Home >

news Help

Publication Information


Title
Japanese: 
English:LDMSE: Low Computational Cost Generative Diffusion Model for Speech Enhancement 
Author
Japanese: 西 悠希, 篠田 浩一, 岩野 公司.  
English: Yuki Nishi, Koichi Shinoda, Koji Iwano.  
Language English 
Journal/Book name
Japanese: 
English:2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) 
Volume, Number, Page         pp. 1-6
Published date Jan. 27, 2025 
Publisher
Japanese: 
English:IEEE 
Conference name
Japanese: 
English:2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 
Conference site
Japanese: 
English:Macau 
File
DOI https://doi.org/10.1109/APSIPAASC63619.2025.10849051
Abstract Recently, a generative model called diffusion model has attracted attention. Compared to GANs, it can be trained stably but has a high computational cost in the generation stage. This paper proposes a method called Low computational cost Generative Diffusion Model for Speech Enhancement (LDMSE). It reduces its computational cost with comparable quality by compressing speech signals to a latent space using an autoencoder and removing noise in the latent space using the diffusion model. In our evaluation using VOICBANK-DEMAND and WSJ0- CHiME3 datasets, the proposed method reduced the generation time by more than 35% without any degradation in speech quality.

©2007 Institute of Science Tokyo All rights reserved.