{"id":"https://openalex.org/W4386764631","doi":"https://doi.org/10.1109/waspaa58266.2023.10248189","title":"Yet Another Generative Model for Room Impulse Response Estimation","display_name":"Yet Another Generative Model for Room Impulse Response Estimation","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W4386764631","doi":"https://doi.org/10.1109/waspaa58266.2023.10248189"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa58266.2023.10248189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5100402786","display_name":"Sungho Lee","orcid":"https://orcid.org/0000-0002-7421-9529"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sungho Lee","raw_affiliation_strings":["Department of Intelligence and Information"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligence and Information","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091245121","display_name":"Hyeong-Seok Choi","orcid":"https://orcid.org/0000-0001-6494-7736"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyeong-Seok Choi","raw_affiliation_strings":["Supertone, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Supertone, Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088852010","display_name":"Kyogu Lee","orcid":"https://orcid.org/0000-0002-4210-0312"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyogu Lee","raw_affiliation_strings":["Department of Intelligence and Information","AI Institute, Seoul National University","Supertone, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligence and Information","institution_ids":[]},{"raw_affiliation_string":"AI Institute, Seoul National University","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Supertone, Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7589563131332397},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6183774471282959},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5731430053710938},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.483719140291214},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4577140212059021},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.45360007882118225},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.44735515117645264},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.44073253870010376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3424319624900818},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33145779371261597},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23897278308868408},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17451220750808716},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09018000960350037},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08561357855796814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7589563131332397},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6183774471282959},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5731430053710938},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.483719140291214},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4577140212059021},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.45360007882118225},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.44735515117645264},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.44073253870010376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3424319624900818},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33145779371261597},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23897278308868408},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17451220750808716},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09018000960350037},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08561357855796814},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa58266.2023.10248189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1557831657","https://openalex.org/W1700083040","https://openalex.org/W1968834101","https://openalex.org/W2030535888","https://openalex.org/W2058341666","https://openalex.org/W2067709094","https://openalex.org/W2086381917","https://openalex.org/W2120847449","https://openalex.org/W2136682440","https://openalex.org/W2410879554","https://openalex.org/W2555915854","https://openalex.org/W2611709348","https://openalex.org/W2752796333","https://openalex.org/W2901243971","https://openalex.org/W2908510526","https://openalex.org/W2963799213","https://openalex.org/W2982059757","https://openalex.org/W3015676952","https://openalex.org/W3034772996","https://openalex.org/W3093583495","https://openalex.org/W3094502228","https://openalex.org/W3163656839","https://openalex.org/W3163735648","https://openalex.org/W3165004824","https://openalex.org/W3178031393","https://openalex.org/W3180355996","https://openalex.org/W3191448984","https://openalex.org/W3215615641","https://openalex.org/W4221146826","https://openalex.org/W4224932531","https://openalex.org/W4296930493","https://openalex.org/W4307323391","https://openalex.org/W4307977385","https://openalex.org/W4312974539","https://openalex.org/W4313679638","https://openalex.org/W4367050859","https://openalex.org/W4372341113","https://openalex.org/W4381786045","https://openalex.org/W4385245566","https://openalex.org/W4393898665","https://openalex.org/W6664955365","https://openalex.org/W6739901393","https://openalex.org/W6757817989","https://openalex.org/W6772381481","https://openalex.org/W6784333009","https://openalex.org/W6798098866","https://openalex.org/W6843330092","https://openalex.org/W6848735303","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W4387768015","https://openalex.org/W4304700937"],"abstract_inverted_index":{"Recent":[0],"neural":[1],"room":[2],"impulse":[3],"response":[4],"(RIR)":[5],"estimators":[6],"typically":[7],"comprise":[8],"an":[9,41,51,118],"encoder":[10],"for":[11,18,45],"reference":[12],"audio":[13],"analysis":[14],"and":[15,96,109],"a":[16,58,67,82],"generator":[17,28,43],"RIR":[19,78,119],"synthesis.":[20],"Especially,":[21],"it":[22],"is":[23,137],"the":[24,27,32,72,77,104,122,126],"performance":[25],"of":[26,71],"that":[29,91,120,134],"directly":[30],"influences":[31],"overall":[33],"estimation":[34,79,107],"quality.":[35],"In":[36],"this":[37],"context,":[38],"we":[39,75,102],"explore":[40],"alternate":[42],"architecture":[44],"improved":[46],"performance.":[47],"We":[48],"first":[49],"train":[50],"autoencoder":[52],"with":[53],"residual":[54],"quantization":[55,97],"to":[56,116,125,139],"learn":[57],"discrete":[59],"latent":[60],"token":[61,65,85],"space,":[62],"where":[63],"each":[64],"represents":[66],"small":[68],"time-frequency":[69],"patch":[70],"RIR.":[73],"Then,":[74],"cast":[76],"problem":[80],"as":[81],"reference-conditioned":[83],"autoregressive":[84],"generation":[86],"task,":[87],"employing":[88],"transformer":[89],"variants":[90],"operate":[92],"across":[93,142],"frequency,":[94],"time,":[95],"depth":[98],"axes.":[99],"This":[100],"way,":[101],"address":[103],"standard":[105],"blind":[106],"task":[108],"additional":[110],"acoustic":[111],"matching":[112],"problem,":[113],"which":[114],"aims":[115],"find":[117],"matches":[121],"source":[123],"signal":[124],"target":[127],"signal\u2019s":[128],"reverberation":[129],"characteristics.":[130],"Experimental":[131],"results":[132],"show":[133],"our":[135],"system":[136],"preferable":[138],"other":[140],"baselines":[141],"various":[143],"evaluation":[144],"metrics.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}