{"id":"https://openalex.org/W4414489296","doi":"https://doi.org/10.21437/interspeech.2025-2109","title":"Cryfish: On deep audio analysis with Large Language Models","display_name":"Cryfish: On deep audio analysis with Large Language Models","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4414489296","doi":"https://doi.org/10.21437/interspeech.2025-2109"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-2109","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.12666","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023799323","display_name":"Anton Mitrofanov","orcid":"https://orcid.org/0000-0001-9791-6418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anton Mitrofanov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Sergey Novoselov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sergey Novoselov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044290144","display_name":"Tatiana Prisyach","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tatiana Prisyach","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116594417","display_name":"Vladislav Marchevskiy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vladislav Marchevskiy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Arseniy Karelin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arseniy Karelin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092639584","display_name":"Nikita Khmelev","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikita Khmelev","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106912726","display_name":"Dmitry Dutov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dmitry Dutov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Stepan Malykh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stepan Malykh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106912727","display_name":"Igor Agafonov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Igor Agafonov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119723897","display_name":"Aleksandr Nikitin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aleksandr Nikitin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5060412786","display_name":"Oleg Petrov","orcid":"https://orcid.org/0000-0001-8258-3171"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oleg Petrov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.130683,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3249","last_page":"3253"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955999851226807,"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":0.9955999851226807,"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/T11309","display_name":"Music and Audio Processing","score":0.9812999963760376,"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/T10028","display_name":"Topic Modeling","score":0.9724000096321106,"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/active-listening","display_name":"Active listening","score":0.5623999834060669},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.49239999055862427},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4885999858379364},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.47999998927116394},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3167000114917755},{"id":"https://openalex.org/keywords/auditory-perception","display_name":"Auditory perception","score":0.3073999881744385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766700029373169},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5623999834060669},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49239999055862427},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4885999858379364},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.47999998927116394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4715000092983246},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44190001487731934},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3495999872684479},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34049999713897705},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C3020799230","wikidata":"https://www.wikidata.org/wiki/Q160289","display_name":"Auditory perception","level":3,"score":0.3073999881744385},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2922999858856201},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2612999975681305}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-2109","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.12666","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.12666","pdf_url":"https://arxiv.org/pdf/2508.12666","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.12666","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.12666","pdf_url":"https://arxiv.org/pdf/2508.12666","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,76,119],"recent":[1],"revolutionary":[2],"progress":[3],"in":[4,17,55],"text-based":[5],"large":[6],"language":[7],"models":[8,22],"(LLMs)":[9],"has":[10],"contributed":[11],"to":[12,23,38,92],"the":[13,103,106,131],"growth":[14],"of":[15,20,73,128],"interest":[16],"extending":[18],"capabilities":[19,47],"such":[21],"multimodal":[24],"perception":[25],"and":[26,62,125],"understanding":[27],"tasks.":[28],"Hearing":[29],"is":[30,35,50,90],"an":[31,122],"essential":[32],"capability":[33],"that":[34],"highly":[36],"desired":[37],"be":[39],"integrated":[40],"into":[41,48,82],"LLMs.":[42],"However,":[43],"effective":[44],"integrating":[45],"listening":[46],"LLMs":[49],"a":[51,86,97],"significant":[52],"challenge":[53],"lying":[54],"generalizing":[56],"complex":[57],"auditory":[58,94],"tasks":[59,95],"across":[60],"speech":[61],"sounds.":[63],"To":[64],"address":[65],"these":[66],"issues,":[67],"we":[68],"introduce":[69],"Cryfish,":[70],"our":[71],"version":[72],"auditory-capable":[74,117],"LLM.":[75],"model":[77,84,104],"integrates":[78],"WavLM":[79],"audio-encoder":[80],"features":[81],"Qwen2":[83],"using":[85],"transformer-based":[87],"connector.":[88],"Cryfish":[89,129],"adapted":[91],"various":[93],"through":[96],"specialized":[98],"training":[99],"strategy.":[100],"We":[101],"evaluate":[102],"on":[105],"new":[107],"Dynamic":[108],"SUPERB":[109],"Phase-2":[110],"comprehensive":[111],"multitask":[112],"benchmark":[113],"specifically":[114],"designed":[115],"for":[116],"models.":[118,134],"paper":[120],"presents":[121],"in-depth":[123],"analysis":[124],"detailed":[126],"comparison":[127],"with":[130],"publicly":[132],"available":[133]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}