{"id":"https://openalex.org/W4385823008","doi":"https://doi.org/10.21437/interspeech.2023-2506","title":"Strategies for Improving Low Resource Speech to Text Translation Relying on Pre-trained ASR Models","display_name":"Strategies for Improving Low Resource Speech to Text Translation Relying on Pre-trained ASR Models","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823008","doi":"https://doi.org/10.21437/interspeech.2023-2506"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-2506","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5008468618","display_name":"Santosh Kesiraju","orcid":"https://orcid.org/0000-0002-3725-742X"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Santosh Kesiraju","raw_affiliation_strings":["Speech@FIT, Brno University of Technology, Czechia"],"affiliations":[{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092081352","display_name":"Marek Sarva\u0161","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Marek Sarva\u0161","raw_affiliation_strings":["Speech@FIT, Brno University of Technology, Czechia"],"affiliations":[{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078840047","display_name":"Tom\u00e1\u0161 Pavl\u0131\u0301\u010dek","orcid":"https://orcid.org/0000-0003-2581-2657"},"institutions":[{"id":"https://openalex.org/I4210110967","display_name":"Phonexia (Czechia)","ror":"https://ror.org/01q216d88","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210110967"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Tom\u00e1\u0161 Pavl\u00ed\u010dek","raw_affiliation_strings":["Phonexia, Czechia"],"affiliations":[{"raw_affiliation_string":"Phonexia, Czechia","institution_ids":["https://openalex.org/I4210110967"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050955407","display_name":"C\u00e9cile Macaire","orcid":null},"institutions":[{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"C\u00e9cile Macaire","raw_affiliation_strings":["Univ. Grenoble Alpes, France"],"affiliations":[{"raw_affiliation_string":"Univ. Grenoble Alpes, France","institution_ids":["https://openalex.org/I899635006"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092081353","display_name":"Alejandro Ciuba","orcid":null},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alejandro Ciuba","raw_affiliation_strings":["University of Pittsburgh, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, USA","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5008468618"],"corresponding_institution_ids":["https://openalex.org/I60587646"],"apc_list":null,"apc_paid":null,"fwci":0.8757,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78737818,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2148","last_page":"2152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7741000056266785,"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":0.7741000056266785,"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":0.7468000054359436,"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":0.8008735179901123},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5609172582626343},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5558578968048096},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5455819964408875},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5220065712928772},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.47504711151123047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45233818888664246},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4507730007171631}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8008735179901123},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5609172582626343},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5558578968048096},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5455819964408875},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5220065712928772},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.47504711151123047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45233818888664246},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4507730007171631},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-2506","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2250342921","https://openalex.org/W2573062194","https://openalex.org/W2899274165","https://openalex.org/W2963250244","https://openalex.org/W2963532001","https://openalex.org/W2963979492","https://openalex.org/W2964172053","https://openalex.org/W2972389417","https://openalex.org/W3006988520","https://openalex.org/W3007871436","https://openalex.org/W3037217258","https://openalex.org/W3107826490","https://openalex.org/W3163093788","https://openalex.org/W3172862365","https://openalex.org/W3174446152","https://openalex.org/W3177132412","https://openalex.org/W3213029956","https://openalex.org/W4224308495","https://openalex.org/W4281982771","https://openalex.org/W4285158119","https://openalex.org/W4285188582","https://openalex.org/W4385245566","https://openalex.org/W4385572885","https://openalex.org/W4386566728"],"related_works":["https://openalex.org/W2610387714","https://openalex.org/W1512718085","https://openalex.org/W1484029852","https://openalex.org/W4379525811","https://openalex.org/W2167662847","https://openalex.org/W2186089609","https://openalex.org/W193726211","https://openalex.org/W2977183928","https://openalex.org/W3198474835","https://openalex.org/W1569841287"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"techniques":[3],"and":[4,22,31,69,77,92],"findings":[5],"for":[6,38,65,98],"improving":[7],"the":[8,35,59,74,79,96],"performance":[9],"of":[10,106],"low-resource":[11,56],"speech":[12,47],"to":[13,72,86],"text":[14],"translation":[15,66],"(ST).We":[16],"conducted":[17],"experiments":[18],"on":[19,26,115],"both":[20],"simulated":[21],"reallow":[23],"resource":[24],"setups,":[25],"language":[27],"pairs":[28],"English":[29],"-Portuguese,":[30],"Tamasheq":[32,116],"-French":[33,117],"respectively.Using":[34],"encoder-decoder":[36],"framework":[37],"ST,":[39],"our":[40,82,109],"results":[41],"show":[42],"that":[43,94],"a":[44,52],"multilingual":[45],"automatic":[46],"recognition":[48],"system":[49],"acts":[50],"as":[51,61],"good":[53],"initialization":[54],"under":[55],"scenarios.Furthermore,":[57],"using":[58],"CTC":[60],"an":[62],"additional":[63],"objective":[64],"during":[67],"training":[68],"decoding":[70],"helps":[71],"reorder":[73],"internal":[75],"representations":[76],"improves":[78],"final":[80],"translation.Through":[81],"experiments,":[83],"we":[84],"try":[85],"identify":[87],"various":[88],"factors":[89],"(initializations,":[90],"objectives,":[91],"hyperparameters)":[93],"contribute":[95],"most":[97],"improvements":[99],"in":[100],"lowresource":[101],"setups.With":[102],"only":[103],"300":[104],"hours":[105],"pre-training":[107],"data,":[108,118],"model":[110],"achieved":[111],"7.3":[112],"BLEU":[113],"score":[114],"outperforming":[119],"prior":[120],"published":[121],"works":[122],"from":[123],"IWSLT":[124],"2022":[125],"by":[126],"1.6":[127],"points.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}