{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T11:16:27Z","timestamp":1778152587667,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,7]],"date-time":"2023-12-07T00:00:00Z","timestamp":1701907200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"University of Science, VNU-HCM"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,7]]},"DOI":"10.1145\/3628797.3629004","type":"proceedings-article","created":{"date-parts":[[2023,12,6]],"date-time":"2023-12-06T15:25:34Z","timestamp":1701876334000},"page":"435-442","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Improving Bird Sounds Classification with Additional Fine-tuning on Augmented Data"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7584-8153","authenticated-orcid":false,"given":"Duy-Khang","family":"Ho","sequence":"first","affiliation":[{"name":"Faculty of Information Technology, University of Science, VNU-HCM, Viet Nam and Vietnam National University, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6648-3844","authenticated-orcid":false,"given":"Huy-Hoang","family":"Do-Huu","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, University of Science, VNU-HCM, Viet Nam and Vietnam National University, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4711-6696","authenticated-orcid":false,"given":"Minh-Phuong","family":"Le-Thi","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, University of Science, VNU-HCM, Viet Nam and Vietnam National University, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3614-7982","authenticated-orcid":false,"given":"Xuan-Nam","family":"Cao","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, University of Science, VNU-HCM, Viet Nam and Vietnam National University, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,12,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-40065-5_7"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-40065-5_6"},{"key":"e_1_3_2_1_3_1","volume-title":"Long-term and large-scale multispecies dataset tracking population changes of common European breeding birds. Scientific data 8, 1","author":"Brl\u00edk Vojt\u011bch","year":"2021","unstructured":"Vojt\u011bch Brl\u00edk, Eva \u0160ilarov\u00e1, Jana \u0160korpilov\u00e1, Hany Alonso, Marc Anton, Ainars Aunins, Zolt\u00e1n Benk\u00f6, Gilles Biver, Malte Busch, Tomasz Chodkiewicz, 2021. Long-term and large-scale multispecies dataset tracking population changes of common European breeding birds. Scientific data 8, 1 (2021), 21."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02592055"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1111\/2041-210X.12060"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3043201"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.12.010"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-021-09866-4"},{"key":"e_1_3_2_1_9_1","volume-title":"CLEF 2020-Conference and Labs of the Evaluation Forum, Vol.\u00a02696","author":"Kahl Stefan","year":"2020","unstructured":"Stefan Kahl, Mary Clapp, W\u00a0Alexander Hopping, Herv\u00e9 Go\u00ebau, Herv\u00e9 Glotin, Robert Planqu\u00e9, Willem-Pier Vellinga, and Alexis Joly. 2020. Overview of birdclef 2020: Bird sound recognition in complex acoustic environments. In CLEF 2020-Conference and Labs of the Evaluation Forum, Vol.\u00a02696."},{"key":"e_1_3_2_1_10_1","volume-title":"ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Li Kang","unstructured":"Kang Li, Yan Song, Li-Rong Dai, Ian McLoughlin, Xin Fang, and Lin Liu. 2023. AST-SED: An Effective Sound Event Detection Method Based on Audio Spectrogram Transformer. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1\u20135."