{"id":"https://openalex.org/W7125584192","doi":"https://doi.org/10.1109/iciip68302.2025.11346348","title":"Speech-to-Image Generation Using Audio Embeddings and Latent Diffusion Models","display_name":"Speech-to-Image Generation Using Audio Embeddings and Latent Diffusion Models","publication_year":2025,"publication_date":"2025-11-27","ids":{"openalex":"https://openalex.org/W7125584192","doi":"https://doi.org/10.1109/iciip68302.2025.11346348"},"language":"en","primary_location":{"id":"doi:10.1109/iciip68302.2025.11346348","doi":"https://doi.org/10.1109/iciip68302.2025.11346348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iciip68302.2025.11346348","pdf_url":null,"source":{"id":"https://openalex.org/S4363608454","display_name":"International Conference on Image Information Processing (ICIIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Eighth International Conference on Image Information Processing (ICIIP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5123766596","display_name":"Chandan Rani S R","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I65674248","display_name":"Visvesvaraya Technological University","ror":"https://ror.org/00ha14p11","country_code":"IN","type":"education","lineage":["https://openalex.org/I65674248"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chandan Rani S R","raw_affiliation_strings":["Visvesvaraya Technological University,Department of CS&E RNS Institute of Technology,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visvesvaraya Technological University,Department of CS&E RNS Institute of Technology,Bangalore,India","institution_ids":["https://openalex.org/I65674248"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039566295","display_name":"N P Kavya","orcid":"https://orcid.org/0000-0002-7908-1346","observed_orcids":["https://orcid.org/0000-0002-7908-1346"]},"institutions":[{"id":"https://openalex.org/I65674248","display_name":"Visvesvaraya Technological University","ror":"https://ror.org/00ha14p11","country_code":"IN","type":"education","lineage":["https://openalex.org/I65674248"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"N P Kavya","raw_affiliation_strings":["Visvesvaraya Technological University,Department of CS&E RNS Institute of Technology,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visvesvaraya Technological University,Department of CS&E RNS Institute of Technology,Bangalore,India","institution_ids":["https://openalex.org/I65674248"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I65674248"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"793","last_page":"799"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5404999852180481,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5404999852180481,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.45239999890327454,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.003599999938160181,"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/audio-embeddings","display_name":"audio embeddings","score":0.8050000071525574},{"id":"https://openalex.org/keywords/latent-diffusion-models","display_name":"latent diffusion models","score":0.9850000143051147},{"id":"https://openalex.org/keywords/audio-clips","display_name":"audio clips","score":0.8479999899864197},{"id":"https://openalex.org/keywords/audio-captioning","display_name":"audio captioning","score":0.6029999852180481},{"id":"https://openalex.org/keywords/paralanguage","display_name":"paralinguistic features","score":0.777999997138977},{"id":"https://openalex.org/keywords/prosodic-features","display_name":"prosodic features","score":0.8050000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7450000047683716},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5472999811172485},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5235999822616577},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4740999937057495},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43320000171661377},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40049999952316284},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.3831000030040741},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.37929999828338623},{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.35580000281333923},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27129998803138733},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iciip68302.2025.11346348","doi":"https://doi.org/10.1109/iciip68302.2025.11346348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iciip68302.2025.11346348","pdf_url":null,"source":{"id":"https://openalex.org/S4363608454","display_name":"International Conference on Image Information Processing (ICIIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Eighth International Conference on Image Information Processing (ICIIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2137010615","https://openalex.org/W3095030004","https://openalex.org/W3111551570","https://openalex.org/W3153469116","https://openalex.org/W3176445421","https://openalex.org/W4221068645","https://openalex.org/W4284898017","https://openalex.org/W4312933868","https://openalex.org/W4372266552","https://openalex.org/W4385822589","https://openalex.org/W4386076291","https://openalex.org/W4387187602","https://openalex.org/W4390872674"],"related_works":["https://openalex.org/W7167204203","https://openalex.org/W4385482641","https://openalex.org/W7130362549","https://openalex.org/W3128001455","https://openalex.org/W7104275497","https://openalex.org/W4387445713","https://openalex.org/W3123798147","https://openalex.org/W4327654059","https://openalex.org/W7218428013","https://openalex.org/W3155217823"],"abstract_inverted_index":{"Speech-driven":[0],"image":[1,138],"generation":[2,50,167],"is":[3],"an":[4,52,73],"emerging":[5],"multimodal":[6,166],"learning":[7,45],"task":[8],"that":[9,107],"enables":[10],"the":[11,81,97,116,152],"creation":[12],"of":[13,84,154],"visual":[14,129],"content":[15],"directly":[16],"from":[17,69],"spoken":[18],"descriptions.":[19],"Most":[20],"existing":[21],"systems":[22],"depend":[23],"on":[24,115],"intermediate":[25],"text":[26,136],"transcription":[27],"or":[28],"require":[29],"large":[30],"paired":[31],"audio\u2013image":[32],"datasets,":[33],"limiting":[34],"their":[35],"applicability":[36],"in":[37,143],"realistic":[38],"environments.":[39],"This":[40,94],"paper":[41],"presents":[42],"a":[43,57,85,90,160],"deep":[44],"framework":[46],"for":[47,163],"end-to-end":[48],"speech-to-image":[49],"using":[51,72],"audio-CLIP":[53],"encoder":[54],"integrated":[55],"with":[56,140],"latent":[58,82],"diffusion":[59,87],"model.":[60],"The":[61,149],"proposed":[62],"method":[63],"extracts":[64],"semantic":[65,126],"and":[66,77,104,121,128,146,158],"prosodic":[67],"features":[68],"raw":[70],"speech":[71],"audio":[74,156],"embedding":[75],"network":[76],"maps":[78],"them":[79],"to":[80,99,132],"space":[83],"pretrained":[86],"generator":[88],"through":[89],"hybrid":[91],"feature-fusion":[92],"module.":[93],"design":[95],"allows":[96],"model":[98],"utilize":[100],"both":[101],"linguistic":[102],"information":[103],"paralinguistic":[105],"cues":[106],"conventional":[108],"ASR-based":[109],"pipelines":[110],"often":[111],"discard.":[112],"Experiments":[113],"conducted":[114],"Flickr8k":[117],"Audio":[118],"Caption":[119],"Corpus":[120],"SPEECH-COCO":[122],"datasets":[123],"demonstrate":[124],"improved":[125],"alignment":[127],"quality":[130],"compared":[131],"baseline":[133],"ASR":[134],"\u2192":[135,137],"approaches,":[139],"notable":[141],"gains":[142],"CLIP":[144],"similarity":[145],"perceptual":[147],"metrics.":[148],"results":[150],"highlight":[151],"effectiveness":[153],"direct":[155],"conditioning":[157],"establish":[159],"strong":[161],"foundation":[162],"future":[164],"speech-native":[165],"systems.":[168]},"counts_by_year":[],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-01-25T00:00:00"}