{"id":"https://openalex.org/W2796768192","doi":"https://doi.org/10.21437/interspeech.2018-2194","title":"Unspeech: Unsupervised Speech Context Embeddings","display_name":"Unspeech: Unsupervised Speech Context Embeddings","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2796768192","doi":"https://doi.org/10.21437/interspeech.2018-2194","mag":"2796768192"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-2194","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1804.06775","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078278300","display_name":"Benjamin Milde","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Benjamin Milde","raw_affiliation_strings":["Technical University of Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021287757","display_name":"Chris Biemann","orcid":"https://orcid.org/0000-0002-8449-9624"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chris Biemann","raw_affiliation_strings":["Universit\u00e4t Hamburg, Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Universit\u00e4t Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5078278300"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":0.19856246,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56324434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2693","last_page":"2697"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9954000115394592,"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/T12031","display_name":"Speech and dialogue systems","score":0.9776999950408936,"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":0.7959475517272949},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6867634654045105},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6415331363677979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5771341919898987},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5711899399757385},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5654201507568359},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.488844096660614},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.48180335760116577},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.46917444467544556},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.43964749574661255},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4275243878364563},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.42338842153549194},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10367047786712646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7959475517272949},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6867634654045105},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6415331363677979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5771341919898987},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5711899399757385},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5654201507568359},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.488844096660614},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.48180335760116577},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.46917444467544556},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.43964749574661255},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4275243878364563},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.42338842153549194},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10367047786712646},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2018-2194","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1804.06775","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.06775","pdf_url":"https://arxiv.org/pdf/1804.06775","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:2796768192","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1804.06775v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1804.06775","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1804.06775","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1804.06775","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.06775","pdf_url":"https://arxiv.org/pdf/1804.06775","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2796768192.pdf","grobid_xml":"https://content.openalex.org/works/W2796768192.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2963317665","https://openalex.org/W2916685081","https://openalex.org/W3011209123","https://openalex.org/W3046492833","https://openalex.org/W3037580942","https://openalex.org/W2772376594","https://openalex.org/W2794739275","https://openalex.org/W2766579050","https://openalex.org/W3203561692","https://openalex.org/W3099254168","https://openalex.org/W2468716020","https://openalex.org/W3164689641","https://openalex.org/W2262099980","https://openalex.org/W3131709275","https://openalex.org/W3126607341","https://openalex.org/W2584414011","https://openalex.org/W3150635893","https://openalex.org/W3095298905","https://openalex.org/W3104842308","https://openalex.org/W2972705840"],"abstract_inverted_index":{"We":[0,51,104],"introduce":[1],"\"Unspeech\"":[2],"embeddings,":[3],"which":[4],"are":[5],"based":[6,42],"on":[7,21,43,66,81],"unsupervised":[8],"learning":[9,40],"of":[10,26],"context":[11,44,74],"feature":[12,75],"representations":[13],"for":[14],"spoken":[15],"language.":[16],"The":[17],"embeddings":[18,62],"were":[19],"trained":[20,80],"up":[22],"to":[23,59,85],"9500":[24],"hours":[25],"crawled":[27],"English":[28],"speech":[29,91],"data":[30,92],"without":[31],"transcriptions":[32],"or":[33],"speaker":[34,67],"information,":[35],"by":[36],"using":[37],"a":[38,53,73,114],"straightforward":[39],"objective":[41],"and":[45,63,71,109],"non-context":[46],"discrimination":[47],"with":[48],"negative":[49],"sampling.":[50],"use":[52],"Siamese":[54],"convolutional":[55],"neural":[56],"network":[57],"architecture":[58],"train":[60],"Unspeech":[61,111],"evaluate":[64],"them":[65],"comparison,":[68],"utterance":[69],"clustering":[70],"as":[72],"in":[76],"TDNN-HMM":[77],"acoustic":[78],"models":[79,112],"TED-LIUM,":[82],"comparing":[83],"it":[84],"i-vector":[86],"baselines.":[87],"Particularly":[88],"decoding":[89],"out-of-domain":[90],"from":[93],"the":[94],"recently":[95],"released":[96],"Common":[97],"Voice":[98],"corpus":[99],"shows":[100],"consistent":[101],"WER":[102],"reductions.":[103],"release":[105],"our":[106],"source":[107,117],"code":[108],"pre-trained":[110],"under":[113],"permissive":[115],"open":[116],"license.":[118]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}