{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:36:20Z","timestamp":1780587380681,"version":"3.54.1"},"reference-count":40,"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\/icassp49660.2025.10888202","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":5,"title":["Low Frame-rate Speech Codec: a Codec Designed for Fast High-quality Speech LLM Training and Inference"],"prefix":"10.1109","author":[{"given":"Edresson","family":"Casanova","sequence":"first","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryan","family":"Langman","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paarth","family":"Neekhara","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shehzeen","family":"Hussain","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason","family":"Li","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Subhankar","family":"Ghosh","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ante","family":"Juki\u0107","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sang-Gil","family":"Lee","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3417347"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref3","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref4","article-title":"Speechtokenizer: Unified speech tokenizer for speech large language models","author":"Zhang","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-335"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096797"},{"key":"ref7","article-title":"Many-to-many spoken language translation via unified speech and text representation learning with unit-to-unit translation","author":"Kim","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095616"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461487"},{"key":"ref10","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683277"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref13","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref14","article-title":"High-fidelity audio compression with improved rvqgan","volume":"36","author":"Kumar","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MP.2006.1664069"},{"key":"ref16","first-page":"17 022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Language-codec: Reducing the gaps between discrete codec representation and speech language models","author":"Ji","year":"2024"},{"key":"ref18","article-title":"Gull: A generative multifunctional audio codec","author":"Luo","year":"2024"},{"key":"ref19","article-title":"Spectral codecs: Spectrogram-based audio codecs for high quality speech synthesis","author":"Langman","year":"2024"},{"key":"ref20","article-title":"Simple and controllable music generation","volume":"36","author":"Copet","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448454"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-537"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1490"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447532"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-108"},{"key":"ref26","article-title":"Wavtokenizer: an efficient acoustic discrete codec tokenizer for audio language modeling","author":"Ji","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3519881"},{"key":"ref28","article-title":"Hifi-codec: Group-residual vector quantization for high fidelity audio codec","author":"Yang","year":"2023"},{"key":"ref29","article-title":"Styletts 2: Towards human-level text-to-speech through style diffusion and adversarial training with large speech language models","volume":"36","author":"Li","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref31","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","author":"Ardila"},{"key":"ref32","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096680"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref35","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1599"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.7488\/ds\/2645"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2016"}],"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\/10888202.pdf?arnumber=10888202","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:43Z","timestamp":1774416223000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888202\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888202","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}