{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:09:18Z","timestamp":1779379758569,"version":"3.53.1"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032079558","type":"print"},{"value":"9783032079565","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-07956-5_2","type":"book-chapter","created":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:19:14Z","timestamp":1760253554000},"page":"25-38","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["When Voice Matters: Evidence of\u00a0Gender Disparity in\u00a0Positional Bias of\u00a0SpeechLLMs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0554-7265","authenticated-orcid":false,"given":"Shree Harsha","family":"Bokkahalli Satish","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1643-1054","authenticated-orcid":false,"given":"Gustav Eje","family":"Henter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1175-840X","authenticated-orcid":false,"given":"\u00c9va","family":"Sz\u00e9kely","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,13]]},"reference":[{"key":"2_CR1","doi-asserted-by":"publisher","unstructured":"Ao, J., et al.: SpeechT5: unified-modal encoder-decoder pre-training for spoken language processing (2022). https:\/\/doi.org\/10.48550\/arXiv.2110.07205. arXiv:2110.07205","DOI":"10.48550\/arXiv.2110.07205"},{"key":"2_CR2","doi-asserted-by":"publisher","unstructured":"Bordia, S., Bowman, S.R.: Identifying and reducing gender bias in word-level language models. In: Kar, S., Nadeem, F., Burdick, L., Durrett, G., Han, N.R. (eds.) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop, pp. 7\u201315. Association for Computational Linguistics, Minneapolis (2019). https:\/\/doi.org\/10.18653\/v1\/N19-3002. https:\/\/aclanthology.org\/N19-3002\/","DOI":"10.18653\/v1\/N19-3002"},{"key":"2_CR3","unstructured":"CanopyAI: canopylabs\/orpheus-3b-0.1-ft . hugging face (2025). https:\/\/huggingface.co\/canopylabs\/orpheus-3b-0.1-ft"},{"key":"2_CR4","doi-asserted-by":"publisher","unstructured":"Chakraborty, J., Majumder, S., Menzies, T.: Bias in machine learning software: why? how? what to do? In: Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC\/FSE 2021, pp. 429\u2013440. Association for Computing Machinery, New York (2021). https:\/\/doi.org\/10.1145\/3468264.3468537. https:\/\/dl.acm.org\/doi\/10.1145\/3468264.3468537","DOI":"10.1145\/3468264.3468537"},{"key":"2_CR5","doi-asserted-by":"publisher","unstructured":"Chu, Y., et al.: Qwen2-audio technical report (2024). https:\/\/doi.org\/10.48550\/arXiv.2407.10759. arXiv:2407.10759","DOI":"10.48550\/arXiv.2407.10759"},{"key":"2_CR6","doi-asserted-by":"publisher","unstructured":"Cui, W., Jiao, X., Meng, Z., King, I.: VoxEval: benchmarking the knowledge understanding capabilities of end-to-end spoken language models (2025).https:\/\/doi.org\/10.48550\/arXiv.2501.04962. arXiv:2501.04962","DOI":"10.48550\/arXiv.2501.04962"},{"key":"2_CR7","doi-asserted-by":"publisher","unstructured":"Cui, W., et al.: Recent advances in speech language models: a survey (2025). https:\/\/doi.org\/10.48550\/arXiv.2410.03751., arXiv:2410.03751","DOI":"10.48550\/arXiv.2410.03751"},{"key":"2_CR8","doi-asserted-by":"publisher","unstructured":"Das, N., et al.: SpeechVerse: a large-scale generalizable audio language model (2025). https:\/\/doi.org\/10.48550\/arXiv.2405.08295. arXiv:2405.08295","DOI":"10.48550\/arXiv.2405.08295"},{"key":"2_CR9","doi-asserted-by":"publisher","unstructured":"Deshmukh, S., Elizalde, B., Singh, R., Wang, H.: Pengi: an audio language model for audio tasks (2024). https:\/\/doi.org\/10.48550\/arXiv.2305.11834. arXiv:2305.11834","DOI":"10.48550\/arXiv.2305.11834"},{"issue":"3","key":"2_CR10","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1162\/coli_a_00524","volume":"50","author":"IO Gallegos","year":"2024","unstructured":"Gallegos, I.O., et al.: Bias and fairness in large language models: a survey. Comput. Linguist. 