{"id":"https://openalex.org/W2168013545","doi":"https://doi.org/10.21437/interspeech.2010-487","title":"Binary coding of speech spectrograms using a deep auto-encoder","display_name":"Binary coding of speech spectrograms using a deep auto-encoder","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W2168013545","doi":"https://doi.org/10.21437/interspeech.2010-487","mag":"2168013545"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-487","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","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/A5100671324","display_name":"Li Deng","orcid":"https://orcid.org/0000-0002-1014-0790"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"L. Deng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041313589","display_name":"Michael L. Seltzer","orcid":"https://orcid.org/0000-0003-3474-2451"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael L. Seltzer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111957484","display_name":"Alex Acero","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alex Acero","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103742478","display_name":"Abdelrahman Mohamed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdel-rahman Mohamed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108093963","display_name":"Geoffrey E. Hinton","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"G. Hinton","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":383,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1692","last_page":"1695"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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/spectrogram","display_name":"Spectrogram","score":0.927485466003418},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6980951428413391},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6555500626564026},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6315310001373291},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5496712923049927},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5337681770324707},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.527967095375061},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4466167986392975},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3951353430747986},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.24173632264137268},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11861193180084229},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.07933634519577026}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.927485466003418},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6980951428413391},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6555500626564026},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6315310001373291},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5496712923049927},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5337681770324707},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.527967095375061},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4466167986392975},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3951353430747986},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.24173632264137268},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11861193180084229},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.07933634519577026},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"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:10.21437/interspeech.2010-487","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","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":14,"referenced_works":["https://openalex.org/W42107399","https://openalex.org/W197206975","https://openalex.org/W1481688629","https://openalex.org/W2027915610","https://openalex.org/W2084514013","https://openalex.org/W2096170322","https://openalex.org/W2097035595","https://openalex.org/W2100495367","https://openalex.org/W2135013272","https://openalex.org/W2136922672","https://openalex.org/W2141778357","https://openalex.org/W2143987987","https://openalex.org/W2148632119","https://openalex.org/W2913932916"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W2159052453","https://openalex.org/W3013693939","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W2566616303","https://openalex.org/W2011227383","https://openalex.org/W3138614332","https://openalex.org/W2366163563","https://openalex.org/W2163885456"],"abstract_inverted_index":{"This":[0],"paper":[1],"reports":[2],"our":[3],"recent":[4],"exploration":[5],"of":[6,17,19,25,39,57,161],"the":[7,26,58,65,69,79,84,93,110,137,157],"layer-by-layer":[8],"learning":[9],"strategy":[10],"for":[11,36,46],"training":[12],"a":[13,98,141,151],"multi-layer":[14],"generative":[15,27,59,94],"model":[16,28,60,95],"patches":[18],"speech":[20,40,48,52,112,132,168],"spectrograms.":[21],"The":[22],"top":[23],"layer":[24,56,66],"learns":[29],"binary":[30,121,138,174],"codes":[31,122,139],"that":[32,136,144],"can":[33],"be":[34,44],"used":[35,45],"efficient":[37],"compression":[38],"and":[41,68],"could":[42],"also":[43],"scalable":[47],"recognition":[49],"or":[50],"rapid":[51],"content":[53],"retrieval.":[54],"Each":[55],"is":[61,145],"fully":[62],"connected":[63],"to":[64,83,96],"below":[67],"weights":[70],"on":[71,131],"these":[72],"connections":[73],"are":[74,103,123],"pretrained":[75],"efficiently":[76],"by":[77,118],"using":[78,106,125],"contrastive":[80],"divergence":[81],"approximation":[82],"log":[85],"likelihood":[86],"gradient.":[87],"After":[88],"layer-bylayer":[89],"pre-training":[90],"we":[91],"\u201cunroll\u201d":[92],"form":[97],"deep":[99,166],"auto-encoder,":[100,173],"whose":[101],"parameters":[102],"then":[104],"fine-tuned":[105],"back-propagation.":[107],"To":[108],"reconstruct":[109],"full-length":[111],"spectrogram,":[113],"individual":[114],"spectrogram":[115,133],"segments":[116],"predicted":[117],"their":[119],"respective":[120],"combined":[124],"an":[126],"overlapand-add":[127],"method.":[128],"Experimental":[129],"results":[130],"coding":[134],"demonstrate":[135],"produce":[140],"logspectral":[142],"distortion":[143],"approximately":[146],"2":[147],"dB":[148],"lower":[149],"than":[150],"subband":[152],"vector":[153],"quantization":[154],"technique":[155],"over":[156],"entire":[158],"frequency":[159],"range":[160],"wide-band":[162],"speech.":[163],"Index":[164],"Terms:":[165],"learning,":[167],"feature":[169],"extraction,":[170],"neural":[171],"networks,":[172],"codes,":[175],"Boltzmann":[176],"machine":[177]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":53},{"year":2020,"cited_by_count":46},{"year":2019,"cited_by_count":49},{"year":2018,"cited_by_count":49},{"year":2017,"cited_by_count":35},{"year":2016,"cited_by_count":25},{"year":2015,"cited_by_count":26},{"year":2014,"cited_by_count":23},{"year":2013,"cited_by_count":17},{"year":2012,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}