{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T04:01:45Z","timestamp":1748491305209,"version":"3.41.0"},"reference-count":28,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icasspw65056.2025.11011110","type":"proceedings-article","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T17:05:14Z","timestamp":1748365514000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Investigating Temporal Convolutional Networks for Automated Stroke Transcription in the Mridangam"],"prefix":"10.1109","author":[{"given":"Gopika","family":"Krishnan","sequence":"first","affiliation":[{"name":"Universitat Pompeu Fabra,Department of Engineering,Barcelona,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akshay","family":"Anantapadmanabhan","sequence":"additional","affiliation":[{"name":"Freelance Musician,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaustuv Kanti","family":"Ganguli","sequence":"additional","affiliation":[{"name":"Zayed University,Department of Computational Systems,Abu Dhabi,United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carlos","family":"Guedes","sequence":"additional","affiliation":[{"name":"New York University Abu Dhabi,Music and Sound Cultures Research Group,Abu Dhabi,United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2830113"},{"key":"ref2","first-page":"181","article-title":"Modal analysis and transcription of strokes of the mridangam using non-negative matrix factorization","volume-title":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing.","author":"Anantapadmanabhan"},{"article-title":"Automatic Transcription of Drum Strokes in Carnatic Music","year":"2022","author":"Chandramouli","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.914120"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362739"},{"key":"ref6","first-page":"16","article-title":"On the use of zero-crossing rate for an application of classification of percussive sounds","volume-title":"Proceedings of the COST G-6 conference on Digital Audio Effects (DAFX-00), Verona, Italy","volume":"5","author":"Gouyon"},{"key":"ref7","first-page":"184","article-title":"Automatic drum sound description for real-world music using template adaptation and matching methods","volume-title":"ISMIR","author":"Yoshii"},{"key":"ref8","article-title":"Adamast: A drum sound recognizer based on adaptation and matching of spectrogram templates","author":"Yoshii","year":"2005","journal-title":"1st Annual Music Information Retrieval Evaluation eXchange (MIREX)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876754"},{"key":"ref10","first-page":"353","article-title":"Drum transcription in polyphonic music using non-negative matrix factorisation","volume-title":"ISMIR","author":"Moreau"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280342"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2986416.2986453"},{"key":"ref13","first-page":"219","article-title":"Supervised and unsupervised sequence modelling for drum transcription","volume-title":"ISMIR","author":"Gillet"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1155\/2011\/291860"},{"key":"ref15","first-page":"49","article-title":"Voice drummer: A music notation interface of drum sounds using voice percussion input","volume-title":"Proc. of UIST 2005 (Demos)","author":"Nakano"},{"key":"ref16","first-page":"730","article-title":"Recurrent neural networks for drum transcription","volume-title":"ISMIR","author":"Vogl"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952146"},{"article-title":"Automatic drum transcription for polyphonic recordings using soft attention mechanisms and convolutional neural networks","year":"2017","author":"Southall","key":"ref18"},{"article-title":"Tonic-independent stroke transcription of the mridangam","volume-title":"Audio engineering society conference: 53rd international conference: Semantic audio","author":"Anantapadmanabhan","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/BF03035705"},{"key":"ref21","first-page":"304","article-title":"A study of harmonic overtones produced in indian drums","author":"Siddharthan","year":"1994","journal-title":"Physics Education"},{"key":"ref22","first-page":"1","article-title":"Akshara transcription of mrudangam strokes in Carnatic music","volume-title":"2015 Twenty First National Conference on Communications (NCC)","author":"Kuriakose"},{"article-title":"Wavenet: A generative model for raw audio","year":"2016","author":"Oord","key":"ref23"},{"article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","year":"2018","author":"Bai","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902578"},{"article-title":"Temporal convolutional networks for speech and music detection in radio broadcast","volume-title":"20th International Society for Music Information Retrieval Conference, ISMIR 2019, 4-8 November 2019","author":"Lemaire","key":"ref26"},{"article-title":"A data-driven bayesian approach to automatic rhythm analysis of indian art music","year":"2016","author":"Srinivasamurthy","key":"ref27"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSPW65056.2025.11011256","article-title":"Closing the loop on speech to music translation: Automatically generating synthetic percussive sequences on the mridangam from konnakol","volume-title":"Proceedings of the SALMA Workshop, co-located with IEEE ICASSP 2025.","author":"Krishnan"}],"event":{"name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","start":{"date-parts":[[2025,4,6]]},"location":"Hyderabad, India","end":{"date-parts":[[2025,4,11]]}},"container-title":["2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11010992\/11010997\/11011110.pdf?arnumber=11011110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T04:52:16Z","timestamp":1748407936000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11011110\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icasspw65056.2025.11011110","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}