{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T07:17:44Z","timestamp":1781248664288,"version":"3.54.1"},"reference-count":182,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/jstsp.2025.3640535","type":"journal-article","created":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T18:37:17Z","timestamp":1764873437000},"page":"2-31","source":"Crossref","is-referenced-by-count":4,"title":["A Survey on Speech Large Language Models for Understanding"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0858-1527","authenticated-orcid":false,"given":"Jing","family":"Peng","sequence":"first","affiliation":[{"name":"X-LANCE Lab, School of Computer Science, MoE Key Laboratory of Artificial Intelligence, Jiangsu Key Laboratory of Language Computing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7039-9235","authenticated-orcid":false,"given":"Yucheng","family":"Wang","sequence":"additional","affiliation":[{"name":"ETH Zürich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4428-4065","authenticated-orcid":false,"given":"Bohan","family":"Li","sequence":"additional","affiliation":[{"name":"X-LANCE Lab, School of Computer Science, MoE Key Laboratory of Artificial Intelligence, Jiangsu Key Laboratory of Language Computing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8114-2085","authenticated-orcid":false,"given":"Yiwei","family":"Guo","sequence":"additional","affiliation":[{"name":"X-LANCE Lab, School of Computer Science, MoE Key Laboratory of Artificial Intelligence, Jiangsu Key Laboratory of Language Computing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7959-0336","authenticated-orcid":false,"given":"Hankun","family":"Wang","sequence":"additional","affiliation":[{"name":"X-LANCE Lab, School of Computer Science, MoE Key Laboratory of Artificial Intelligence, Jiangsu Key Laboratory of Language Computing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7677-4697","authenticated-orcid":false,"given":"YanGui","family":"Fang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8448-0190","authenticated-orcid":false,"given":"Yu","family":"Xi","sequence":"additional","affiliation":[{"name":"X-LANCE Lab, School of Computer Science, MoE Key Laboratory of Artificial Intelligence, Jiangsu Key Laboratory of Language Computing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8096-4664","authenticated-orcid":false,"given":"Haoyu","family":"Li","sequence":"additional","affiliation":[{"name":"X-LANCE Lab, School of Computer Science, MoE Key Laboratory of Artificial Intelligence, Jiangsu Key Laboratory of Language Computing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8239-8320","authenticated-orcid":false,"given":"Xu","family":"Li","sequence":"additional","affiliation":[{"name":"AISpeech Company, Ltd., Jiangsu Key Laboratory of Language Computing, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Data Science, The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1523-9631","authenticated-orcid":false,"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Intelligence Science and Technology, Nanjing University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7102-9826","authenticated-orcid":false,"given":"Kai","family":"Yu","sequence":"additional","affiliation":[{"name":"X-LANCE Lab, School of Computer Science, MoE Key Laboratory of Artificial Intelligence, Jiangsu Key Laboratory of Language Computing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Snips voice platform: An embedded spoken language understanding system for private-by-design voice interfaces","author":"Coucke","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846294"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/9781119992691"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2396"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref6","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Graves","year":"2014"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/622"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-47"},{"issue":"3","key":"ref10","first-page":"664","article-title":"ASR error mitigation for improving spoken language understanding","volume":"27","author":"Tur","year":"2013","journal-title":"Comput. Speech Lang."},{"key":"ref11","first-page":"2220","article-title":"Lattice rescoring for speech-to-SQL translation","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Ladhak","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639043"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461785"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10890"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1570"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746137"},{"key":"ref18","first-page":"2267","article-title":"End-to-end spoken question answering with pretrained transformers","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Seo","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref21","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in English and Mandarin","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amodei","year":"2016"},{"key":"ref22","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2022.3188113"},{"key":"ref25","article-title":"SALMONN: Towards generic hearing abilities for large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tang","year":"2024"},{"key":"ref26","article-title":"Seed-ASR: Understanding diverse speech and contexts with LLM-based speech recognition","author":"Bai","year":"2024"},{"key":"ref27","article-title":"Listen, think, and understand","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gong","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889444"},{"key":"ref29","article-title":"An embarrassingly simple approach for LLM with strong ASR capacity","author":"Ma","year":"2024"},{"key":"ref30","article-title":"FireRedASR: Open-source industrial-grade mandarin speech recognition models from encoder-decoder to LLM integration","author":"Xu","year":"2025"},{"key":"ref31","first-page":"18090","article-title":"Pengi: An audio language model for audio tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Deshmukh","year":"2023"},{"key":"ref32","article-title":"OSUM: Advancing open speech understanding models with limited resources in academia","author":"Geng","year":"2025"},{"key":"ref33","article-title":"On the landscape of spoken language models: A comprehensive survey","volume-title":"Trans. Mach. Learn. Res.","author":"Arora","year":"2025"},{"key":"ref34","article-title":"WavChat: A survey of spoken dialogue