},{"key":"e_1_3_2_1_11_1","volume-title":"Channel Spatial Based Few-Shot Bird Sounds Event Detection. arXiv preprint arXiv:2306.10499","author":"Liu Lingwen","year":"2023","unstructured":"Lingwen Liu, Yuxuan Feng, Haitao Fu, Yajie Yang, Xin Pan, and Chenlei Jin. 2023. Channel Spatial Based Few-Shot Bird Sounds Event Detection. arXiv preprint arXiv:2306.10499 (2023)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095504"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3090678"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3090678"},{"key":"e_1_3_2_1_15_1","unstructured":"Naoki Murakami Hajime Tanaka and Masataka Nishimori. 2021. Birdcall Identification Using CNN and Gradient Boosting Decision Trees with Weak and Noisy Supervision.. In CLEF (Working Notes). 1597\u20131608."},{"key":"e_1_3_2_1_16_1","volume-title":"https:\/\/www.kaggle.com\/code\/yasufuminakama\/cassava-resnext50-32x4d-starter-training\/notebook. Last accessed","author":"Nakama Y.","year":"2023","unstructured":"Y. Nakama. 2020. Cassava \/ resnext50_32x4d starter [training]. https:\/\/www.kaggle.com\/code\/yasufuminakama\/cassava-resnext50-32x4d-starter-training\/notebook. Last accessed 24 June 2023."},{"key":"e_1_3_2_1_17_1","volume-title":"d.]. BirdCLEF 2021 - Birdcall Identification. https:\/\/www.kaggle.com\/competitions\/birdclef-2021. Last accessed","author":"Ornithology Cornell\u00a0Lab","year":"2023","unstructured":"Cornell\u00a0Lab of Ornithology. [n. d.]. BirdCLEF 2021 - Birdcall Identification. https:\/\/www.kaggle.com\/competitions\/birdclef-2021. Last accessed 28 June 2023."},{"key":"e_1_3_2_1_18_1","volume-title":"d.]. BirdCLEF 2023 - Birdcall Identification. https:\/\/www.kaggle.com\/competitions\/birdclef-2023. Last accessed","author":"Ornithology Cornell\u00a0Lab","year":"2023","unstructured":"Cornell\u00a0Lab of Ornithology.[n. d.]. BirdCLEF 2023 - Birdcall Identification. https:\/\/www.kaggle.com\/competitions\/birdclef-2023. Last accessed 28 June 2023."},{"key":"e_1_3_2_1_19_1","volume-title":"https:\/\/www.kaggle.com\/competitions\/birdclef-2021\/data. Last accessed","author":"Ornithology Cornell\u00a0Lab","year":"2023","unstructured":"Cornell\u00a0Lab of Ornithology. 2021. Dataset Description. https:\/\/www.kaggle.com\/competitions\/birdclef-2021\/data. Last accessed 14 June 2023."},{"key":"e_1_3_2_1_20_1","volume-title":"Evaluation metric. https:\/\/www.kaggle.com\/competitions\/birdclef-2021\/overview\/evaluation. Last accessed","author":"Ornithology Cornell\u00a0Lab","year":"2023","unstructured":"Cornell\u00a0Lab of Ornithology. 2021. Evaluation metric. https:\/\/www.kaggle.com\/competitions\/birdclef-2021\/overview\/evaluation. Last accessed 28 June 2023."},{"key":"e_1_3_2_1_21_1","volume-title":"Acoustic Classification of Bird Species. In Advances in Signal and Data Processing: Select Proceedings of ICSDP","author":"Patole Rashmika","year":"2021","unstructured":"Rashmika Patole and Priti Rege. 2021. Acoustic Classification of Bird Species. In Advances in Signal and Data Processing: Select Proceedings of ICSDP 2019. Springer, 313\u2013319."},{"key":"e_1_3_2_1_22_1","unstructured":"M.\u00a0J.\u00a0D. Powell. 2007. A View of Algorithms for Optimization without Derivatives. Technical Report DAMTP 2007. Cambridge University. Pages 3 and 6."},{"key":"e_1_3_2_1_23_1","volume-title":"d.]. RESNEXT50_32X4D. https:\/\/pytorch.org\/vision\/main\/models\/generated\/torchvision.models.resnext50_32x4d.html. Last accessed","year":"2023","unstructured":"PyTorch. [n. d.]. RESNEXT50_32X4D. https:\/\/pytorch.org\/vision\/main\/models\/generated\/torchvision.models.resnext50_32x4d.html. Last accessed 28 June 2023."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnbeh.2021.811737"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10531-020-01948-0"},{"key":"e_1_3_2_1_26_1","volume-title":"d.]. 