Inventor · Bellevue, WA, US

Dong Yu

56Patents
6h-index
37Co-inventors
72Inventor score

Filing activity: Nov 15, 1984 → Mar 8, 2024

Most-cited inventions

PatentTitleAreaCited byStatus
US4908222A Microwave brewing apparatus and method Emerging Cross-Sectional Technologies 37 Expired
US9818431B2 Multi-speaker speech separation Physics 23 Active
US9390712B2 Mixed speech recognition Physics 23 Active
US4675434A Process for producing phthalic acid esters Chemistry; Metallurgy 16 Expired
US9824684B2 Prediction-based sequence recognition Physics 12 Active
US7240373B2 Simplified and stable hat construction with rotatable brim Human Necessities 10 Expired
US11004443B2 Multistage curriculum training framework for acoustic-to-word speech recognition Physics 4 Active
US12094481B2 ADL-UFE: all deep learning unified front-end system Physics 2 Active
US11302301B2 Learnable speed control for speech synthesis Physics 2 Active
US11902757B2 Techniques for unified acoustic echo suppression using a recurrent neural network Electricity 2 Active
US11776556B2 Unified deep neural network model for acoustic echo cancellation and residual echo suppression Physics 1 Active
US11183168B2 Singing voice conversion Physics 1 Active
US11410652B2 Multi-look enhancement modeling and application for keyword spotting Electricity 1 Active
US11688412B2 Multi-modal framework for multi-channel target speech separation Physics 1 Active
US11170167B2 Automatic lexical sememe prediction system using lexical dictionaries Physics 1 Active
US11011154B2 Enhancing hybrid self-attention structure with relative-position-aware bias for speech synthesis Physics 1 Active
US11037547B2 Token-wise training for attention based end-to-end speech recognition Physics 1 Active
US11380307B2 All deep learning minimum variance distortionless response beamformer for speech separation and enhancement Physics 1 Active
US11423906B2 Multi-tap minimum variance distortionless response beamformer with neural networks for target speech separation Physics 1 Active
US12373643B2 Efficient zero shot event extraction with context definition Physics 0 Active
US11257481B2 Multi-task training architecture and strategy for attention-based speech recognition system Physics 0 Active
US11551136B2 N-best softmax smoothing for minimum bayes risk training of attention based sequence-to-sequence models Physics 0 Active
US12354594B2 Techniques for disentangled variational speech representation learning for zero-shot voice conversion Physics 0 Active
US11128435B2 Distributed and collaborative analytics of encrypted data using deep polynomial networks Physics 0 Active
US11468879B2 Duration informed attention network for text-to-speech analysis Physics 0 Active

Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.