{"id":"https://openalex.org/W2749006145","doi":"https://doi.org/10.21437/interspeech.2017-1340","title":"Learning Word Vector Representations Based on Acoustic Counts","display_name":"Learning Word Vector Representations Based on Acoustic Counts","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2749006145","doi":"https://doi.org/10.21437/interspeech.2017-1340","mag":"2749006145"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1340","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/f3669a68-32c7-4a66-b211-1aee30499aea","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109494794","display_name":"Manuel Sam Ribeiro","orcid":"https://orcid.org/0000-0001-8096-2231"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"M. Sam Ribeiro","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110238677","display_name":"Oliver Watts","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oliver Watts","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5109494794"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":0.5851,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75727787,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"799","last_page":"803"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/computer-science","display_name":"Computer science","score":0.733449399471283},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6199376583099365},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5961615443229675},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5444338321685791},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5027022361755371},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.4907189607620239},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.48034632205963135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4692798852920532},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4513895809650421},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4438059329986572},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.43466728925704956},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4113519489765167},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3208169639110565},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19325396418571472}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.733449399471283},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6199376583099365},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5961615443229675},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5444338321685791},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5027022361755371},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.4907189607620239},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.48034632205963135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4692798852920532},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4513895809650421},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4438059329986572},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.43466728925704956},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4113519489765167},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3208169639110565},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19325396418571472},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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":3,"locations":[{"id":"doi:10.21437/interspeech.2017-1340","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/f3669a68-32c7-4a66-b211-1aee30499aea","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f3669a68-32c7-4a66-b211-1aee30499aea","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ribeiro, M S, Watts, O & Yamagishi, J 2017, Learning word vector representations based on acoustic counts. in Interspeech 2017. Interspeech, International Speech Communication Association, pp. 799-803, Interspeech 2017, Stockholm, Sweden, 20/08/17. https://doi.org/10.21437/Interspeech.2017-1340","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/f3669a68-32c7-4a66-b211-1aee30499aea","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/learning-word-vector-representations-based-on-acoustic-counts(f3669a68-32c7-4a66-b211-1aee30499aea).html","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/f3669a68-32c7-4a66-b211-1aee30499aea","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f3669a68-32c7-4a66-b211-1aee30499aea","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ribeiro, M S, Watts, O & Yamagishi, J 2017, Learning word vector representations based on acoustic counts. in Interspeech 2017. Interspeech, International Speech Communication Association, pp. 799-803, Interspeech 2017, Stockholm, Sweden, 20/08/17. https://doi.org/10.21437/Interspeech.2017-1340","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W5866514","https://openalex.org/W174066062","https://openalex.org/W193898724","https://openalex.org/W1527151497","https://openalex.org/W1571950845","https://openalex.org/W1578102511","https://openalex.org/W1614298861","https://openalex.org/W1615991656","https://openalex.org/W1662133657","https://openalex.org/W1937075317","https://openalex.org/W1977362129","https://openalex.org/W1978400666","https://openalex.org/W1992009922","https://openalex.org/W2029190953","https://openalex.org/W2099062766","https://openalex.org/W2102003408","https://openalex.org/W2111284386","https://openalex.org/W2119929864","https://openalex.org/W2150612204","https://openalex.org/W2152205330","https://openalex.org/W2158139315","https://openalex.org/W2164019165","https://openalex.org/W2181715383","https://openalex.org/W2250539671","https://openalex.org/W2251803266","https://openalex.org/W2344211044","https://openalex.org/W2517266855","https://openalex.org/W2525520955","https://openalex.org/W2598638573","https://openalex.org/W2950577311","https://openalex.org/W4327693937"],"related_works":["https://openalex.org/W2006251942","https://openalex.org/W2364741597","https://openalex.org/W1492103595","https://openalex.org/W1864774435","https://openalex.org/W946352265","https://openalex.org/W3020787026","https://openalex.org/W2334479858","https://openalex.org/W2799209613","https://openalex.org/W2793786119","https://openalex.org/W1507702947"],"abstract_inverted_index":{"This":[0,21],"paper":[1],"presents":[2],"a":[3,57,63,73,80,100,136,159],"simple":[4],"count-based":[5,164],"approach":[6],"to":[7,50,110],"learning":[8],"word":[9,105],"vector":[10],"representations":[11,126],"by":[12],"leveraging":[13],"statistics":[14],"of":[15,23,29,40,56,60,65,75,85,102,113,132,153],"cooccurrences":[16],"between":[17],"text":[18],"and":[19,53,91,120,151],"speech.":[20],"type":[22],"representation":[24],"requires":[25],"two":[26],"discrete":[27,76],"sequences":[28],"units":[30],"defined":[31],"across":[32],"modalities.":[33],"Two":[34],"possible":[35],"methods":[36],"for":[37,116,129],"the":[38,83,111,130,145,166],"discretization":[39,147],"an":[41],"acoustic":[42,77,89,114,133,149],"signal":[43],"are":[44,47,108,127,156],"presented,":[45],"which":[46],"then":[48],"applied":[49,109],"fundamental":[51],"frequency":[52],"energy":[54],"contours":[55],"transcribed":[58],"corpus":[59],"speech,":[61],"yielding":[62],"sequence":[64,74],"textual":[66,86],"objects":[67,87],"(e.g.":[68],"words,":[69],"syllables)":[70],"aligned":[71],"with":[72,88,95],"events.":[78],"Constructing":[79],"matrix":[81,96],"recording":[82],"co-occurrence":[84],"events":[90],"reducing":[92],"its":[93],"dimensionality":[94],"decomposition":[97],"results":[98,122],"in":[99,135],"set":[101],"context-independent":[103],"representations<br/>of":[104],"types.":[106],"These":[107],"task":[112],"modelling":[115],"speech":[117],"synthesis;":[118],"objective":[119],"subjective":[121],"indicate":[123],"that":[124,144,168],"these":[125,163],"useful":[128],"generation":[131],"parameters":[134],"text-to-speech":[137],"(TTS)":[138],"system.":[139],"In":[140],"general,":[141],"we":[142],"observe":[143],"more":[146],"approaches,":[148],"signals,":[150],"levels":[152],"linguistic":[154],"analysis":[155],"incorporated":[157],"into":[158],"TTS":[160,169],"system":[161,170],"via":[162],"representations,":[165],"better":[167],"performs.":[171]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}