3.1. Cross-validation: evaluating estimator performance. https:\/\/scikit-learn.org\/stable\/modules\/cross_validation.html. Last accessed","year":"2023","unstructured":"scikit learn. [n. d.]. 3.1. Cross-validation: evaluating estimator performance. https:\/\/scikit-learn.org\/stable\/modules\/cross_validation.html. Last accessed 24 June 2023."},{"key":"e_1_3_2_1_27_1","volume-title":"d.]. SLSQP - Qiskit 0.44.0 documentation. https:\/\/qiskit.org\/documentation\/stubs\/qiskit.algorithms.optimizers.SLSQP.html. Last accessed","author":"Py.","year":"2023","unstructured":"SciPy. [n. d.]. SLSQP - Qiskit 0.44.0 documentation. https:\/\/qiskit.org\/documentation\/stubs\/qiskit.algorithms.optimizers.SLSQP.html. Last accessed 3 August 2023."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0408049101"},{"key":"e_1_3_2_1_29_1","volume-title":"ff1010bird_duration7. https:\/\/www.kaggle.com\/datasets\/startjapan\/ff1010bird-duration7. Last accessed","year":"2023","unstructured":"start. 2021. ff1010bird_duration7. https:\/\/www.kaggle.com\/datasets\/startjapan\/ff1010bird-duration7. Last accessed 24 June 2023."},{"key":"e_1_3_2_1_30_1","volume-title":"An open dataset for research on audio field recording archives: freefield1010. arXiv preprint arXiv:1309.5275","author":"Stowell Dan","year":"2013","unstructured":"Dan Stowell and Mark\u00a0D Plumbley. 2013. An open dataset for research on audio field recording archives: freefield1010. arXiv preprint arXiv:1309.5275 (2013)."},{"key":"e_1_3_2_1_31_1","unstructured":"BZJLS Thornton. 2019. Audio recognition using mel spectrograms and convolution neural networks. (2019)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/0-306-48332-7_393"},{"key":"e_1_3_2_1_33_1","volume-title":"1st place solution: Correct Data is All You Need. https:\/\/www.kaggle.com\/competitions\/birdclef-2023\/discussion\/412808. Last accessed","year":"2023","unstructured":"Volodymyr. 2023. 1st place solution: Correct Data is All You Need. https:\/\/www.kaggle.com\/competitions\/birdclef-2023\/discussion\/412808. Last accessed 14 June 2023."},{"key":"e_1_3_2_1_34_1","volume-title":"d.]. Softmax Function. https:\/\/deepai.org\/machine-learning-glossary-and-terms\/softmax-layer. Last accessed","author":"Wood Thosmas","year":"2023","unstructured":"Thosmas Wood. [n. d.]. Softmax Function. https:\/\/deepai.org\/machine-learning-glossary-and-terms\/softmax-layer. Last accessed 24 June 2023."},{"key":"e_1_3_2_1_35_1","volume-title":"d.]. What is the F-score?https:\/\/deepai.org\/machine-learning-glossary-and-terms\/f-score. Last accessed","author":"Wood Thosmas","year":"2023","unstructured":"Thosmas Wood.[n. d.]. What is the F-score?https:\/\/deepai.org\/machine-learning-glossary-and-terms\/f-score. Last accessed 28 June 2023."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2019.05.007"}],"event":{"name":"SOICT 2023: The 12th International Symposium on Information and Communication Technology","location":"Ho Chi Minh Vietnam","acronym":"SOICT 2023"},"container-title":["Proceedings of the 12th International Symposium on Information and Communication Technology"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3628797.3629004","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3628797.3629004","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T12:24:19Z","timestamp":1755779059000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3628797.3629004"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,7]]},"references-count":36,"alternative-id":["10.1145\/3628797.3629004","10.1145\/3628797"],"URL":"https:\/\/doi.org\/10.1145\/3628797.3629004","relation":{},"subject":[],"published":{"date-parts":[[2023,12,7]]},"assertion":[{"value":"2023-12-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}