{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:59:45Z","timestamp":1776887985376,"version":"3.51.2"},"reference-count":48,"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\/icassp49660.2025.10888561","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":6,"title":["Salmon: A Suite for Acoustic Language Model Evaluation"],"prefix":"10.1109","author":[{"given":"Gallil","family":"Maimon","sequence":"first","affiliation":[{"name":"Hebrew University of Jerusalem,School of Computer Science & Eng.,Jerusalem,Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amit","family":"Roth","sequence":"additional","affiliation":[{"name":"Hebrew University of Jerusalem,School of Computer Science & Eng.,Jerusalem,Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yossi","family":"Adi","sequence":"additional","affiliation":[{"name":"Hebrew University of Jerusalem,School of Computer Science & Eng.,Jerusalem,Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3436618"},{"key":"ref2","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":"ref3","article-title":"Textually pretrained speech language models","volume":"36","author":"Hassid","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.21"},{"key":"ref5","article-title":"Spirit-lm: Interleaved spoken and written language model","author":"Nguyen","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447112"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-457"},{"key":"ref8","article-title":"Salmonn: Towards generic hearing abilities for large language models","author":"Tang","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00545"},{"key":"ref10","article-title":"Speechalign: Aligning speech generation to human preferences","author":"Zhang","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.309"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.644"},{"key":"ref13","article-title":"Modeling real-time interactive conversations as timed diarized transcripts","author":"Tanzer","year":"2024"},{"key":"ref14","article-title":"A full-duplex speech dialogue scheme based on large language models","author":"Wang","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i23.34665"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1755"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.593"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-438"},{"key":"ref19","article-title":"Sd-eval: A benchmark dataset for spoken dialogue understanding beyond words","author":"Ao","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref21","first-page":"7616","article-title":"It\u2019s raw! audio generation with state-space models","volume-title":"International Conference on Machine Learning","author":"Goel"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.182"},{"key":"ref23","article-title":"Spoken question answering and speech continuation using spectrogram-powered llm","author":"Nachmani","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-288"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2135"},{"key":"ref26","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.541"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097097"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref31","article-title":"Lauragpt: Listen, attend, understand, and regenerate audio with gpt","author":"Chen","year":"2023"},{"key":"ref32","article-title":"Audiopalm: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref33","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023"},{"key":"ref34","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.218"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448257"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.109"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1905"},{"key":"ref39","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref40","article-title":"The lj speech dataset","author":"Ito","year":"2017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref42","article-title":"Echothief","author":"Warren"},{"key":"ref43","article-title":"Azure tts"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref45","article-title":"Last: Language model aware speech tokenization","author":"Turetzky","year":"2024"},{"key":"ref46","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref47","article-title":"Gpt-4o"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"}],"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\/10888561.pdf?arnumber=10888561","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:47Z","timestamp":1774416287000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888561\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888561","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}