{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T22:19:54Z","timestamp":1782857994667,"version":"3.54.5"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095171","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["A Content Adaptive Learnable \"Time-Frequency\" Representation for audio Signal Processing"],"prefix":"10.1109","author":[{"given":"Prateek","family":"Verma","sequence":"first","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chris","family":"Chafe","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-38"},{"key":"ref12","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017"},{"key":"ref15","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020"},{"key":"ref14","article-title":"Neural style transfer for audio spectograms","author":"verma","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747908"},{"key":"ref11","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","author":"skerry","year":"2018","journal-title":"ICML"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682553"},{"key":"ref2","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref17","article-title":"Soundnet: Learning sound representations from unlabeled video","volume":"29","author":"aytar","year":"2016","journal-title":"NIPS"},{"key":"ref16","article-title":"Multi-format contrastive learning of audio representations","author":"wang","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-1"},{"key":"ref24","first-page":"24206","article-title":"Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text","volume":"34","author":"akbari","year":"2021","journal-title":"NeurIPS"},{"key":"ref23","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"shazeer","year":"2017"},{"key":"ref26","first-page":"451","article-title":"A pitch estimation filter robust to high levels of noise (pefac)","author":"gonzalez","year":"2011","journal-title":"2011 19th European Signal Processing Conference"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-679"},{"key":"ref20","article-title":"Pretrained transformers as universal computation engines","author":"lu","year":"2021"},{"key":"ref22","first-page":"1068","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","author":"engel","year":"2017","journal-title":"ICML"},{"key":"ref21","article-title":"Fsd50k: an open dataset of human-labeled sound events","author":"fonseca","year":"2020"},{"key":"ref28","article-title":"Leaf: A learnable frontend for audio classification","author":"zeghidour","year":"2021"},{"key":"ref27","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"2016"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3120633"},{"key":"ref8","article-title":"Speech2vec: A sequence-to-sequence framework for learning word embeddings from speech","author":"yu-an","year":"2018"},{"key":"ref7","article-title":"Jukebox: A generative model for music","author":"dhariwal","year":"2020"},{"key":"ref9","article-title":"A framework for contrastive and generative learning of audio representations","author":"verma","year":"2020"},{"key":"ref4","article-title":"Finetuned language models are zero-shot learners","author":"wei","year":"2021"},{"key":"ref3","article-title":"Transformers for image recognition at scale","author":"dosovitskiy","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.23919\/DAFx51585.2021.9768298"},{"key":"ref5","article-title":"Audio transformers: Transformer architectures for large scale audio understanding","author":"verma","year":"2021"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095171.pdf?arnumber=10095171","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T14:06:01Z","timestamp":1700489161000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095171\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095171","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}