{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T15:26:09Z","timestamp":1762183569466,"version":"build-2065373602"},"reference-count":16,"publisher":"The Open Journal","issue":"115","license":[{"start":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T00:00:00Z","timestamp":1762128000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T00:00:00Z","timestamp":1762128000000},"content-version":"am","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T00:00:00Z","timestamp":1762128000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JOSS"],"published-print":{"date-parts":[[2025,11,3]]},"DOI":"10.21105\/joss.08049","type":"journal-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T14:36:46Z","timestamp":1762180606000},"page":"8049","source":"Crossref","is-referenced-by-count":0,"title":["Nkululeko 1.0: A Python package to predict speaker characteristics with a high-level interface"],"prefix":"10.21105","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2689-0545","authenticated-orcid":false,"given":"Felix","family":"Burkhardt","sequence":"first","affiliation":[{"name":"audEERING GmbH, Germany"},{"name":"TU Berlin, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1560-2824","authenticated-orcid":false,"given":"Bagus Tris","family":"Atmaja","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology (NAIST), Japan"}]}],"member":"8722","reference":[{"key":"scikit-learn:2011","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825\u20132830. https:\/\/doi.org\/10.5555\/1953048.2078195","journal-title":"Journal of Machine Learning Research"},{"key":"nkululeko:2022","isbn-type":"print","article-title":"Nkululeko: A tool for rapid speaker characteristics detection","author":"Burkhardt","year":"2022","unstructured":"Burkhardt, F., Wagner, J., Wierstorf, H., Eyben, F., & Schuller, B. (2022). Nkululeko: A tool for rapid speaker characteristics detection. 2022 Language Resources and Evaluation Conference, LREC 2022, 1925\u20131932. ISBN:\u00a09791095546726","ISBN":"https:\/\/id.crossref.org\/isbn\/9791095546726","journal-title":"2022 Language Resources and Evaluation Conference, LREC 2022"},{"issue":"Scipy","key":"McFee:2015","doi-asserted-by":"publisher","DOI":"10.25080\/majora-7b98e3ed-003","article-title":"librosa: Audio and Music Signal Analysis in Python","author":"McFee","year":"2015","unstructured":"McFee, B., Raffel, C., Liang, D., Ellis, D., McVicar, M., Battenberg, E., & Nieto, O. (2015). librosa: Audio and Music Signal Analysis in Python. Proc. 14th Python Sci. Conf., Scipy, 18\u201324. https:\/\/doi.org\/10.25080\/majora-7b98e3ed-003","journal-title":"Proc. 14th Python Sci. Conf."},{"key":"torch:2020","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-7998-3095-5.ch003","volume-title":"Deep learning with PyTorch","author":"Chaudhary","year":"2020","unstructured":"Chaudhary, A., Chouhan, K. S., Gajrani, J., & Sharma, B. (2020). Deep learning with PyTorch. https:\/\/doi.org\/10.4018\/978-1-7998-3095-5.ch003"},{"key":"Yang:2021","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775","article-title":"SUPERB: Speech Processing Universal PERformance Benchmark","author":"Yang","year":"2021","unstructured":"Yang, S., Chi, P.-H., Chuang, Y.-S., Lai, C.-I. J., Lakhotia, K., Lin, Y. Y., Liu, A. T., Shi, J., Chang, X., Lin, G.-T., Huang, T.-H., Tseng, W.-C., Lee, K., Liu, D.-R., Huang, Z., Dong, S., Li, S.-W., Watanabe, S., Mohamed, A., & Lee, H. (2021). SUPERB: Speech Processing Universal PERformance Benchmark. Interspeech 2021, 1194\u20131198. https:\/\/doi.org\/10.21437\/Interspeech.2021-1775","journal-title":"Interspeech 2021"},{"issue":"12","key":"Giannakopoulos:2015","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0144610","article-title":"pyAudioAnalysis: An open-source Python library for audio signal analysis","volume":"10","author":"Giannakopoulos","year":"2015","unstructured":"Giannakopoulos, T. (2015). pyAudioAnalysis: An open-source Python library for audio signal analysis. PLoS One, 10(12), 1\u201317. https:\/\/doi.org\/10.1371\/journal.pone.0144610","journal-title":"PLoS One"},{"issue":"September","key":"Watanabe:2018","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456","article-title":"ESPNet: End-to-end speech processing toolkit","volume":"2018-Septe","author":"Watanabe","year":"2018","unstructured":"Watanabe, S., Hori, T., Karita, S., Hayashi, T., Nishitoba, J., Unno, Y., Soplin, N. E. Y., Heymann, J., Wiesner, M., Chen, N., Renduchintala, A., & Ochiai, T. (2018). ESPNet: End-to-end speech processing toolkit. Proc. Annu. Conf. Int. Speech Commun. Assoc. INTERSPEECH, 2018-Septe(September), 2207\u20132211. https:\/\/doi.org\/10.21437\/Interspeech.2018-1456","journal-title":"Proc. Annu. Conf. Int. Speech Commun. Assoc. INTERSPEECH"},{"key":"speechbrain:2021","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2106.04624","article-title":"SpeechBrain: A general-purpose speech toolkit","author":"Ravanelli","year":"2021","unstructured":"Ravanelli, M., Parcollet, T., Plantinga, P., Rouhe, A., Cornell, S., Lugosch, L., Subakan, C., Dawalatabad, N., Heba, A., Zhong, J., Chou, J.-C., Yeh, S.-L., Fu, S.-W., Liao, C.