{"id":"https://openalex.org/W3196659080","doi":"https://doi.org/10.21437/interspeech.2021-526","title":"AlloST: Low-Resource Speech Translation Without Source Transcription","display_name":"AlloST: Low-Resource Speech Translation Without Source Transcription","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196659080","doi":"https://doi.org/10.21437/interspeech.2021-526","mag":"3196659080"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-526","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5002404521","display_name":"Yao-Fei Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yao-Fei Cheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048338308","display_name":"Hung-Shin Lee","orcid":"https://orcid.org/0000-0001-7044-9434"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hung-Shin Lee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5002404521"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6316,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.86671687,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2252","last_page":"2256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9876000285148621,"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":0.8357819318771362},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6838942766189575},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.629541277885437},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.56951904296875},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5591868162155151},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5202839970588684},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5167888402938843},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5074765086174011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4679763615131378},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4496479630470276},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4399200677871704},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.43714478611946106},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4326721727848053},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4310038387775421},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.43062639236450195},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10244473814964294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8357819318771362},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6838942766189575},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.629541277885437},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.56951904296875},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5591868162155151},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5202839970588684},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5167888402938843},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5074765086174011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4679763615131378},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4496479630470276},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4399200677871704},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.43714478611946106},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4326721727848053},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4310038387775421},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.43062639236450195},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10244473814964294},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-526","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7799999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2114097550","https://openalex.org/W2918559346","https://openalex.org/W84309476","https://openalex.org/W4200502108","https://openalex.org/W2949968076","https://openalex.org/W3016124757","https://openalex.org/W2935811960","https://openalex.org/W2969407538","https://openalex.org/W2917049097","https://openalex.org/W2069071271"],"abstract_inverted_index":{"The":[0,66],"end-to-end":[1],"architecture":[2],"has":[3],"made":[4],"promising":[5],"progress":[6],"in":[7,29,148],"speech":[8,38],"translation":[9],"(ST).":[10],"However,":[11],"the":[12,30,36,76,79,87,90,93,99,112,132,153,165,169,176],"ST":[13,22,48],"task":[14],"is":[15,68,171],"still":[16],"challenging":[17],"under":[18],"low-resource":[19],"conditions.":[20],"Most":[21],"models":[23],"have":[24],"shown":[25],"unsatisfactory":[26],"results,":[27],"especially":[28],"absence":[31],"of":[32,92,115,134,175],"word":[33],"information":[34,146],"from":[35],"source":[37,52,181],"utterance.":[39],"In":[40,103],"this":[41],"study,":[42],"we":[43,110],"survey":[44],"methods":[45],"to":[46,97,105,131,173],"improve":[47],"performance":[49,170],"without":[50],"using":[51,180],"transcription,":[53],"and":[54,82,86,156,168],"propose":[55],"a":[56,61,122,126,136],"learning":[57],"framework":[58,67],"that":[59,161,174],"utilizes":[60],"language-independent":[62],"universal":[63],"phone":[64,123],"recognizer.":[65],"based":[69],"on":[70,152],"an":[71],"attention-based":[72],"sequence-to-sequence":[73],"model,":[74],"where":[75],"encoder":[77],"generates":[78],"phonetic":[80],"embeddings":[81],"phone-aware":[83],"acoustic":[84],"representations,":[85],"decoder":[88],"controls":[89],"fusion":[91,108],"two":[94],"embedding":[95],"streams":[96],"produce":[98],"target":[100],"token":[101],"sequence.":[102,129],"addition":[104],"investigating":[106],"different":[107],"strategies,":[109],"explore":[111],"specific":[113],"usage":[114],"byte":[116],"pair":[117],"encoding":[118],"(BPE),":[119],"which":[120],"compresses":[121],"sequence":[124,138],"into":[125],"syllable-like":[127],"segmented":[128,137],"Due":[130],"conversion":[133],"symbols,":[135],"represents":[139],"not":[140],"only":[141],"pronunciation":[142],"but":[143],"also":[144],"language-dependent":[145],"lacking":[147],"phones.":[149],"Experiments":[150],"conducted":[151],"Fisher":[154],"Spanish-English":[155],"Taigi-Mandarin":[157],"drama":[158],"corpora":[159],"show":[160],"our":[162],"method":[163,179],"outperforms":[164],"conformer-based":[166],"baseline,":[167],"close":[172],"existing":[177],"best":[178],"transcription.":[182]},"counts_by_year":[{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}