{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T12:00:10Z","timestamp":1780056010957,"version":"3.54.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889173","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["HAPG-SAQAM: Human Auditory Perception Guided Spatial Audio Quality Assessment Metric"],"prefix":"10.1109","author":[{"given":"Yuanming","family":"Zheng","sequence":"first","affiliation":[{"name":"Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science,Wuhan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxuan","family":"Yao","sequence":"additional","affiliation":[{"name":"Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science,Wuhan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyu","family":"Deng","sequence":"additional","affiliation":[{"name":"Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science,Wuhan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhong","family":"Yang","sequence":"additional","affiliation":[{"name":"Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science,Wuhan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiqi","family":"Liao","sequence":"additional","affiliation":[{"name":"Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science,Wuhan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiping","family":"Tu","sequence":"additional","affiliation":[{"name":"Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science,Wuhan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cedar","family":"Lin","sequence":"additional","affiliation":[{"name":"Guangdong OPPO Mobile Telecommunications Corp.,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2017.0037"},{"key":"ref2","article-title":"Standardization of PEAQ-MC: Extension of ITU-R BS.1387-1 to multichannel audio","volume-title":"Audio Engineering Society Conference: 40th International Conference: Spatial Audio: Sense the Sound of Space","author":"K\u00e4mpf"},{"issue":"7\/8","key":"ref3","first-page":"535","article-title":"Perceptual objective quality evaluation method for high quality multichannel audio codecs","volume":"61","author":"Seo","year":"2013","journal-title":"Journal of the Audio Engineering Society"},{"key":"ref4","article-title":"A binaural auditory model for the evaluation of reproduced stereophonic sound","volume-title":"Audio Engineering Society Conference: 45th International Conference: Applications of Time-Frequency Processing in Audio","author":"Takanen"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632781"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-406"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-832"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447947"},{"key":"ref9","volume-title":"Spatial Audio Quality Inventory (SAQI). Test Manual","author":"Lindau","year":"2014"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.180"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24261-3_7"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1121\/1.1945368"},{"key":"ref13","article-title":"Assessment of spatial audio quality based on sound attributes","author":"Le Bagousse","year":"2012","journal-title":"Acoustics 2012"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1191"},{"key":"ref15","first-page":"343","article-title":"Earth mover distance over high-dimensional spaces","volume-title":"SODA","volume":"8","author":"Andoni"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1111"},{"key":"ref17","volume-title":"TIMIT Acoustic-Phonetic Continuous Speech Corpus","author":"Garofolo","year":"1993"},{"key":"ref18","article-title":"Database of binaural room impulse responses of an apartment-like environment","volume-title":"Audio Engineering Society Convention 140","author":"Winter","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2020.107867"},{"key":"ref20","article-title":"360\u00b0 binaural room impulse response (brir) database for 6dof spatial perception research","volume-title":"Audio Engineering Society Convention 146","author":"Bacila","year":"2019"},{"key":"ref21","article-title":"Dataset of kemar-brirs measured at several positions and head orientations in a real room","author":"Mittag","year":"2016"},{"key":"ref22","article-title":"IoSR Listening Room Multichannel BRIR Dataset","author":"Francombe","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1155\/2009\/298605"},{"key":"ref24","article-title":"Database of single-channel and binaural room impulse responses of a 64-channel loudspeaker array","volume-title":"Audio Engineering Society Convention 138","author":"Erbes","year":"2015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSP.2009.5201259"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3038"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2015.7336899"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3813\/AAA.919349"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2028374"},{"key":"ref30","article-title":"Definition of the Opus audio codec","author":"Valin","year":"2012","journal-title":"Tech. Rep."},{"key":"ref31","article-title":"Method for the subjective assessment of intermediate quality level of audio systems","volume-title":"International Telecommunication Union, Tech. Rep. BS.1534-3","author":"Sector","year":"2015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.307"},{"key":"ref33","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings","author":"Glorot"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3055038"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2020.0038"},{"key":"ref36","article-title":"Perceptual evaluation of bitrate compressed ambisonic scenes in loudspeaker based reproduction","volume-title":"Audio Engineering Society Conference: 2019 AES International Conference on Immersive and Interactive Audio","author":"Rudzki"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889173.pdf?arnumber=10889173","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:31Z","timestamp":1774416151000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889173\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889173","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}