-F., Rastorgueva, E., Grondin, F., Aris, W., Na, H., Gao, Y., \u2026 Bengio, Y. (2021). SpeechBrain: A general-purpose speech toolkit. https:\/\/doi.org\/10.48550\/arXiv.2106.04624"},{"key":"spotlight:2023","article-title":"Spotlight","author":"Suwelack","year":"2023","unstructured":"Suwelack, S. (2023). Spotlight. In GitHub repository. https:\/\/github.com\/Renumics\/spotlight\/; GitHub.","journal-title":"GitHub repository"},{"key":"opensmile:2010","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246","article-title":"openSMILE \u2013 the munich versatile and fast open-source audio feature extractor","author":"Eyben","year":"2010","unstructured":"Eyben, F., W\u00f6llmer, M., & Schuller, B. (2010). openSMILE \u2013 the munich versatile and fast open-source audio feature extractor. MM\u201910 - Proceedings of the ACM Multimedia 2010 International Conference, 1459\u20131462. https:\/\/doi.org\/10.1145\/1873951.1874246","journal-title":"MM\u201910 - Proceedings of the ACM Multimedia 2010 International Conference"},{"key":"wav2vec:2020","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.11477","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., & Auli, M. (2020). wav2vec 2.0: A framework for self-supervised learning of speech representations. In H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, & H. Lin (Eds.), Advances in neural information processing systems (Vol. 33, pp. 12449\u201312460). Curran Associates, Inc. https:\/\/doi.org\/10.48550\/arXiv.2006.11477","journal-title":"Advances in neural information processing systems"},{"key":"burkhardt:2022-syntact","article-title":"SyntAct : A Synthesized Database of Basic Emotions","author":"Burkhardt","year":"2022","unstructured":"Burkhardt, F., Eyben, F., & Schuller, W. (2022). SyntAct : A Synthesized Database of Basic Emotions. In Jonne S\u00e4lev\u00e4 & C. Lignos (Eds.), Proc. Work. Dataset creat. Low. Lang. Within 13th lang. Resour. Eval. conf. European Language Resources Association.","journal-title":"Proc. Work. Dataset creat. Low. Lang. Within 13th lang. Resour. Eval. conf."},{"key":"Atmaja:2024a","doi-asserted-by":"publisher","DOI":"10.1109\/O-COCOSDA64382.2024.10800111","article-title":"Uncertainty-based ensemble learning for speech classification","author":"Atmaja","year":"2024","unstructured":"Atmaja, B. T., Sasou, A., & Burkhardt, F. (2024). Uncertainty-based ensemble learning for speech classification. 2024 27th Conference of the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques (o-COCOSDA), 1\u20136. https:\/\/doi.org\/10.1109\/O-COCOSDA64382.2024.10800111","journal-title":"2024 27th conference of the oriental COCOSDA international committee for the co-ordination and standardisation of speech databases and assessment techniques (o-COCOSDA)"},{"key":"Burkhardt:2024","doi-asserted-by":"publisher","DOI":"10.1109\/O-COCOSDA64382.2024.10800580","article-title":"Check your audio data: Nkululeko for bias detection","author":"Burkhardt","year":"2024","unstructured":"Burkhardt, F., Atmaja, B. T., Derington, A., & Eyben, F. (2024). Check your audio data: Nkululeko for bias detection. 2024 27th Conference of the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques (o-COCOSDA), 1\u20136. https:\/\/doi.org\/10.1109\/O-COCOSDA64382.2024.10800580","journal-title":"2024 27th conference of the oriental COCOSDA international committee for the co-ordination and standardisation of speech databases and assessment techniques (o-COCOSDA)"},{"key":"Atmaja:2025","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW65056.2025.11011272","article-title":"Pathological voice detection from sustained vowels: Handcrafted vs. Self-supervised learning","author":"Atmaja","year":"2025","unstructured":"Atmaja, B. T., & Sasou, A. (2025). Pathological voice detection from sustained vowels: Handcrafted vs. Self-supervised learning. 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW). https:\/\/doi.org\/10.1109\/ICASSPW65056.2025.11011272","journal-title":"2025 IEEE international conference on acoustics, speech, and signal processing workshops (ICASSPW)"},{"key":"Atmaja:2025b","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIIC64266.2025.10920862","article-title":"Performance-weighted ensemble learning for speech classification","author":"Atmaja","year":"2025","unstructured":"Atmaja, B. T., Burkhardt, F., & Sasou, A. (2025). Performance-weighted ensemble learning for speech classification. 2025 International Conference on Artificial Intelligence in Information and Communication (ICAIIC). https:\/\/doi.org\/10.1109\/ICAIIC64266.2025.10920862","journal-title":"2025 international conference on artificial intelligence in information and communication (ICAIIC)"}],"container-title":["Journal of Open Source Software"],"original-title":[],"link":[{"URL":"https:\/\/joss.theoj.org\/papers\/10.21105\/joss.08049.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T14:36:47Z","timestamp":1762180607000},"score":1,"resource":{"primary":{"URL":"https:\/\/joss.theoj.org\/papers\/10.21105\/joss.08049"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,3]]},"references-count":16,"journal-issue":{"issue":"115","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["10.21105\/joss.08049"],"URL":"https:\/\/doi.org\/10.21105\/joss.08049","relation":{"has-review":[{"id-type":"uri","id":"https:\/\/github.com\/openjournals\/joss-reviews\/issues\/8049","asserted-by":"subject"}],"references":[{"id-type":"doi","id":"10.5281\/zenodo.17349217","asserted-by":"subject"}]},"ISSN":["2475-9066"],"issn-type":[{"value":"2475-9066","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,3]]}}}