{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:51:23Z","timestamp":1764399083538,"version":"3.46.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249088","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"234-239","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Transformer-Based Piano Transcription with Sparse Attention Mechanisms"],"prefix":"10.1109","author":[{"given":"Weixing","family":"Wei","sequence":"first","affiliation":[{"name":"Kyoto University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuyoshi","family":"Yoshii","sequence":"additional","affiliation":[{"name":"Kyoto University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2869928"},{"key":"ref2","first-page":"50","article-title":"Onsets and frames: Dual-objective piano transcription","volume-title":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","author":"Hawthorne","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3121991"},{"key":"ref4","first-page":"709","article-title":"HPPNet: Modeling the harmonic structure and pitch invariance in piano transcription","volume-title":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","author":"Wei","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref6","first-page":"246","article-title":"Sequence-to-sequence piano transcription with transformers","volume-title":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","author":"Hawthorne","year":"2021"},{"key":"ref7","article-title":"MT3: Multi-task multitrack music transcription","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Gardner","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746789"},{"key":"ref9","first-page":"215","article-title":"Automatic piano transcription with hierarchical frequency-time transformer","volume-title":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","author":"Toyama","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3419441"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC58517.2023.10317104"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC63619.2025.10848780"},{"key":"ref13","first-page":"2058320595","article-title":"Skipping the frame-level: Eventbased piano transcription with neural Semi-CRFs","volume":"34","author":"Yan","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref14","first-page":"973","article-title":"Scoring time intervals using non-hierarchical transformer for automatic piano transcription","volume-title":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","author":"Yan","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746549"},{"key":"ref16","first-page":"906","article-title":"Streaming piano transcription based on consistent onset and offset decoding with sustain pedal detection","volume-title":"Proceedings of the 25th International Society for Music Information Retrieval Conference, (ISMIR)","author":"Wei","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO58844.2023.10290067"},{"key":"ref18","first-page":"4","article-title":"Real-time automatic piano music transcription system","volume-title":"Late Breaking\/Demo of the International Society for Music Information Retrieval Conference (ISMIR)","author":"Jeong","year":"2020"},{"journal-title":"Longformer: The long-document transformer","year":"2020","author":"Beltagy","key":"ref19"},{"key":"ref20","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","volume":"33","author":"Zaheer","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref21","article-title":"FlashAttention: Fast and memory-efficient exact attention with IO-awareness","author":"Dao","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref22","first-page":"140:1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref23","first-page":"1","article-title":"Enabling factorized piano music modeling and generation with the MAESTRO dataset","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Hawthorne","year":"2019"},{"key":"ref24","article-title":"Decoupled weight decay regularization","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Loshchilov","year":"2019"},{"key":"ref25","first-page":"1","article-title":"Mir_eval: A transparent implementation of common mir metrics","volume-title":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","author":"Raffel","year":"2014"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249088.pdf?arnumber=11249088","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:50:19Z","timestamp":1764399019000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249088\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249088","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}