{"id":"https://openalex.org/W4415433242","doi":"https://doi.org/10.21437/interspeech.2025-1292","title":"Speechless: Speech Instruction Training Without Speech for Low Resource Languages","display_name":"Speechless: Speech Instruction Training Without Speech for Low Resource Languages","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433242","doi":"https://doi.org/10.21437/interspeech.2025-1292"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1292","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1292","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.17417","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114534344","display_name":"Alan Dao","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Alan Dao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114534345","display_name":"Dinh Bach Vu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dinh Bach Vu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114534346","display_name":"Huy Hoang Ha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huy Hoang Ha","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112718370","display_name":"Tuan Le Duc Anh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tuan Le Duc Anh","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shreyas Gopal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shreyas Gopal","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112025134","display_name":"Yue Heng Yeo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Heng Yeo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120093850","display_name":"Warren Keng Hoong Low","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Warren Keng Hoong Low","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102941083","display_name":"Jia Qi Yip","orcid":"https://orcid.org/0000-0002-9896-9658"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Qi Yip","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5114534344"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.26,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91212233,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3239","last_page":"3243"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.29089999198913574,"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/T12031","display_name":"Speech and dialogue systems","score":0.29089999198913574,"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/process","display_name":"Process (computing)","score":0.5674999952316284},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4805999994277954},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4652000069618225},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.41679999232292175},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4138000011444092},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.41359999775886536},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.40639999508857727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8486999869346619},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5674999952316284},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5486999750137329},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4805999994277954},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47369998693466187},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4652000069618225},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.41679999232292175},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4138000011444092},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.41359999775886536},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3968000113964081},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.33739998936653137},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.26919999718666077}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-1292","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1292","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.17417","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.17417","pdf_url":"https://arxiv.org/pdf/2505.17417","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.17417","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.17417","pdf_url":"https://arxiv.org/pdf/2505.17417","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415433242.pdf","grobid_xml":"https://content.openalex.org/works/W4415433242.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"growth":[2],"of":[3,27,36],"voice":[4,132],"assistants":[5],"powered":[6],"by":[7,77,93],"large":[8],"language":[9],"models":[10,45],"(LLM)":[11],"has":[12],"highlighted":[13],"a":[14,33,57,127],"need":[15,87],"for":[16,43,88,134],"speech":[17,28,37,55],"instruction":[18,38],"data":[19],"to":[20,46,67,106,116,130],"train":[21],"these":[22],"systems.":[23],"Despite":[24],"the":[25,81,86,99,114],"abundance":[26],"recognition":[29],"data,":[30,39],"there":[31],"is":[32,41,126],"notable":[34],"scarcity":[35],"which":[40,62],"essential":[42],"fine-tuning":[44],"understand":[47,117],"and":[48],"execute":[49],"spoken":[50,118],"commands.":[51],"Generating":[52],"high-quality":[53],"synthetic":[54,95],"requires":[56],"good":[58],"text-to-speech":[59],"(TTS)":[60],"model,":[61],"may":[63],"not":[64],"be":[65,107],"available":[66],"low":[68],"resource":[69],"languages.":[70,136],"Our":[71],"novel":[72],"approach":[73,129],"addresses":[74],"this":[75,92],"challenge":[76],"halting":[78],"synthesis":[79],"at":[80],"semantic":[82,96],"representation":[83],"level,":[84],"bypassing":[85],"TTS.":[89],"We":[90],"achieve":[91],"aligning":[94],"representations":[97],"with":[98],"pre-trained":[100],"Whisper":[101],"encoder,":[102],"enabling":[103],"an":[104],"LLM":[105],"fine-tuned":[108],"on":[109],"text":[110],"instructions":[111,119],"while":[112],"maintaining":[113],"ability":[115],"during":[120],"inference.":[121],"This":[122],"simplified":[123],"training":[124],"process":[125],"promising":[128],"building":[131],"assistant":[133],"low-resource":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-23T00:00:00"}
