{"id":"https://openalex.org/W4402389976","doi":"https://doi.org/10.1109/icasspw62465.2024.10669911","title":"ISPA: Inter-Species Phonetic Alphabet for Transcribing Animal Sounds","display_name":"ISPA: Inter-Species Phonetic Alphabet for Transcribing Animal Sounds","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4402389976","doi":"https://doi.org/10.1109/icasspw62465.2024.10669911"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10669911","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10669911","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5036557983","display_name":"Masato Hagiwara","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masato Hagiwara","raw_affiliation_strings":["Earth Species Project"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Earth Species Project","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039915904","display_name":"Marius Miron","orcid":"https://orcid.org/0000-0002-2563-075X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marius Miron","raw_affiliation_strings":["Earth Species Project"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Earth Species Project","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101719938","display_name":"Jen-Yu Liu","orcid":"https://orcid.org/0000-0003-1299-6688"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jen-Yu Liu","raw_affiliation_strings":["Earth Species Project"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Earth Species Project","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"828","last_page":"832"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9937999844551086,"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/alphabet","display_name":"Alphabet","score":0.8351113200187683},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6000080108642578},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5038697123527527},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3579959273338318},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.343809574842453},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2484017014503479}],"concepts":[{"id":"https://openalex.org/C112876837","wikidata":"https://www.wikidata.org/wiki/Q837518","display_name":"Alphabet","level":2,"score":0.8351113200187683},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6000080108642578},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5038697123527527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3579959273338318},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.343809574842453},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2484017014503479},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10669911","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10669911","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W129413713","https://openalex.org/W1976353778","https://openalex.org/W2052666245","https://openalex.org/W2161632835","https://openalex.org/W2161944985","https://openalex.org/W2590924240","https://openalex.org/W2752796333","https://openalex.org/W2757431469","https://openalex.org/W2906214917","https://openalex.org/W2964169922","https://openalex.org/W2965373594","https://openalex.org/W2979826702","https://openalex.org/W3001279689","https://openalex.org/W3015877095","https://openalex.org/W3134881075","https://openalex.org/W3196974791","https://openalex.org/W3209059054","https://openalex.org/W4205689591","https://openalex.org/W4226051760","https://openalex.org/W4362515116","https://openalex.org/W4372262734","https://openalex.org/W4372266830","https://openalex.org/W4385567057","https://openalex.org/W6766673545","https://openalex.org/W6772383348","https://openalex.org/W6791299810","https://openalex.org/W6799586247","https://openalex.org/W6851775633","https://openalex.org/W6856125517"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Traditionally,":[0],"bioacoustics":[1],"has":[2,32],"relied":[3],"on":[4],"spectrograms":[5],"and":[6,55,68,73,103,112],"continuous,":[7,85],"per-frame":[8],"audio":[9,87],"representations":[10],"for":[11,38,59,71],"the":[12,26],"analysis":[13],"of":[14],"animal":[15,61,75,91],"sounds,":[16,76],"also":[17],"serving":[18],"as":[19,99,115],"input":[20],"to":[21,122],"machine":[22],"learning":[23],"models.":[24],"Meanwhile,":[25],"International":[27],"Phonetic":[28,50],"Alphabet":[29],"(IPA)":[30],"system":[31,57],"provided":[33],"an":[34],"interpretable,":[35],"language-independent":[36],"method":[37],"transcribing":[39,60,72],"human":[40,108],"speech":[41],"sounds.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46,95,104],"introduce":[47],"ISPA":[48],"(Inter-Species":[49],"Alphabet),":[51],"a":[52,100],"precise,":[53],"concise,":[54],"interpretable":[56],"designed":[58],"sounds":[62,92],"into":[63],"text.":[64],"We":[65],"compare":[66],"acoustics-based":[67],"feature-based":[69],"methods":[70,83],"classifying":[74],"demonstrating":[77],"their":[78],"comparable":[79],"performance":[80],"with":[81,93],"baseline":[82],"utilizing":[84],"dense":[86],"representations.":[88],"By":[89],"representing":[90],"text,":[94],"effectively":[96],"treat":[97],"them":[98],"\"foreign":[101],"language,\"":[102],"show":[105],"that":[106],"established":[107],"language":[109,116],"ML":[110],"paradigms":[111],"models,":[113,117],"such":[114],"can":[118],"be":[119],"successfully":[120],"applied":[121],"improve":[123],"performance.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}