{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T15:52:15Z","timestamp":1776181935494,"version":"3.50.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889205","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["SpeechCaps: Advancing Instruction-Based Universal Speech Models with Multi-Talker Speaking Style Captioning"],"prefix":"10.1109","author":[{"given":"Chien-Yu","family":"Huang","sequence":"first","affiliation":[{"name":"National Taiwan University,Taipei,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min-Han","family":"Shih","sequence":"additional","affiliation":[{"name":"University of Southern California,California,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke-Han","family":"Lu","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taipei,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi-Yuan","family":"Hsiao","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taipei,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taipei,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Listen, think, and understand","volume-title":"International Conference on Learning Representations","author":"Gong"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389703"},{"key":"ref4","article-title":"Spoken question answering and speech continuation using spectrogram-powered llm","volume-title":"International Conference on Learning Representations","author":"Nachmani"},{"key":"ref5","article-title":"Audio flamingo: A novel audio language model with few-shot learning and dialogue abilities","volume-title":"International Conference on Machine Learning","author":"Kong"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389742"},{"key":"ref7","article-title":"Salmonn: Towards generic hearing abilities for large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Tang"},{"key":"ref8","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023"},{"key":"ref9","article-title":"Llasm: Large language and speech model","author":"Shu","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.263"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-457"},{"key":"ref12","article-title":"Finetuned language models are zero-shot learners","volume-title":"International Conference on Learning Representations","author":"Wei"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448257"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"ref15","article-title":"Data-speech","author":"Lacombe","year":"2024"},{"key":"ref16","article-title":"Sox - sound exchange","author":"Contributors","year":"2024"},{"key":"ref17","first-page":"18","article-title":"Data augmentation using pre-trained transformer models","volume-title":"Proceedings of the 2nd Workshop on Life-long Learning for Spoken Language Systems","author":"Kumar"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"2225","DOI":"10.18653\/v1\/2021.findings-emnlp.192","article-title":"GPT3Mix: Leveraging large-scale language models for text augmentation","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2021","author":"Yoo","year":"2021"},{"key":"ref19","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref20","article-title":"Claude","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.newsum-1.1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.153"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.870"},{"key":"ref24","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.172"},{"key":"ref26","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref27","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref28","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref29","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref30","first-page":"5178","article-title":"Beats: audio pre-training with acoustic tokenizers","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Chen"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889205.pdf?arnumber=10889205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:04Z","timestamp":1774416184000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889205\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889205","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}