{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T01:11:34Z","timestamp":1785805894541,"version":"3.56.0"},"reference-count":31,"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\/icassp49660.2025.10890120","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":3,"title":["InstantSpeech: Instant Synchronous Text-to-Speech Synthesis for LLM-driven Voice Chatbots"],"prefix":"10.1109","author":[{"given":"Muyang","family":"Du","sequence":"first","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuan","family":"Liu","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjie","family":"Lai","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 Technical Report","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"The LLaMA 3 Herd of Models","author":"Dubey","year":"2024"},{"key":"ref3","article-title":"Gemma: Open Models Based on Gemini Research and Technology","author":"Mesnard","year":"2024","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413889"},{"key":"ref5","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":"ref6","article-title":"Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Jiang"},{"key":"ref7","article-title":"High Fidelity Neural Audio Compression","author":"Defossez","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref8","article-title":"SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447523"},{"key":"ref10","article-title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","author":"Wang","year":"2023","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446214"},{"key":"ref13","article-title":"Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling","author":"Shen"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.346"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref18","first-page":"2410","article-title":"Efficient Neural Audio Synthesis","volume-title":"International Conference on Machine Learning","author":"Kalchbrenner"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/78.258122"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26479"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1655"},{"key":"ref22","first-page":"17022","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":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref24","article-title":"The LJ Speech Dataset","author":"Ito"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.183"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03958"},{"key":"ref28","article-title":"Adam: A Method for Stochastic Optimization","author":"Kingma","year":"2014","journal-title":"CoRR"},{"key":"ref29","first-page":"37524","article-title":"Understanding INT4 Quantization for Language Models: Latency Speedup, Composability, and Failure Cases","volume-title":"International Conference on Machine Learning","author":"Wu"},{"key":"ref30","article-title":"Gemma 2: Improving Open Language Models at a Practical Size","author":"Team","year":"2024"},{"key":"ref31","article-title":"Mistral NeMo: A state-of-the-art 12B model with 128k context length"}],"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\/10890120.pdf?arnumber=10890120","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:20:45Z","timestamp":1774416045000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890120\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890120","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}