{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T16:05:12Z","timestamp":1785945912682,"version":"3.56.0"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3288409","type":"journal-article","created":{"date-parts":[[2023,6,23]],"date-time":"2023-06-23T20:53:34Z","timestamp":1687553614000},"page":"2523-2533","source":"Crossref","is-referenced-by-count":369,"title":["AudioLM: A Language Modeling Approach to Audio Generation"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0007-829X","authenticated-orcid":false,"given":"Zal\u00e1n","family":"Borsos","sequence":"first","affiliation":[{"name":"Google, Research, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rapha\u00ebl","family":"Marinier","sequence":"additional","affiliation":[{"name":"Google, Research, Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Damien","family":"Vincent","sequence":"additional","affiliation":[{"name":"Google, Research, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eugene","family":"Kharitonov","sequence":"additional","affiliation":[{"name":"Google, Research, Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olivier","family":"Pietquin","sequence":"additional","affiliation":[{"name":"Google, Research, Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0316-3281","authenticated-orcid":false,"given":"Matt","family":"Sharifi","sequence":"additional","affiliation":[{"name":"Google, Research, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2155-450X","authenticated-orcid":false,"given":"Dominik","family":"Roblek","sequence":"additional","affiliation":[{"name":"Google, Research, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olivier","family":"Teboul","sequence":"additional","affiliation":[{"name":"Google, Research, Paris, CA, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8847-9532","authenticated-orcid":false,"given":"David","family":"Grangier","sequence":"additional","affiliation":[{"name":"Google, Research, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7682-6795","authenticated-orcid":false,"given":"Marco","family":"Tagliasacchi","sequence":"additional","affiliation":[{"name":"Google, Research, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6896-3987","authenticated-orcid":false,"given":"Neil","family":"Zeghidour","sequence":"additional","affiliation":[{"name":"Google, Research, Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1755"},{"key":"ref57","article-title":"Self-supervised audio representation learning for mobile devices","author":"tagliasacchi","year":"2019"},{"key":"ref12","first-page":"2022","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"yu","year":"0","journal-title":"Trans Mach Learn Res"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414460"},{"key":"ref15","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref59","article-title":"Self-supervised representation learning for speech using visual grounding and masked language modeling","author":"peng","year":"2022"},{"key":"ref14","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume":"9","author":"lakhotia","year":"2021","journal-title":"Trans Assoc Comput Linguistics"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3200909"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref52","article-title":"Abx-discriminability measures and applications","author":"schatz","year":"2016"},{"key":"ref11","first-page":"2022","article-title":"Vector-quantized image modeling with improved VQGAN","author":"yu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383461"},{"key":"ref10","article-title":"PaLM: Scaling language modeling with pathways","author":"chowdhery","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref19","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref18","article-title":"Scaling up models and data with $\\mathtt {t5x}$ and $\\mathtt {seqio}$","author":"roberts","year":"2022"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-441"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-demo.1"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.593"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10007"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref41","first-page":"8535","article-title":"General-purpose, long-context autoregressive modeling with perceiver AR","volume":"162","author":"hawthorne","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref44","article-title":"Jukebox: A generative model for music","author":"dhariwal","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_7"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-015-0054-9"},{"key":"ref8","first-page":"1877","article-title":"Language models are few-shot learners","author":"brown","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","article-title":"WaveGrad: Estimating gradients for waveform generation","author":"chen","year":"0","journal-title":"Int Conf Learn Representations"},{"key":"ref9","article-title":"Scaling language models: Methods, analysis & insights from training gopher","author":"rae","year":"2021"},{"key":"ref4","first-page":"17022","article-title":"Hifi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"0","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref3","first-page":"14881","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","first-page":"2021","article-title":"DiffWave: A versatile diffusion model for audio synthesis","author":"kong","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1563"},{"key":"ref40","first-page":"2021","article-title":"Rethinking attention with performers","author":"choromanski","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref35","article-title":"MDA: Language models for dialog applications","author":"thoppilan","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref37","article-title":"Deep learning for symbolic mathematics","author":"lample","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref36","article-title":"Evaluating large language models trained on code","author":"chen","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383605"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref32","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref2","first-page":"2415","article-title":"Efficient neural audio synthesis","volume":"80","author":"kalchbrenner","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref1","article-title":"WaveNet: A generative model for raw audio","author":"oord","year":"2016"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00353"},{"key":"ref38","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"raffel","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref24","first-page":"1141","article-title":"Soft-to-hard vector quantization for end-to-end learned compression of images and neural networks","author":"agustsson","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","first-page":"14837","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","author":"razavi","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1816"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461487"},{"key":"ref20","first-page":"3915","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","volume":"80","author":"oord","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref64","first-page":"2709","article-title":"Yourtts: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume":"162","author":"casanova","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref63","article-title":"ASVspoof 2021: Automatic speaker verification spoofing and countermeasures challenge evaluation plan","author":"delgado","year":"2021"},{"key":"ref22","first-page":"6306","article-title":"Neural discrete representation learning","author":"oord","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","article-title":"High fidelity speech synthesis with adversarial networks","author":"binkowski","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref28","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632723"},{"key":"ref29","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref60","article-title":"A robustly optimized BERT pretraining approach","author":"liu","year":"2019"},{"key":"ref62","article-title":"Enabling factorized piano music modeling and generation with the MAESTRO dataset","author":"hawthorne","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1182"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10158503.pdf?arnumber=10158503","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,31]],"date-time":"2023-07-31T17:40:37Z","timestamp":1690825237000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10158503\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3288409","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}