models","author":"Ji","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.682"},{"key":"ref36","article-title":"Qwen-Audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023"},{"key":"ref37","article-title":"Qwen2-Audio technical report","author":"Chu","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-457"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.59.103006.093629"},{"key":"ref40","volume-title":"Thinking, Fast and Slow","author":"Kahneman","year":"2011"},{"key":"ref41","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","volume-title":"Proc. 40th Annu. Meeting Assoc. Comput. Linguistics","author":"Papineni","year":"2002"},{"key":"ref42","article-title":"SeamlessM4T-massively multilingual & multimodal machine translation","author":"Barrault","year":"2023"},{"key":"ref43","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out: Proc. ACL-04 Workshop","author":"Lin","year":"2004"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref45","first-page":"5","article-title":"The Kaldi speech recognition toolkit","volume-title":"Proc. IEEE workshop Autom. Speech Recognit. Understanding","author":"Povey","year":"2011"},{"key":"ref46","first-page":"2","article-title":"The CMU sphinx-4 speech recognition system","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech Signal Process.","volume":"1","author":"Lamere","year":"2003"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2383614"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-402"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.393"},{"key":"ref50","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref52","first-page":"2097","article-title":"SpeechFormer: Redesigning the transformer architecture for end-to-end spoken language understanding","volume-title":"Proc. Interspeech","author":"Qian","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3009477"},{"key":"ref54","first-page":"12345","article-title":"SpokenCot: Chain-of-thought prompting for speech language models","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Huang","year":"2023"},{"key":"ref55","first-page":"4160","article-title":"SLAM: A unified encoder for speech and language modeling via speech-text joint pre-training","volume-title":"Proc. 60th Annu. Meeting Assoc. Comput. Linguistics","author":"Bapna","year":"2022"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref57","article-title":"High fidelity neural audio compression","author":"Dfossez","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref58","first-page":"27826","article-title":"Unsupervised speech recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Baevski","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i21.30570"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.416"},{"key":"ref63","article-title":"Low-resource domain adaptation for speech LLMs via text-only fine-tuning","author":"Fang","year":"2025"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW65056.2025.11010998"},{"key":"ref65","article-title":"MinMo: A multimodal large language model for seamless voice interaction","author":"Chen","year":"2025"},{"key":"ref66","article-title":"Step-audio 2 technical report","author":"Wu","year":"2025"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447605"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-488"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11031"},{"key":"ref70","first-page":"11","article-title":"PandaGPT: One model to instruction-follow them all","volume-title":"Proc. 1st Workshop Taming Large Lang. Models: Controllability Interactive Assistants!","author":"Su","year":"2023"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389742"},{"key":"ref73","article-title":"Speech translation with large language models: An industrial practice","author":"Huang","year":"2023"},{"key":"ref74","article-title":"An embarrassingly simple approach for LLM with strong ASR capacity","author":"Ma","year":"2024"},{"key":"ref75","article-title":"Audio Flamingo: A novel audio language model with few-shot learning and dialogue abilities","author":"Kong","year":"2024"},{"key":"ref76","article-title":"BLSP: Bootstrapping language-speech pre-training via behavior alignment of continuation writing","author":"Wang","year":"2023"},{"key":"ref77","article-title":"SpeechVerse: A large-scale generalizable audio language model","author":"Das","year":"2024"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP63861.2024.10800447"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.416"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.263"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-95-5382-2_5"},{"key":"ref82","article-title":"Audio flamingo 2: An audio-language model with long-audio understanding and expert reasoning abilities","author":"Ghosh","year":"2025"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.985"},{"key":"ref84","article-title":"DeSTA2.5-audio: Toward general-purpose large audio language model with self-generated cross-modal alignment","author":"Lu","year":"2025"},{"key":"ref85","article-title":"MiDashengLM: Efficient audio understanding with general audio captions","author":"Dinkel","year":"2025"},{"key":"ref86","article-title":"Qwen2.5-omni technical report","author":"Xu","year":"2025"},{"key":"ref87","article-title":"Kimi-audio technical report","author":"Ding","year":"2025"},{"key":"ref88","article-title":"Audio flamingo 3: Advancing audio intelligence with fully open large audio language models","author":"Goel","year":"2025"},{"key":"ref89","article-title":"MIMO-audio: Audio language models are few-shot learners","author":"Xiaomi","year":"2025"},{"key":"ref90","article-title":"UALM: Unified audio language model for understanding, generation and reasoning","author":"Tian","year":"2025"},{"key":"ref91","article-title":"Qwen3-Omni technical report","author":"Xu","year":"2025"},{"key":"ref92","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"van den Oord","year":"2017"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/MASSP.1984.1162229"},{"key":"ref95","article-title":"Decoder-only architecture for speech recognition with CTC prompts and text data augmentation","author":"Tsunoo","year":"2024"},{"key":"ref96","article-title":"AudioPaLM: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.521"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2025.3588378"},{"key":"ref99","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.4324\/9781315015637-36"},{"key":"ref101","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kong","year":"2020"},{"key":"ref102","article-title":"Qwen2.5 technical