{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T23:19:58Z","timestamp":1777591198719,"version":"3.51.4"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447705","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1156-1160","source":"Crossref","is-referenced-by-count":4,"title":["Generation or Replication: Auscultating Audio Latent Diffusion Models"],"prefix":"10.1109","author":[{"given":"Dimitrios","family":"Bralios","sequence":"first","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gordon","family":"Wichern","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fran\u00e7ois G.","family":"Germain","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zexu","family":"Pan","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sameer","family":"Khurana","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chiori","family":"Hori","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan Le","family":"Roux","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. NeurIPS","author":"Song"},{"key":"ref2","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","author":"Ho"},{"key":"ref3","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref5","article-title":"Extracting training data from diffusion models","volume-title":"Proc. USENIX Secur. Symp","author":"Carlini"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00586"},{"key":"ref7","article-title":"Understanding and mitigating copying in diffusion models","volume-title":"Proc. NeurIPS","author":"Somepalli"},{"key":"ref8","article-title":"What neural networks memorize and why: Discovering the long tail via influence estimation","volume-title":"Proc. NeurIPS","author":"Feldman"},{"key":"ref9","article-title":"The privacy onion effect: Memorization is relative","volume-title":"Proc. NeurIPS","author":"Carlini"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833649"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-11245"},{"key":"ref12","first-page":"10697","article-title":"Deduplicating training data mitigates privacy risks in language models","volume-title":"Proc. ICML","author":"Kandpal"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref14","first-page":"119","article-title":"AudioCaps: Generating captions for audios in the wild","volume-title":"Proc. NAACL-HLT","author":"Kim"},{"key":"ref15","article-title":"DiffWave: A versatile diffusion model for audio synthesis","volume-title":"Proc. ICLR","author":"Kong"},{"key":"ref16","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-tospeech","volume-title":"Proc. ICML","author":"Popov"},{"key":"ref17","article-title":"Noise2Music: Textconditioned music generation with diffusion models","author":"Huang","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447265"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"ref20","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"Proc. ICML","author":"Liu"},{"key":"ref21","article-title":"Make-An-Audio: Text-to-audio generation with prompt-enhanced diffusion models","volume-title":"Proc. ICML","author":"Huang"},{"key":"ref22","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","author":"Kong"},{"key":"ref23","article-title":"Foley sound synthesis at the DCASE 2023 challenge","author":"Choi","year":"2023"},{"key":"ref24","article-title":"MusicLM: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01413"},{"key":"ref28","article-title":"The 2021 image similarity dataset and challenge","author":"Douze","year":"2021"},{"key":"ref29","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2002.1203274"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414337"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.577"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447705.pdf?arnumber=10447705","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:31:59Z","timestamp":1722573119000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447705\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447705","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}