{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:17:45Z","timestamp":1776881865381,"version":"3.51.2"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448213","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11936-11940","source":"Crossref","is-referenced-by-count":4,"title":["Prompting Audios Using Acoustic Properties for Emotion Representation"],"prefix":"10.1109","author":[{"given":"Hira","family":"Dhamyal","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benjamin","family":"Elizalde","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soham","family":"Deshmukh","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaming","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhiksha","family":"Raj","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rita","family":"Singh","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"The emotions","author":"Plutchik","year":"1991"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.99.3.550"},{"key":"ref3","article-title":"Detecting gender differences in perception of emotion in crowdsourced data","author":"Memon","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3046"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1037\/\/0033-2909.97.3.412"},{"key":"ref6","article-title":"Acoustic concomitants of emotional dimensions: Judging affect from synthesized tone sequences","author":"Scherer","year":"1972"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511584305"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095889"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1136"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11085"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.11.036"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.10.002"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref16","article-title":"AudioCaps: Generating Captions for Audios in The Wild","author":"Kim","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616087"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1050"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref24","article-title":"The frequency range of the voice fundamental in the speech of male and female adults","volume":"11","author":"Traunm\u00fcller","year":"1995","journal-title":"Unpublished manuscript"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1177\/0301006615602623"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.nrleng.2014.12.014"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.25080\/majora-7b98e3ed-003"},{"key":"ref28","article-title":"Praat"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683461"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/app12010327"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448213.pdf?arnumber=10448213","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T06:58:48Z","timestamp":1722581928000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448213\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448213","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}