{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:12:08Z","timestamp":1775200328477,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434804","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["CoLMbo: Speaker Language Model for Descriptive Profiling"],"prefix":"10.1109","author":[{"given":"Massa","family":"Baali","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,USA"}]},{"given":"Shuo","family":"Han","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,USA"}]},{"given":"Syed Abdul","family":"Hannan","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,USA"}]},{"given":"Purusottam","family":"Samal","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,USA"}]},{"given":"Karanveer","family":"Singh","sequence":"additional","affiliation":[{"name":"FPrime AI,Pittsburgh,USA"}]},{"given":"Soham","family":"Deshmukh","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,USA"}]},{"given":"Rita","family":"Singh","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,USA"}]},{"given":"Bhiksha","family":"Raj","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-8403-5"},{"key":"ref2","article-title":"Segaa: A unified approach to predicting age, gender, and emotion in speech","author":"A. R","year":"2024"},{"key":"ref3","first-page":"1","article-title":"Prediction of age from speech features using a multi-layer perceptron model","volume-title":"2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT)","author":"Ravishankar"},{"key":"ref4","article-title":"Salmonn: Towards generic hearing abilities for large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Tang"},{"key":"ref5","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023","journal-title":"arXiv preprint arXiv:2311.07919"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0795"},{"key":"ref7","article-title":"Listen, think, and understand","author":"Gong","year":"2023","journal-title":"arXiv preprint arXiv:2305.10790"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.361"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683760"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-563"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21236\/ADA613971"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1804"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1226"},{"issue":"14","key":"ref19","doi-asserted-by":"crossref","first-page":"4785","DOI":"10.3390\/s21144785","article-title":"Gender and age estimation methods based on speech using deep neural networks","volume":"21","author":"Kwasny","year":"2021","journal-title":"Sensors"},{"key":"ref20","article-title":"Explainable attribute-based speaker verification","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv:2405.19796"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832294"},{"key":"ref22","article-title":"Clipcap: Clip prefix for image captioning","author":"Mokady","year":"2021","journal-title":"arXiv preprint arXiv:2111.09734"},{"key":"ref23","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume":"34","author":"Tsimpoukelli","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-153"},{"key":"ref25","first-page":"27403","article-title":"Darpa timit acoustic-phonetic continuous speech corpus cd-rom. nist speech disc 1-1.1","volume-title":"NASA STI\/Recon Technical Report N","volume":"93","author":"Garofolo","year":"1993"},{"key":"ref26","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2302.13971"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i22.34548"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"ICLR"},{"key":"ref29","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434804.pdf?arnumber=11434804","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:57Z","timestamp":1775192397000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434804\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434804","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}