{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:01:17Z","timestamp":1775199677674,"version":"3.50.1"},"reference-count":32,"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\/asru65441.2025.11434634","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":["CASPER: A Large Scale Spontaneous Speech Dataset"],"prefix":"10.1109","author":[{"given":"Cihan","family":"Xiao","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Baltimore,USA"}]},{"given":"Ruixing","family":"Liang","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Baltimore,USA"}]},{"given":"Xiangyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Baltimore,USA"}]},{"given":"Mehmet Emre","family":"Tiryaki","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Baltimore,USA"}]},{"given":"Veronica","family":"Bae","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Baltimore,USA"}]},{"given":"Lavanya","family":"Shankar","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Baltimore,USA"}]},{"given":"Rong","family":"Yang","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Baltimore,USA"}]},{"given":"Ethan","family":"Poon","sequence":"additional","affiliation":[{"name":"Edison Academy Magnet School,USA"}]},{"given":"Emmanuel","family":"Dupoux","sequence":"additional","affiliation":[{"name":"Meta,USA"}]},{"given":"Sanjeev","family":"Khudanpur","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Baltimore,USA"}]},{"given":"Leibny Paola Garcia","family":"Perera","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Baltimore,USA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2307.09288"},{"key":"ref2","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint arXiv:2407.21783"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1201\/9781003606635-75"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.83"},{"key":"ref5","first-page":"146","article-title":"When LLMs meets acoustic landmarks: An efficient approach to integrate speech into large language models for depression detection","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","author":"Zhang"},{"key":"ref6","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":"ref7","article-title":"Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","author":"Du","year":"2024","journal-title":"arXiv preprint arXiv:2407.05407"},{"key":"ref8","article-title":"Cosyvoice 2: Scalable streaming speech synthesis with large language models","volume-title":"arXiv preprint arXiv:2412.10117","author":"Du","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00545"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00430"},{"key":"ref16","article-title":"Moshi: a speech-text foundation model for real-time dialogue","author":"D\u00e9fossez","year":"2024","journal-title":"arXiv preprint arXiv:2410.00037"},{"key":"ref17","article-title":"Callhome american english transcripts","author":"Kingsbury"},{"key":"ref18","article-title":"Santa barbara corpus of spoken american english","author":"Du Bois","year":"2000","journal-title":"Linguistic Data Consortium"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/002383099103400404"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw59228.2023.00006"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-2362"},{"key":"ref22","article-title":"Silero models: pre-trained enterprise-grade stt \/ tts models and benchmarks","author":"Team","year":"2021"},{"key":"ref23","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-78"},{"key":"ref25","article-title":"Seamlessm4t: Massively multilingual & multimodal machine translation","author":"Communication","year":"2023"},{"key":"ref26","article-title":"wav2vec 2.0: a framework for self-supervised learning of speech representations","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems, ser. NIPS \u201820.","author":"Baevski"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-105"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-205"},{"key":"ref29","article-title":"Nemo: a toolkit for building AI applications using neural modules","volume":"abs\/1909.09577","author":"Kuchaiev","year":"2019","journal-title":"CoRR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746806"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414470"}],"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\/11434634.pdf?arnumber=11434634","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:57:29Z","timestamp":1775192249000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434634\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434634","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}