{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T18:42:58Z","timestamp":1770748978396,"version":"3.50.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832156","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"1115-1122","source":"Crossref","is-referenced-by-count":3,"title":["WHISMA: A Speech-LLM to Perform Zero-Shot Spoken Language Understanding"],"prefix":"10.1109","author":[{"given":"Mohan","family":"Li","sequence":"first","affiliation":[{"name":"Toshiba Europe Ltd,Cambridge Research Laboratory,Cambridge,UK"}]},{"given":"Cong-Thanh","family":"Do","sequence":"additional","affiliation":[{"name":"Toshiba Europe Ltd,Cambridge Research Laboratory,Cambridge,UK"}]},{"given":"Simon","family":"Keizer","sequence":"additional","affiliation":[{"name":"Toshiba Europe Ltd,Cambridge Research Laboratory,Cambridge,UK"}]},{"given":"Youmna","family":"Farag","sequence":"additional","affiliation":[{"name":"Toshiba Europe Ltd,Cambridge Research Laboratory,Cambridge,UK"}]},{"given":"Svetlana","family":"Stoyanchev","sequence":"additional","affiliation":[{"name":"Toshiba Europe Ltd,Cambridge Research Laboratory,Cambridge,UK"}]},{"given":"Rama","family":"Doddipatla","sequence":"additional","affiliation":[{"name":"Toshiba Europe Ltd,Cambridge Research Laboratory,Cambridge,UK"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-55560-2_5"},{"key":"ref5","article-title":"GPT-4 technical report","volume-title":"arXiv preprint arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref6","article-title":"Llama 3 model card","year":"2024"},{"key":"ref7","article-title":"BLSP: Bootstrapping language-speech pre-training via behavior alignment of continuation writing","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2309.00916"},{"key":"ref8","article-title":"SALMONN: Towards generic hearing abilities for large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Tang"},{"key":"ref9","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":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.263"},{"key":"ref11","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref12","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref13","article-title":"Stanford alpaca: An instruction-following llama model","author":"Taori","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.588"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/EMC2-NIPS53020.2019.00021"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.459"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447605"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389703"},{"key":"ref23","article-title":"LLaSM: Large language and speech model","author":"Shu","year":"2023","journal-title":"arXiv preprint arXiv:2308.15930"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.151"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-26"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref27","article-title":"Librisqa: Pioneering freeform and open-ended spoken question answering with a novel dataset and framework","author":"Zhao","year":"2023","journal-title":"arXiv preprint arXiv:2308.10390"},{"key":"ref28","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023042"},{"key":"ref31","article-title":"ASR-GLUE: A new multi-task benchmark for asr-robust natural language understanding","author":"Feng","year":"2021","journal-title":"arXiv preprint arXiv:2108.13048"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389768"},{"key":"ref33","article-title":"Finstreder: Simple and fast spoken language understanding with finite state transducers using modern speech-to-text models","author":"Bermuth","year":"2022","journal-title":"arXiv preprint arXiv:2206.14589"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832156.pdf?arnumber=10832156","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:39:22Z","timestamp":1737398362000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832156\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832156","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}