{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:13:42Z","timestamp":1764785622523,"version":"3.40.4"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031901669","type":"print"},{"value":"9783031901676","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-90167-6_13","type":"book-chapter","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T02:15:13Z","timestamp":1745288113000},"page":"186-201","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["An Ensemble Approach to\u00a0Music Source Separation: A Comparative Analysis of\u00a0Conventional and\u00a0Hierarchical Stem Separation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2234-8845","authenticated-orcid":false,"given":"Saarth","family":"Vardhan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2967-9621","authenticated-orcid":false,"given":"Pavani R","family":"Acharya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8159-2261","authenticated-orcid":false,"given":"Samarth S","family":"Rao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0209-5452","authenticated-orcid":false,"given":"Oorjitha Ratna","family":"Jasthi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8689-5137","authenticated-orcid":false,"given":"S.","family":"Natarajan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,20]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Tong, W., et al.: SCNet: sparse compression network for music source separation. In: ICASSP (2024)","DOI":"10.1109\/ICASSP48485.2024.10446651"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Chen, J., Vekkot, S., Shukla, P.: Music source separation based on a lightweight deep learning framework (DTTNET: dual-path TFC-TDF UNET). In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 656\u2013660. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10448020"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Lu, W.T., Wang, J.C., Kong, Q., Hung, Y.N.: Music source separation with band-split RoPE transformer (2023)","DOI":"10.1109\/ICASSP48485.2024.10446843"},{"key":"13_CR4","unstructured":"Wang, J.C., Lu, W.T., Won, M.: Mel-band RoFormer for music source separation. In: Speech, Audio, and Music Intelligence (SAMI), ByteDance (2023)"},{"key":"13_CR5","unstructured":"Pereira, I., Ara\u00fajo, F., Korzeniowski, F., Vogl, R.: MoisesDB: a dataset for source separation beyond 4-stems. In: Proceedings of the 24th International Society for Music Information Retrieval Conference, Milan, pp. 619\u2013626 (2023)"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Luo, Y., Yu, J.: Music source separation with band-split RNN. In: IEEE\/ACM Transactions on Audio, Speech, and Language Processing, vol. 31, pp. 1893\u20131901. IEEE (2023)","DOI":"10.1109\/TASLP.2023.3271145"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Petermann, D., Wichern, G., Wang, Z.Q., Le Roux, J.: The Cocktail Fork Problem: Three-Stem Audio Separation for Real-World. arXiv:2110.09958 (2022)","DOI":"10.1109\/ICASSP43922.2022.9746005"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Wang, Y., Stoller, D., Bittner, R.M., Bello, J.P.: Few-shot musical source separation. In: Proceedings of the 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore, pp. 121\u2013125. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9747536"},{"key":"13_CR9","unstructured":"Kharah, D., Parekh, D., Suthar, K.: Audio stems separation using deep learning. Int. J. Eng. Res. Technol. (IJERT) 10(03) (2021)"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Lee, S., Bajic, I.V.: Information flow through U-nets. In: Proceedings of the 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), Nice, pp. 812\u2013816. IEEE (2021)","DOI":"10.1109\/ISBI48211.2021.9433801"},{"key":"13_CR11","unstructured":"Kong, Q., Cao, Y., Liu, H., Choi, K., Wang, Y.: Decoupling magnitude and phase estimation with deep ResUNet for music source separation. In: Proceedings of the 22nd International Society for Music Information Retrieval Conference, pp. 342\u2013349 (2021)"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Luo, Y., Chen, Z., Yoshioka, T.: Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation. In: Proceedings of the 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 46\u201350 (2020)","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"13_CR13","unstructured":"Takahashi, N., Mitsufuji, Y.: D3Net: Densely Connected Multidilated Densenet for Music Source Separation. arXiv preprint arXiv:2010.01733 (2020)"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Satya, M.F., Suyanto, S.: Music source separation using generative adversarial network and U-net. In: Proceedings of the 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 1\u20136. IEEE (2020)","DOI":"10.1109\/ICoICT49345.2020.9166374"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Hennequin, R., Khlif, A., Voituret, F., Moussallam, M.: Spleeter: a fast and state-of-the-art music source separation tool with pretrained models. In: Proceedings of the 2019 International Society for Music Information Retrieval Conference (ISMIR) (2019)","DOI":"10.21105\/joss.02154"},{"issue":"41","key":"13_CR16","doi-asserted-by":"publisher","first-page":"1667","DOI":"10.21105\/joss.01667","volume":"4","author":"F-R St\u00f6ter","year":"2019","unstructured":"St\u00f6ter, F.