{"id":"https://openalex.org/W2108817613","doi":"https://doi.org/10.1109/icassp.2011.5947516","title":"Joint encoding of the waveform and speech recognition features using a transform codec","display_name":"Joint encoding of the waveform and speech recognition features using a transform codec","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2108817613","doi":"https://doi.org/10.1109/icassp.2011.5947516","mag":"2108817613"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947516","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5018483554","display_name":"Xing Fan","orcid":"https://orcid.org/0000-0002-0178-6442"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xing Fan","raw_affiliation_strings":["Microsoft Research Limited, Redmond, WA, USA","Microsoft Research, One Microsoft Way, Redmond, WA, 98052 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, One Microsoft Way, Redmond, WA, 98052 USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041313589","display_name":"Michael L. Seltzer","orcid":"https://orcid.org/0000-0003-3474-2451"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Seltzer","raw_affiliation_strings":["Microsoft Research Limited, Redmond, WA, USA","Microsoft Research, One Microsoft Way, Redmond, WA, 98052 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, One Microsoft Way, Redmond, WA, 98052 USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012153296","display_name":"Jasha Droppo","orcid":"https://orcid.org/0000-0001-6097-0090"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jasha Droppo","raw_affiliation_strings":["Microsoft Research Limited, Redmond, WA, USA","Microsoft Research, One Microsoft Way, Redmond, WA, 98052 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, One Microsoft Way, Redmond, WA, 98052 USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087876461","display_name":"H.S. Malvar","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Henrique S. Malvar","raw_affiliation_strings":["Microsoft Research Limited, Redmond, WA, USA","Microsoft Research, One Microsoft Way, Redmond, WA, 98052 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, One Microsoft Way, Redmond, WA, 98052 USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111957484","display_name":"Alex Acero","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Acero","raw_affiliation_strings":["Microsoft Research Limited, Redmond, WA, USA","Microsoft Research, One Microsoft Way, Redmond, WA, 98052 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, One Microsoft Way, Redmond, WA, 98052 USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"52","issue":null,"first_page":"5148","last_page":"5151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.836756706237793},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8255549669265747},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.7002245783805847},{"id":"https://openalex.org/keywords/wideband-audio","display_name":"Wideband audio","score":0.6842426061630249},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.6744463443756104},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.6104305386543274},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6037428975105286},{"id":"https://openalex.org/keywords/narrowband","display_name":"Narrowband","score":0.5720248222351074},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5430516600608826},{"id":"https://openalex.org/keywords/wideband","display_name":"Wideband","score":0.49686673283576965},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4886534512042999},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4436291456222534},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.43589285016059875},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.3970739245414734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32126474380493164},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.10869506001472473},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.10260742902755737},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.10059332847595215},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.09923255443572998},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09126055240631104},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07097625732421875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.836756706237793},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8255549669265747},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.7002245783805847},{"id":"https://openalex.org/C173391809","wikidata":"https://www.wikidata.org/wiki/Q2740189","display_name":"Wideband audio","level":5,"score":0.6842426061630249},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.6744463443756104},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.6104305386543274},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6037428975105286},{"id":"https://openalex.org/C2776096036","wikidata":"https://www.wikidata.org/wiki/Q1140483","display_name":"Narrowband","level":2,"score":0.5720248222351074},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5430516600608826},{"id":"https://openalex.org/C2780202535","wikidata":"https://www.wikidata.org/wiki/Q4524457","display_name":"Wideband","level":2,"score":0.49686673283576965},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4886534512042999},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4436291456222534},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.43589285016059875},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.3970739245414734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32126474380493164},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.10869506001472473},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.10260742902755737},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.10059332847595215},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.09923255443572998},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09126055240631104},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07097625732421875},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2011.5947516","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.891.3387","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.891.3387","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mirlab.org/conference_papers/International_Conference/ICASSP%202011/pdfs/0005148.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.896.6454","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.896.6454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/pubs/144091/0005148.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.550000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W183623625","https://openalex.org/W382624523","https://openalex.org/W1575842579","https://openalex.org/W2055815603","https://openalex.org/W2115914516","https://openalex.org/W2476401852","https://openalex.org/W6612950508"],"related_works":["https://openalex.org/W2060409740","https://openalex.org/W2115236569","https://openalex.org/W2106874932","https://openalex.org/W1542588102","https://openalex.org/W1578591928","https://openalex.org/W1570121624","https://openalex.org/W2496295964","https://openalex.org/W2020464095","https://openalex.org/W2336887028","https://openalex.org/W69679757"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,10,41,65,110],"new":[3,87],"transform":[4,105],"speech":[5,19,24,51,54,78,121],"codec":[6,106],"that":[7,43,82],"jointly":[8],"encodes":[9],"wideband":[11,16,26,70],"waveform":[12,36],"and":[13,17,30,126],"its":[14],"corresponding":[15],"narrowband":[18],"recognition":[20,79],"features.":[21,52,71],"For":[22],"distributed":[23],"recognition,":[25],"features":[27,56],"are":[28],"compressed":[29],"transmitted":[31],"as":[32],"side":[33],"information.":[34],"The":[35],"is":[37,122],"then":[38],"encoded":[39],"in":[40,94,113],"manner":[42],"exploits":[44],"the":[45,50,61,68,103],"information":[46],"already":[47],"captured":[48],"by":[49,63],"Narrowband":[53],"acoustic":[55],"can":[57],"be":[58],"synthesized":[59],"at":[60,83],"server":[62],"applying":[64],"transformation":[66],"to":[67,99,109,134],"decoded":[69],"An":[72],"evaluation":[73],"conducted":[74],"on":[75],"an":[76],"in-car":[77],"task":[80],"show":[81],"16":[84],"kbps":[85],"our":[86],"system":[88],"typically":[89],"shows":[90],"essentially":[91],"no":[92],"impact":[93],"word":[95,114],"error":[96,115],"rate":[97],"compared":[98],"uncompressed":[100],"audio,":[101],"whereas":[102],"standard":[104],"produces":[107],"up":[108],"20%":[111],"increase":[112],"rate.":[116],"In":[117],"addition,":[118],"good":[119],"quality":[120],"obtained":[123],"for":[124],"playback":[125],"transcription,":[127],"with":[128],"PESQ":[129],"scores":[130],"ranging":[131],"from":[132],"3.2":[133],"3.4.":[135]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
