{"id":"https://openalex.org/W4392904805","doi":"https://doi.org/10.1109/icassp48485.2024.10447112","title":"VoxtLM: Unified Decoder-Only Models for Consolidating Speech Recognition, Synthesis and Speech, Text Continuation Tasks","display_name":"VoxtLM: Unified Decoder-Only Models for Consolidating Speech Recognition, Synthesis and Speech, Text Continuation Tasks","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904805","doi":"https://doi.org/10.1109/icassp48485.2024.10447112"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5010858961","display_name":"Soumi Maiti","orcid":"https://orcid.org/0000-0001-6940-0115"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soumi Maiti","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033862822","display_name":"Yifan Peng","orcid":"https://orcid.org/0000-0002-8581-8674"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Peng","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046390548","display_name":"Shukjae Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I18003638","display_name":"Mando Corporation (South Korea)","ror":"https://ror.org/051v3pe92","country_code":"KR","type":"company","lineage":["https://openalex.org/I18003638"]},{"id":"https://openalex.org/I4210086063","display_name":"Handok (South Korea)","ror":"https://ror.org/00exehz38","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210086063"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Shukjae Choi","raw_affiliation_strings":["42dot Inc,Republic of Korea","42dot Inc, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"42dot Inc,Republic of Korea","institution_ids":["https://openalex.org/I18003638","https://openalex.org/I4210086063"]},{"raw_affiliation_string":"42dot Inc, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091834525","display_name":"Jee-weon Jung","orcid":"https://orcid.org/0000-0003-0505-2988"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jee-Weon Jung","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuankai Chang","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.9567,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.98750018,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"13326","last_page":"13330"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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/T10028","display_name":"Topic Modeling","score":0.9980999827384949,"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":0.8627610206604004},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7632830739021301},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.691662073135376},{"id":"https://openalex.org/keywords/continuation","display_name":"Continuation","score":0.6505333781242371},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5770701766014099},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5539360642433167},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5530220866203308},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5391682982444763},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5369055271148682},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5359450578689575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4464885890483856},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41896340250968933},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.4163632392883301},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4160038232803345}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8627610206604004},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7632830739021301},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.691662073135376},{"id":"https://openalex.org/C88626702","wikidata":"https://www.wikidata.org/wiki/Q1128903","display_name":"Continuation","level":2,"score":0.6505333781242371},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5770701766014099},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5539360642433167},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5530220866203308},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5391682982444763},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5369055271148682},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5359450578689575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4464885890483856},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41896340250968933},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4163632392883301},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4160038232803345},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":46,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2890964092","https://openalex.org/W2899575547","https://openalex.org/W2962784628","https://openalex.org/W2963250244","https://openalex.org/W2963979492","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2972394484","https://openalex.org/W2995181338","https://openalex.org/W2998572311","https://openalex.org/W3024605872","https://openalex.org/W3095410713","https://openalex.org/W3202278141","https://openalex.org/W3207222250","https://openalex.org/W3209059054","https://openalex.org/W3215615641","https://openalex.org/W4226033575","https://openalex.org/W4226120743","https://openalex.org/W4229005866","https://openalex.org/W4307323391","https://openalex.org/W4313679638","https://openalex.org/W4319862255","https://openalex.org/W4377865046","https://openalex.org/W4378501656","https://openalex.org/W4379540238","https://openalex.org/W4381786045","https://openalex.org/W4385822683","https://openalex.org/W4388017359","https://openalex.org/W4389524500","https://openalex.org/W4394671563","https://openalex.org/W6631190155","https://openalex.org/W6777028661","https://openalex.org/W6778823374","https://openalex.org/W6778883912","https://openalex.org/W6783867762","https://openalex.org/W6786696081","https://openalex.org/W6790356757","https://openalex.org/W6796464841","https://openalex.org/W6802465204","https://openalex.org/W6803092890","https://openalex.org/W6811340617","https://openalex.org/W6848735303","https://openalex.org/W6852381208","https://openalex.org/W6852781825","https://openalex.org/W6853611000"],"related_works":["https://openalex.org/W2081919107","https://openalex.org/W3115948027","https://openalex.org/W4397292310","https://openalex.org/W2811496854","https://openalex.org/W2500421879","https://openalex.org/W2537969829","https://openalex.org/W2184371793","https://openalex.org/W2405110677","https://openalex.org/W596245619","https://openalex.org/W642007152"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,43,48],"decoder-only":[3],"language":[4],"model,":[5,45],"VoxtLM,":[6],"that":[7],"can":[8],"perform":[9],"four":[10],"tasks:":[11],"speech":[12,14,19,27,31,52,58,74,77],"recognition,":[13],"synthesis,":[15,53],"text":[16,23],"generation,":[17],"and":[18,33,64,76,92,95],"continuation.":[20],"VoxtLM":[21,46,71,85],"integrates":[22],"vocabulary":[24],"with":[25,54,88],"discrete":[26],"tokens":[28,36],"from":[29,60,67],"self-supervised":[30],"features":[32],"uses":[34],"special":[35],"to":[37,42,62,69,100],"enable":[38],"multitask":[39],"learning.":[40],"Compared":[41],"single-task":[44,82],"exhibits":[47],"significant":[49],"improvement":[50],"in":[51,56],"improvements":[55],"both":[57],"intelligibility":[59],"28.9":[61],"5.6":[63],"objective":[65],"quality":[66],"2.68":[68],"3.90.":[70],"also":[72],"improves":[73],"generation":[75],"recognition":[78],"performance":[79],"over":[80],"the":[81],"counterpart.":[83],"Further,":[84],"is":[86],"trained":[87],"publicly":[89],"available":[90],"data":[91],"training":[93],"recipes":[94],"model":[96],"checkpoints":[97],"are":[98],"open-sourced":[99],"make":[101],"fully":[102],"reproducible":[103],"work.":[104]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
