{"id":"https://openalex.org/W2406820985","doi":"https://doi.org/10.21437/interspeech.2012-266","title":"Intrinsic spectral analysis for zero and high resource speech recognition","display_name":"Intrinsic spectral analysis for zero and high resource speech recognition","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2406820985","doi":"https://doi.org/10.21437/interspeech.2012-266","mag":"2406820985"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-266","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","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/A5103622427","display_name":"Aren Jansen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Aren Jansen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5042260050","display_name":"Hynek He\u0159mansk\u00fd","orcid":"https://orcid.org/0000-0001-8032-4811"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hynek Hermansky","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103622427"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9727,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.93827784,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"879","last_page":"882"},"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":0.9988999962806702,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.816234827041626},{"id":"https://openalex.org/keywords/salience","display_name":"Salience (neuroscience)","score":0.6955840587615967},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6679142713546753},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6208160519599915},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5663267970085144},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5500891208648682},{"id":"https://openalex.org/keywords/manifold","display_name":"Manifold (fluid mechanics)","score":0.44641152024269104},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42952191829681396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3983376622200012},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3975660502910614},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09758126735687256}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.816234827041626},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.6955840587615967},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6679142713546753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6208160519599915},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5663267970085144},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5500891208648682},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.44641152024269104},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42952191829681396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3983376622200012},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3975660502910614},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09758126735687256},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2012-266","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.261.1872","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.261.1872","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.clsp.jhu.edu/%7Esamuel/pdfs/intrinsic.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W30845872","https://openalex.org/W161904138","https://openalex.org/W1539935047","https://openalex.org/W2057007397","https://openalex.org/W2057781541","https://openalex.org/W2096215262","https://openalex.org/W2103372210","https://openalex.org/W2104290444","https://openalex.org/W2114347655","https://openalex.org/W2125879978","https://openalex.org/W2165882272","https://openalex.org/W2407151108"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W2900415423","https://openalex.org/W4394643898","https://openalex.org/W1629152045","https://openalex.org/W3026405273","https://openalex.org/W2970256865","https://openalex.org/W1840351222"],"abstract_inverted_index":{"The":[0],"constraints":[1],"of":[2,40,88,100,117,138],"the":[3,31,41,81,86,97,101,131,136],"speech":[4,53,119,155],"production":[5],"apparatus":[6],"imply":[7],"that":[8,130],"our":[9],"vocalizations":[10],"are":[11,125],"approximately":[12],"restricted":[13],"to":[14,29,46,93,110,142],"a":[15,20,27,60],"lowdimensional":[16],"manifold":[17,153],"embedded":[18],"in":[19,74],"high-dimensional":[21],"space.":[22],"Manifold":[23],"learning":[24],"algorithms":[25],"provide":[26],"means":[28],"recover":[30],"approximate":[32],"embedding":[33],"from":[34],"untranscribed":[35],"data":[36],"and":[37,77,139],"enable":[38],"use":[39],"manifold\u2019s":[42],"intrinsic":[43,67,133,150],"distance":[44],"metric":[45],"characterize":[47],"acoustic":[48,102,112,122],"similarity":[49],"for":[50,66,120],"downstream":[51],"automatic":[52],"applications.":[54],"In":[55,80],"this":[56],"paper,":[57],"we":[58,128],"consider":[59],"previously":[61],"unevaluated":[62],"nonlinear":[63],"outof-sample":[64],"extension":[65],"spectral":[68,151],"analysis":[69],"(ISA),":[70],"investigating":[71],"its":[72],"performance":[73,137],"both":[75],"unsupervised":[76],"supervised":[78,121],"tasks.":[79],"zero":[82,157],"resource":[83,158],"regime,":[84],"where":[85],"lack":[87],"transcribed":[89,118],"resources":[90],"forces":[91],"us":[92],"rely":[94],"solely":[95],"on":[96],"phonetic":[98],"salience":[99],"features":[103],"themselves,":[104],"ISA":[105],"provides":[106],"substantial":[107],"gains":[108],"relative":[109],"canonical":[111],"front-ends.":[113],"When":[114],"large":[115],"amounts":[116],"model":[123],"training":[124],"also":[126],"available,":[127],"find":[129],"data-driven":[132],"spectrogram":[134],"matches":[135],"is":[140],"complementary":[141],"these":[143],"signal":[144],"processing":[145],"derived":[146],"counterparts.":[147],"Index":[148],"Terms:":[149],"analysis,":[152],"learning,":[154],"recognition,":[156]},"counts_by_year":[{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":6}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}