openalex.org/W1522196789"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,118],"present":[4],"a":[5,14,41],"noise":[6,131],"robust":[7,124],"landmark":[8],"detection":[9],"and":[10,45,76,110],"segmentation":[11,32,43,64,78,86],"algorithm":[12,102],"using":[13],"sinusoidal":[15,75],"model":[16,122],"representation":[17],"of":[18,24,60,71,93,113],"speech.":[19],"We":[20,97],"compare":[21],"the":[22,36,61,69,74,84,89,94,104,114],"performance":[23],"our":[25,100,121],"approach":[26,44,47],"under":[27],"noisy":[28],"conditions":[29],"against":[30],"two":[31],"methods":[33],"used":[34],"in":[35,68],"SUMMIT":[37],"segment-based":[38],"speech":[39,126],"recognizer,":[40],"full":[42,77,85],"an":[46],"that":[48,99,120],"detects":[49],"segment":[50],"boundaries":[51],"based":[52],"on":[53],"spectral":[54,62],"change.":[55],"The":[56],"word":[57,108],"error":[58],"rate":[59],"change":[63],"method":[65,87],"degrades":[66],"rapidly":[67],"presence":[70],"noise,":[72],"while":[73],"models":[79],"degrade":[80],"more":[81],"gracefully.":[82],"However,":[83],"requires":[88],"largest":[90],"computation":[91,111],"time":[92,112],"three":[95,115],"approaches.":[96],"find":[98,119],"new":[101],"provides":[103],"best":[105],"tradeoff":[106],"between":[107],"accuracy":[109],"methods.":[116],"Furthermore,":[117],"is":[123,127],"when":[125],"contaminated":[128],"by":[129],"various":[130],"types":[132]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}