{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T06:59:29Z","timestamp":1774594769101,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T00:00:00Z","timestamp":1768521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T00:00:00Z","timestamp":1768521600000},"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":[[2026,1,16]]},"DOI":"10.1109\/iciis69028.2026.11450741","type":"proceedings-article","created":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:48:40Z","timestamp":1774554520000},"page":"162-167","source":"Crossref","is-referenced-by-count":0,"title":["Feature Conditioned Diffusion for Audio Generation"],"prefix":"10.1109","author":[{"given":"Shakthi","family":"Perera","sequence":"first","affiliation":[{"name":"University of Peradeniya,Dept. of Electrical and Electronic Eng.,Peradeniya,Sri Lanka"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sandunika","family":"Ranasinghe","sequence":"additional","affiliation":[{"name":"University of Peradeniya,Dept. of Electrical and Electronic Eng.,Peradeniya,Sri Lanka"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Senith","family":"Jayakody","sequence":"additional","affiliation":[{"name":"University of Peradeniya,Dept. of Electrical and Electronic Eng.,Peradeniya,Sri Lanka"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Buwaneka","family":"Epakanda","sequence":"additional","affiliation":[{"name":"University of Peradeniya,Dept. of Electrical and Electronic Eng.,Peradeniya,Sri Lanka"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roshan","family":"Godaliyadda","sequence":"additional","affiliation":[{"name":"University of Peradeniya,Dept. of Electrical and Electronic Eng.,Peradeniya,Sri Lanka"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mervyn Parakrama","family":"Ekanayake","sequence":"additional","affiliation":[{"name":"University of Peradeniya,Dept. of Electrical and Electronic Eng.,Peradeniya,Sri Lanka"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"WaveNet: A Generative Model for Raw Audio","author":"van den Oord","year":"2016"},{"key":"ref2","article-title":"Efficient Neural Audio Synthesis","author":"Kalchbrenner","year":"2018"},{"key":"ref3","article-title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","author":"Kong","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/access.2022.3223444"},{"key":"ref5","first-page":"151","volume-title":"A simple introduction to the KLT (Karhunen\u2014Lo\u00e8ve Transform)","year":"2009"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1121\/1.400476"},{"key":"ref7","article-title":"EDMSound: Spectrogram Based Diffusion Models for Efficient and High-Quality Audio Synthesis","author":"Zhu","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095637"},{"key":"ref9","article-title":"Mel-Refine: A Plug-and-Play Approach to Refine Mel-Spectrogram in Audio Generation","author":"Guo","year":"2024"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v36i10.21350","article-title":"DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism","author":"Liu","year":"2022"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1109\/TASLP.2024.3399607","article-title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","author":"Liu","year":"2024"},{"key":"ref12","article-title":"AudioX: Diffusion Transformer for Anything-to-Audio Generation","author":"Tian","year":"2025"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/aiccsa53542.2021.9686838"},{"key":"ref14","article-title":"Denoising Diffusion Probabilistic Models","author":"Ho","year":"2020"},{"key":"ref15","article-title":"The LJ Speech Dataset","author":"Ito","year":"2017"},{"key":"ref16","article-title":"Spectral and Rhythm Features for Audio Classification with Deep Convolutional Neural Networks","author":"Wolf-Monheim","year":"2024"},{"key":"ref17","article-title":"Irmas: a dataset for instrument recognition in musical audio signals","author":"Bosch","year":"2014"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1121\/1.1915893"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2018.8461368"},{"key":"ref20","article-title":"Mel Frequency Cepstral Coefficients for Music Modeling","volume-title":"International Society for Music Information Retrieval Conference","author":"Logan"},{"issue":"4","key":"ref21","first-page":"543","article-title":"Design, analysis and experimental evaluation of block based transformation in MFCC computation for speaker recognition","volume-title":"Speech Communication","volume":"54","author":"Sahidullah","year":"2012"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1121\/1.404385"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tsa.2003.814375"},{"key":"ref24","article-title":"Adam: A Method for Stochastic Optimization","author":"Kingma","year":"2017"},{"key":"ref25","article-title":"Reliable Fidelity and Diversity Metrics for Generative Models","author":"Naeem","year":"2020"},{"key":"ref26","article-title":"Fr\u00e9chet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms","author":"Kilgour","year":"2019"},{"key":"ref27","article-title":"Reducing over-smoothness in speech synthesis using generative adversarial networks","author":"Sheng","year":"2018"},{"key":"ref28","first-page":"5679","article-title":"Speech waveform synthesis from mfcc sequences with generative adversarial networks","volume-title":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).","author":"Juvela"},{"key":"ref29","article-title":"Comparing Representations for Audio Synthesis Using Generative Adversarial Networks","author":"Nistal","year":"2020"},{"issue":"1","key":"ref30","article-title":"Research on the Karhunen\u2013Lo\u00e8ve Transform Method and Its Application to Hull Form Optimization","volume-title":"Journal of Marine Science and Engineering","volume":"11","author":"Chang","year":"2023"},{"key":"ref31","first-page":"105485","article-title":"Smart audio signal classification for tracking of construction tasks","volume-title":"Automation in Construction","volume":"165","author":"Mannem","year":"2024"}],"event":{"name":"2025 IEEE 19th International Conference on Industrial and Information Systems (ICIIS)","location":"Peradeniya, Sri Lanka","start":{"date-parts":[[2026,1,16]]},"end":{"date-parts":[[2026,1,17]]}},"container-title":["2025 IEEE 19th International Conference on Industrial and Information Systems (ICIIS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11450556\/11450558\/11450741.pdf?arnumber=11450741","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T05:28:11Z","timestamp":1774589291000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11450741\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,16]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/iciis69028.2026.11450741","relation":{},"subject":[],"published":{"date-parts":[[2026,1,16]]}}}