{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T07:09:50Z","timestamp":1771571390021,"version":"3.50.1"},"reference-count":72,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T00:00:00Z","timestamp":1764028800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T00:00:00Z","timestamp":1764028800000},"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":[[2025,11,25]]},"DOI":"10.1109\/fllm67465.2025.11391055","type":"proceedings-article","created":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T20:55:46Z","timestamp":1771534546000},"page":"161-171","source":"Crossref","is-referenced-by-count":0,"title":["Training Strategies for Speech Large Language Models: A Comprehensive Survey"],"prefix":"10.1109","author":[{"given":"Shiqi","family":"Yang","sequence":"first","affiliation":[{"name":"New York University,New York,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyi","family":"Huang","sequence":"additional","affiliation":[{"name":"Independent Researcher,Seattle,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wengran","family":"Xiao","sequence":"additional","affiliation":[{"name":"University of Michigan,New York,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Palm 2 technical report","author":"Anil","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.309"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447553"},{"key":"ref4","article-title":"Snips voice platform: an embedded spoken language understanding system for private-by-design voice interfaces","author":"Coucke","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.682"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1467"},{"key":"ref7","article-title":"Moshi: a speech-text foundation model for real-time dialogue","author":"D\u00e9fossez","year":"2024"},{"key":"ref8","article-title":"Openomni: Advancing open-source omnimodal large language models with progressive multimodal alignment and real-time self-aware emotional speech synthesis","author":"Luo","year":"2025"},{"key":"ref9","article-title":"Seamless: Multilingual expressive and streaming speech translation","author":"Communication","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/e27040426"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13245040"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-2626"},{"key":"ref15","article-title":"The pile: An 800gb dataset of diverse text for language modeling","author":"Gao","year":"2020"},{"key":"ref16","article-title":"Think-j: Learning to think for generative llm-as-a-judge","author":"Huang","year":"2025"},{"key":"ref17","article-title":"Applications of small language models in medical imaging classification with a focus on prompt strategies","author":"Wang","year":"2025"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/bdcc9040087"},{"key":"ref19","article-title":"Hands-on tutorial: Labeling with llm and human-in-the-loop","author":"Artemova","year":"2024"},{"key":"ref20","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref22","article-title":"An embarrassingly simple approach for llm with strong asr capacity","author":"Ma","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3112535"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1121\/1.395275"},{"key":"ref25","article-title":"Voicebench: Benchmarking llm-based voice assistants","author":"Chen","year":"2024"},{"issue":"8","key":"ref26","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref27","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref28","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":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2025.3588378"},{"key":"ref30","article-title":"Seed-asr: Understanding diverse speech and contexts with llm-based speech recognition","author":"Bai","year":"2024"},{"key":"ref31","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":"ref32","article-title":"Qwen technical report","author":"Bai","year":"2023"},{"key":"ref33","article-title":"Salmonn: Towards generic hearing abilities for large language models","author":"Tang","year":"2023"},{"key":"ref34","article-title":"Alas: Measuring latent speech-text alignment for spoken language understanding in multimodal llms","author":"Mousavi","year":"2025"},{"key":"ref35","article-title":"Labeling comic mischief content in online videos with a multimodal hierarchical-cross-attention model","volume-title":"2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)","author":"Baharlouei"},{"key":"ref36","article-title":"Osum: Advancing open speech understanding models with limited resources in academia","author":"Geng","year":"2025"},{"key":"ref37","article-title":"Qwen2 technical report","author":"Team","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747077"},{"key":"ref40","first-page":"58346","article-title":"Dinosr: Self-distillation and online clustering for self-supervised speech representation learning","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref41","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume":"9","author":"Lakhotia","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref42","first-page":"30","article-title":"Spirit-lm: Interleaved spoken and written language model","volume":"13","author":"Nguyen","year":"2025","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref43","article-title":"Uniaudio: An audio foundation model toward universal audio generation","author":"Yang","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688051"},{"key":"ref45","article-title":"Instructspeech: Following speech editing instructions via large language models","volume-title":"Forty-first International Conference on Machine Learning","author":"Huang"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1346"},{"key":"ref47","article-title":"Llama-omni: Seamless speech interaction with large language models","author":"Fang","year":"2025"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888133"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3434445"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.magmar-1.9"},{"key":"ref51","article-title":"Low-resource domain adaptation for speech llms via text-only fine-tuning","author":"Fang","year":"2025"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-377"},{"key":"ref53","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref54","article-title":"Enhancing code llms with reinforcement learning in code generation","author":"Wang","year":"2024"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/RICAI64321.2024.10911374"},{"key":"ref56","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022"},{"key":"ref57","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref58","article-title":"Training a helpful and harmless assistant with rlhf","author":"Bai","year":"2022","journal-title":"Anthropic"},{"key":"ref59","article-title":"Direct preference optimization: Your language model is secretly a reward model","author":"Rafailov","year":"2023"},{"key":"ref60","article-title":"Aligncap: Audio captioning via human preference alignment","author":"Liang","year":"2024","journal-title":"EMNLP"},{"key":"ref61","article-title":"Speechalign: Aligning speech generation to human preferences","author":"Zhang","year":"2024"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.997"},{"key":"ref63","article-title":"Rlaif vs. rlhf: Scaling reinforcement learning from human feedback with ai feedback","author":"Lee","year":"2024"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01861"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-571"},{"key":"ref66","article-title":"Enhancing intent understanding for ambiguous prompts through human-machine co-adaptation","author":"He","year":"2025"},{"key":"ref67","article-title":"Interpreting themes from educational stories","volume-title":"2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)","author":"Zhang"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.sigtyp-1.15"},{"key":"ref69","article-title":"Self-supervised cross-lingual speech representation learning at scale","volume":"1708","author":"Babu","year":"2021"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1388"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2025.3549484"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.55248\/gengpi.5.0524.1273"}],"event":{"name":"2025 3rd International Conference on Foundation and Large Language Models (FLLM)","location":"Vienna, Austria","start":{"date-parts":[[2025,11,25]]},"end":{"date-parts":[[2025,11,28]]}},"container-title":["2025 3rd International Conference on Foundation and Large Language Models (FLLM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11390736\/11390873\/11391055.pdf?arnumber=11391055","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T06:42:17Z","timestamp":1771569737000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11391055\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,25]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/fllm67465.2025.11391055","relation":{},"subject":[],"published":{"date-parts":[[2025,11,25]]}}}