{"id":"https://openalex.org/W4317837873","doi":"https://doi.org/10.48550/arxiv.2301.08562","title":"Latent Autoregressive Source Separation","display_name":"Latent Autoregressive Source Separation","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4317837873","doi":"https://doi.org/10.48550/arxiv.2301.08562"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2301.08562","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.08562","pdf_url":"https://arxiv.org/pdf/2301.08562","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2301.08562","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069620223","display_name":"Emilian Postolache","orcid":"https://orcid.org/0000-0002-4785-5204"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Postolache, Emilian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032905625","display_name":"Giorgio Mariani","orcid":"https://orcid.org/0000-0002-8135-0330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mariani, Giorgio","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076690986","display_name":"Michele Mancusi","orcid":"https://orcid.org/0000-0003-1591-7076"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mancusi, Michele","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046548985","display_name":"Andrea Santilli","orcid":"https://orcid.org/0000-0001-8483-2725"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Santilli, Andrea","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085428440","display_name":"Luca Cosmo","orcid":"https://orcid.org/0000-0001-7729-4666"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cosmo, Luca","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5087051832","display_name":"Emanuele Rodol\u00e0","orcid":"https://orcid.org/0000-0003-0091-7241"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rodol\u00e0, Emanuele","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5069620223"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9941999912261963,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9911999702453613,"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/autoregressive-model","display_name":"Autoregressive model","score":0.7378591895103455},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7101059556007385},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.6926100850105286},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5868167877197266},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4455040991306305},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4363604784011841},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43393319845199585},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3459901809692383},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3329387605190277},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32309490442276},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18333929777145386},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12957733869552612}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7378591895103455},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7101059556007385},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6926100850105286},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5868167877197266},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4455040991306305},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4363604784011841},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43393319845199585},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3459901809692383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3329387605190277},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32309490442276},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18333929777145386},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12957733869552612}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2301.08562","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.08562","pdf_url":"https://arxiv.org/pdf/2301.08562","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2301.08562","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2301.08562","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2301.08562","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.08562","pdf_url":"https://arxiv.org/pdf/2301.08562","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4317837873.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2580650124","https://openalex.org/W4386190339","https://openalex.org/W2562263695","https://openalex.org/W2135187896","https://openalex.org/W2147201983","https://openalex.org/W2015518264","https://openalex.org/W2795035211","https://openalex.org/W2160108762","https://openalex.org/W1718066205","https://openalex.org/W2017034551"],"abstract_inverted_index":{"Autoregressive":[0,86],"models":[1,56,120],"have":[2],"achieved":[3],"impressive":[4],"results":[5,160],"over":[6,136],"a":[7,25,80,125],"wide":[8],"range":[9],"of":[10,14,34,105,139,166,179],"domains":[11],"in":[12,116,164,177],"terms":[13,165,178],"generation":[15],"quality":[16,168],"and":[17,48,124,148,182],"downstream":[18],"task":[19],"performance.":[20],"In":[21],"the":[22,32,113,118,122,172],"continuous":[23],"domain,":[24],"key":[26],"factor":[27],"behind":[28],"this":[29],"success":[30],"is":[31,62,130],"usage":[33],"quantized":[35],"latent":[36,137],"spaces":[37],"(e.g.,":[38,154],"obtained":[39],"via":[40],"VQ-VAE":[41],"autoencoders),":[42],"which":[43,117],"allow":[44],"for":[45],"dimensionality":[46],"reduction":[47],"faster":[49],"inference":[50,180],"times.":[51],"However,":[52],"using":[53],"existing":[54,106,162],"pre-trained":[55],"to":[57,72,82,184],"perform":[58,83],"new":[59],"non-trivial":[60],"tasks":[61],"difficult":[63],"since":[64],"it":[65],"requires":[66],"additional":[67,100],"fine-tuning":[68],"or":[69,103],"extensive":[70],"training":[71],"elicit":[73],"prompting.":[74],"This":[75],"paper":[76],"introduces":[77],"LASS":[78],"as":[79],"way":[81],"vector-quantized":[84],"Latent":[85],"Source":[87],"Separation":[88],"(i.e.,":[89],"de-mixing":[90],"an":[91],"input":[92],"signal":[93],"into":[94],"its":[95],"constituent":[96],"sources)":[97],"without":[98],"requiring":[99],"gradient-based":[101],"optimization":[102],"modifications":[104],"models.":[107],"Our":[108],"separation":[109,167],"method":[110,145],"relies":[111],"on":[112,146],"Bayesian":[114],"formulation":[115],"autoregressive":[119],"are":[121],"priors,":[123],"discrete":[126],"(non-parametric)":[127],"likelihood":[128],"function":[129],"constructed":[131],"by":[132],"performing":[133],"frequency":[134],"counts":[135],"sums":[138],"addend":[140],"tokens.":[141],"We":[142],"test":[143],"our":[144],"images":[147],"audio":[149],"with":[150,161],"several":[151],"sampling":[152],"strategies":[153],"ancestral,":[155],"beam":[156],"search)":[157],"showing":[158],"competitive":[159],"approaches":[163],"while":[169],"offering":[170],"at":[171],"same":[173],"time":[174,181],"significant":[175],"speedups":[176],"scalability":[183],"higher":[185],"dimensional":[186],"data.":[187]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}