{"id":"https://openalex.org/W4392902773","doi":"https://doi.org/10.1109/icassp48485.2024.10446214","title":"Speak While You Think: Streaming Speech Synthesis During Text Generation","display_name":"Speak While You Think: Streaming Speech Synthesis During Text Generation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902773","doi":"https://doi.org/10.1109/icassp48485.2024.10446214"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446214","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":"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/A5055632925","display_name":"Avihu Dekel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Avihu Dekel","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035109881","display_name":"Slava Shechtman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Slava Shechtman","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003690515","display_name":"Raul Castro Fernandez","orcid":"https://orcid.org/0000-0001-7675-6080"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raul Fernandez","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049318367","display_name":"David Haws","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Haws","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054462082","display_name":"Zvi Kons","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zvi Kons","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053864983","display_name":"Ron Hoory","orcid":"https://orcid.org/0009-0006-1327-5160"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ron Hoory","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1383,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8844654,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11931","last_page":"11935"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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":0.9987000226974487,"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":0.8449486494064331},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7721884250640869},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.725865364074707},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5591727495193481},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5580875873565674},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5375874042510986},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4254641830921173},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40777045488357544},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37901514768600464},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07239946722984314}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8449486494064331},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7721884250640869},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.725865364074707},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5591727495193481},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5580875873565674},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5375874042510986},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4254641830921173},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40777045488357544},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37901514768600464},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07239946722984314},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446214","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":30,"referenced_works":["https://openalex.org/W2079735306","https://openalex.org/W2519091744","https://openalex.org/W2802023636","https://openalex.org/W2963091184","https://openalex.org/W2964084166","https://openalex.org/W2964243274","https://openalex.org/W2972489453","https://openalex.org/W2972610613","https://openalex.org/W3091928890","https://openalex.org/W3095389792","https://openalex.org/W3096518646","https://openalex.org/W3104081910","https://openalex.org/W3125687907","https://openalex.org/W3144667183","https://openalex.org/W3198061281","https://openalex.org/W3198848374","https://openalex.org/W4224629880","https://openalex.org/W4288089799","https://openalex.org/W4297841509","https://openalex.org/W4297841830","https://openalex.org/W4313679638","https://openalex.org/W4381786045","https://openalex.org/W4385245566","https://openalex.org/W4385822623","https://openalex.org/W6769627184","https://openalex.org/W6784545093","https://openalex.org/W6804171790","https://openalex.org/W6810738896","https://openalex.org/W6845479124","https://openalex.org/W6848735303"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"demonstrate":[4],"impressive":[5],"capabilities,":[6],"yet":[7],"interaction":[8],"with":[9],"these":[10],"models":[11],"is":[12,29,45],"mostly":[13],"facilitated":[14],"through":[15],"text.":[16],"Using":[17],"Text-To-Speech":[18],"to":[19,40,69,74,109],"synthesize":[20,41],"LLM":[21,50],"outputs":[22],"typically":[23],"results":[24,97],"in":[25,72],"notable":[26],"latency,":[27],"which":[28,51],"impractical":[30],"for":[31],"fluent":[32],"voice":[33],"conversations.":[34,112],"We":[35],"propose":[36],"LLM2Speech,":[37],"an":[38,49],"architecture":[39],"speech":[42],"while":[43,65,105],"text":[44,89],"being":[46],"generated":[47],"by":[48],"yields":[52],"significant":[53],"latency":[54,108],"reduction.":[55],"LLM2Speech":[56,100],"mimics":[57],"the":[58,67,79,83,88,102,107],"predictions":[59],"of":[60,82,87],"a":[61,85],"non-streaming":[62],"teacher":[63],"model":[64],"limiting":[66],"exposure":[68],"future":[70],"context":[71],"order":[73],"enable":[75,110],"streaming.":[76],"It":[77],"exploits":[78],"hidden":[80],"embeddings":[81],"LLM,":[84],"by-product":[86],"generation":[90],"that":[91,99],"contains":[92],"informative":[93],"semantic":[94],"context.":[95],"Experimental":[96],"show":[98],"maintains":[101],"teacher\u2019s":[103],"quality":[104],"reducing":[106],"natural":[111]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}