-R., Uhlich, S., Liutkus, A., Mitsufuji, Y.: Open-Unmix - a reference implementation for music source separation. J. Open Source Softw. 4(41), 1667 (2019)","journal-title":"J. Open Source Softw."},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Rouard, S., Massa, F., D\u00e9fossez, A.: Hybrid transformers for music source separation. In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2023)","DOI":"10.1109\/ICASSP49357.2023.10096956"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Stoller, D., Ewert, S., Dixon, S.: Adversarial Semi-supervised Audio Source Separation Applied to Singing Voice Extraction. arXiv preprint arXiv:1711.00048 (2018)","DOI":"10.1109\/ICASSP.2018.8461722"},{"key":"13_CR19","unstructured":"Stoller, D., Ewert, S., Dixon, S.: Wave-U-net: a multi-scale neural network for end-to-end audio source separation. In: Proceedings of the 2018 International Society for Music Information Retrieval Conference (ISMIR), pp. 334\u2013340 (2018)"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Ashwini, B., Ramesh, N., Naik, S.M., Krishna, A.V.: Lead source separation for Indian instrumental audio. In: Proceedings of the 2017 IEEE Region 10 Conference (TENCON), Malaysia (2017)","DOI":"10.1109\/TENCON.2017.8228025"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Takahashi, N., Mitsufuji, Y.: Multi-scale multi-band densenet for audio source separation. Tokyo (2016)","DOI":"10.1109\/WASPAA.2017.8169987"},{"key":"13_CR22","unstructured":"Bittner, R., Salamon, J., Tierney, M., Mauch, M., Cannam, C., Bello, J.P.: MedleyDB: a multitrack dataset for annotation-intensive MIR research. In: Proceedings of the 15th Conference of the International Society for Music Information Retrieval (ISMIR) (2014)"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Itoyama, K., Goto, M., Komatani, K., Ogata, T., Okuno, H.G.: Simultaneous processing of sound source separation and musical instrument identification using bayesian spectral modeling. In: Proceedings of the 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (2011)","DOI":"10.1109\/ICASSP.2011.5947183"},{"key":"13_CR24","unstructured":"Kitahara, T.: Computational Musical Instrument Recognition and Its Application to Content-Based Music Information Retrieval. Ph.D. thesis, Kyoto University (2007)"},{"issue":"1","key":"13_CR25","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1109\/TASL.2006.876754","volume":"15","author":"K Yoshii","year":"2007","unstructured":"Yoshii, K., et al.: Drum sound recognition for polyphonic audio signals by adaptation and matching of spectrogram templates with harmonic structure suppression. IEEE Trans. Audio Speech Lang. Process. 15(1), 333\u2013345 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"13_CR26","unstructured":"Jensen, K.: Mel-Band Roformer Vocal Model. GitHub. https:\/\/github.com\/KimberleyJensen\/Mel-Band-Roformer-Vocal-Model"},{"key":"13_CR27","unstructured":"Facebook Research.: Demucs: Music Source Separation. GitHub. https:\/\/github.com\/facebookresearch\/demucs"},{"key":"13_CR28","unstructured":"Tong, W.: SCNet: Sparse Compression Network. GitHub. https:\/\/github.com\/starrytong\/SCNet?tab=readme-ov-file"},{"key":"13_CR29","unstructured":"Inagoy.: Drum Source Separation. GitHub. https:\/\/github.com\/inagoy\/drumsep"},{"key":"13_CR30","unstructured":"Nomad Karaoke.: Python Audio Separator. GitHub. https:\/\/github.com\/nomadkaraoke\/python-audio-separator\/tree\/main"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence in Music, Sound, Art and Design"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-90167-6_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T02:15:32Z","timestamp":1745288132000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-90167-6_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031901669","9783031901676"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-90167-6_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"20 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"EvoMUSART","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Intelligence in Music, Sound, Art and Design (Part of EvoStar)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Trieste","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 April 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 April 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"evomusart2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.evostar.org\/2025\/evomusart\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}