EffDiffSE: Efficient Diffusion-Based Frequency-Domain Speech Enhancement with Hybrid Discriminative and Generative DNNs - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Yihui Fu, Renzheng Shi, Marvin Sach, Wouter Tirry, Tim Fingscheidt. EffDiffSE: Efficient Diffusion-Based Frequency-Domain Speech Enhancement with Hybrid Discriminative and Generative DNNs. In IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2025, Tahoe City, CA, USA, October 12-15, 2025. pages 1-5, IEEE, 2025. [doi]

This author has not been identified. Look up 'Yihui Fu' in GoogleThis author has not been identified. Look up 'Renzheng Shi' in GoogleThis author has not been identified. Look up 'Marvin Sach' in GoogleThis author has not been identified. Look up 'Wouter Tirry' in GoogleThis author has not been identified. Look up 'Tim Fingscheidt' in Google

runs on WebDSL