Seofp-net: Compression and acceleration of deep neural networks for speech enhancement using sign-exponent-only floating-pointsJan 1, 2021ยทYu-Chen Lin,Cheng Yu,Yi-Te Hsu,Szu-Wei Fu,Yu Tsao,Tei-Wei Kuoยท 0 min read PDF CiteTypeJournal articlePublicationIEEE/ACM Transactions on Audio, Speech, and Language ProcessingLast updated on Jan 1, 2021 ← Generative Context-Aware Fine-Tuning of Self-Supervised Speech Models Jan 1, 2024Efficient inference for neural machine translation Jan 1, 2020 →