report","author":"Qwen","year":"2025"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-968"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445874"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447553"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1669"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446898"},{"key":"ref108","article-title":"Enhancing zero-shot text-to-speech synthesis with human feedback","author":"Chen","year":"2024"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10890510"},{"key":"ref110","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref111","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","author":"Rafailov","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref112","article-title":"SpeechAlign: Aligning speech generation to human preferences","author":"Zhang","year":"2024"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref115","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2019"},{"key":"ref116","article-title":"AISHELL-2: Transforming Mandarin ASR research into industrial scale","author":"Du","year":"2018"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-755"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1965"},{"key":"ref122","first-page":"1","article-title":"The ami meeting corpus","volume-title":"Proc. Int. Conf. Methods Techn. Behav. Res.","author":"Kraaij","year":"2005"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2337"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054017"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2936282"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683474"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-2028"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746828"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1050"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2444"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref135","first-page":"2012","article-title":"Must-C: A multilingual speech translation corpus","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguist.: Hum. Lang. Technol., Vol. 1 (Long Short Papers)","author":"Gangi","year":"2019"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2027"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023141"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746465"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746270"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1397"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.3115\/116580.116613"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075823"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3356098"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.588"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-957"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-876"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1714"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639505"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.91"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-612"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447109"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.109"},{"key":"ref154","article-title":"MMAU: A massive multi-task audio understanding and reasoning benchmark","author":"Sakshi","year":"2024"},{"key":"ref155","article-title":"MMAR: A challenging benchmark for deep reasoning in speech, audio, music, and their mix","author":"Ma","year":"2025"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.281"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/578"},{"key":"ref158","article-title":"HeySQuAD: A spoken question answering dataset","author":"Wu","year":"2023"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-2011"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2025.04.001"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.298"},{"key":"ref162","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee","year":"2005"},{"key":"ref163","article-title":"BERTScore: Evaluating text generation with BERT","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2020"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.365"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.153"},{"key":"ref166","article-title":"Samba-ASR state-of-the-art speech recognition leveraging structured state-space models","author":"Shakhadri","year":"2025"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.5"},{"key":"ref168","article-title":"Efficient long-distance latent relation-aware graph neural network for multi-modal emotion recognition in conversations","author":"Shou","year":"2024"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref170","article-title":"Baichuan-omni-1.5 technical report","author":"Li","year":"2025"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1216"},{"key":"ref172","article-title":"Audio-CoT: Exploring chain-of-thought reasoning in large audio language model","author":"Ma","year":"2025"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746682"},{"key":"ref174","article-title":"MOSA: Mixtures of simple adapters outperform monolithic approaches in LLM-based multilingual ASR","author":"Li","year":"2025"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00638"},{"key":"ref176","first-page":"1","article-title":"Quantifying language models\u2019 sensitivity to spurious features in prompt design or: How i learned to start worrying about prompt formatting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sclar","year":"2024"},{"key":"ref177","article-title":"IFEval-Audio: Instruction-following evaluation in the audio domain","author":"Xu","year":"2024"},{"key":"ref178","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref179","article-title":"PEFT: State-of-the-art parameter-efficient fine-tuning methods","author":"Dettmers","year":"2023"},{"key":"ref180","article-title":"MMSU: A massive multi-task spoken language understanding and reasoning benchmark","author":"Wang","year":"2025"},{"key":"ref181","first-page":"46595","article-title":"Judging LLM-as-a-judge with MT-bench and chatbot arena","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zheng","year":"2023"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/11409413\/11278041.pdf?arnumber=11278041","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T06:57:21Z","timestamp":1772002641000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11278041\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":182,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2025.3640535","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.175321809.95815200\/v1","asserted-by":"object"}]},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}