50(3), 1097\u20131179 (2024). https:\/\/doi.org\/10.1162\/coli_a_00524","journal-title":"Comput. Linguist."},{"key":"2_CR11","unstructured":"Gartner: Gartner says conversational AI capabilities will help drive worldwide contact center market to 16% growth in 2023 (2023). https:\/\/www.gartner.com\/en\/newsroom\/press-releases\/2023-07-31-gartner-says-conversational-ai-capabilities-will-help-drive-worldwide-contact-center-market-to-16-percent-growth-in-2023"},{"key":"2_CR12","unstructured":"Hendrycks, D., et al.: Measuring massive multitask language understanding. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=d7KBjmI3GmQ"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Kotek, H., Dockum, R., Sun, D.: Gender bias and stereotypes in large language models. Association for Computing Machinery (2023). https:\/\/dspace.mit.edu\/handle\/1721.1\/153131","DOI":"10.1145\/3582269.3615599"},{"key":"2_CR14","doi-asserted-by":"publisher","unstructured":"Lin, X., Li, L.: Implicit bias in LLMs: a survey (2025). https:\/\/doi.org\/10.48550\/arXiv.2503.02776. arXiv:2503.02776","DOI":"10.48550\/arXiv.2503.02776"},{"key":"2_CR15","doi-asserted-by":"publisher","unstructured":"Lin, Y.C., Chen, W.C., Lee, H.Y.: Spoken stereoset: on evaluating social bias toward speaker in speech large language models. In: 2024 IEEE Spoken Language Technology Workshop (SLT), pp. 871\u2013878 (2024). https:\/\/doi.org\/10.1109\/SLT61566.2024.10832259. https:\/\/ieeexplore.ieee.org\/document\/10832259\/","DOI":"10.1109\/SLT61566.2024.10832259"},{"key":"2_CR16","doi-asserted-by":"publisher","unstructured":"Lum, K., Anthis, J.R., Robinson, K., Nagpal, C., D\u2019Amour, A.: Bias in language models: beyond trick tests and toward RUTEd evaluation (2025). https:\/\/doi.org\/10.48550\/arXiv.2402.12649. arXiv:2402.12649","DOI":"10.48550\/arXiv.2402.12649"},{"key":"2_CR17","doi-asserted-by":"publisher","unstructured":"Ma, Z., et al.: MMAR: a challenging benchmark for deep reasoning in speech, audio, music, and their mix (2025). https:\/\/doi.org\/10.48550\/arXiv.2505.13032. arXiv:2505.13032","DOI":"10.48550\/arXiv.2505.13032"},{"key":"2_CR18","doi-asserted-by":"publisher","unstructured":"Myrzakhan, A., Bsharat, S.M., Shen, Z.: Open-LLM-leaderboard: from multi-choice to open-style questions for LLMs evaluation, benchmark, and arena (2024). https:\/\/doi.org\/10.48550\/arXiv.2406.07545. arXiv:2406.07545","DOI":"10.48550\/arXiv.2406.07545"},{"key":"2_CR19","doi-asserted-by":"publisher","unstructured":"Nadeem, M., Bethke, A., Reddy, S.: StereoSet: measuring stereotypical bias in pretrained language models. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, vol. 1: Long Papers, pp. 5356\u20135371. Association for Computational Linguistics, Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.416. https:\/\/aclanthology.org\/2021.acl-long.416\/","DOI":"10.18653\/v1\/2021.acl-long.416"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Navigli, R., Conia, S.: Biases in large language models: origins, inventory, and discussion. J. Data Inf. Qual. 15(2), 1\u201321 (2023)","DOI":"10.1145\/3597307"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Patel, D., et al.: Exploring temperature effects on large language models across various clinical tasks (2024)","DOI":"10.1101\/2024.07.22.24310824"},{"key":"2_CR22","doi-asserted-by":"publisher","unstructured":"Renze, M., Guven, E.: The effect of sampling temperature on problem solving in large language models (2024). https:\/\/doi.org\/10.48550\/arXiv.2402.05201. arXiv:2402.05201","DOI":"10.48550\/arXiv.2402.05201"},{"key":"2_CR23","unstructured":"Sakshi, S., et al.: MMAU: a massive multi-task audio understanding and reasoning benchmark (2024). https:\/\/openreview.net\/forum?id=TeVAZXr3yv"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Schwartz, R., Vassilev, A., Greene, K.K., Perine, L., Burt, A., Hall, P.: Towards a standard for identifying and managing bias in artificial intelligence. NIST (2022). https:\/\/www.nist.gov\/publications\/towards-standard-identifying-and-managing-bias-artificial-intelligence","DOI":"10.6028\/NIST.SP.1270"},{"key":"2_CR25","doi-asserted-by":"publisher","unstructured":"Slaughter, I., Greenberg, C., Schwartz, R., Caliskan, A.: Pre-trained speech processing models contain human-like biases that propagate to speech emotion recognition. In: Bouamor, H., Pino, J., Bali, K. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 8967\u20138989. Association for Computational Linguistics, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.602. https:\/\/aclanthology.org\/2023.findings-emnlp.602\/","DOI":"10.18653\/v1\/2023.findings-emnlp.602"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Son, M., Won, Y.J., Lee, S.: Optimizing large language models: a deep dive into effective prompt engineering techniques. Appl. Sci. 15(3), 1430 (2025)","DOI":"10.3390\/app15031430"},{"key":"2_CR27","doi-asserted-by":"publisher","unstructured":"Tang, C., et al.: SALMONN: towards generic hearing abilities for large language models (2024). https:\/\/doi.org\/10.48550\/arXiv.2310.13289. arXiv:2310.13289","DOI":"10.48550\/arXiv.2310.13289"},{"key":"2_CR28","doi-asserted-by":"publisher","unstructured":"Wan, Y., Wang, W., He, P., Gu, J., Bai, H., Lyu, M.R.: BiasAsker: measuring the bias in conversational AI system. In: Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC\/FSE 2023, pp. 515\u2013527. Association for Computing Machinery, New York (2023). https:\/\/doi.org\/10.1145\/3611643.3616310. https:\/\/dl.acm.org\/doi\/10.1145\/3611643.3616310","DOI":"10.1145\/3611643.3616310"},{"key":"2_CR29","doi-asserted-by":"publisher","unstructured":"Wu, J., et al.: On decoder-only architecture for speech-to-text and large language model integration (2023). https:\/\/doi.org\/10.48550\/arXiv.2307.03917. arXiv:2307.03917","DOI":"10.48550\/arXiv.2307.03917"},{"key":"2_CR30","doi-asserted-by":"publisher","unstructured":"Zheng, C., Zhou, H., Meng, F., Zhou, J., Huang, M.: Large language models are not robust multiple choice selectors (2024). https:\/\/doi.org\/10.48550\/arXiv.2309.03882. arXiv:2309.03882","DOI":"10.48550\/arXiv.2309.03882"},{"key":"2_CR31","doi-asserted-by":"publisher","unstructured":"Zhioua, S., Binkyt\u0117, R.: Shedding light on underrepresentation and sampling bias in machine learning (2023). https:\/\/doi.org\/10.48550\/arXiv.2306.05068. arXiv:2306.05068","DOI":"10.48550\/arXiv.2306.05068"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-07956-5_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:19:20Z","timestamp":1760253560000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-07956-5_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"ISBN":["9783032079558","9783032079565"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-07956-5_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,13]]},"assertion":[{"value":"13 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Szeged","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hungary","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":"13 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/specom.inf.u-szeged.hu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}