Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Method for creating and using multiple-word sound models in speech recognition

Method for creating and using multiple-word sound models in speech recognition

US Patent 4837831 · Granted Jun 6, 1989

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Accelerated training of a neural network via regularization2025
Training nodes of a neural network to be decisive2025
Data-dependent training for automated knowledge system that comprises a neural n2025
Generation and discrimination training as a variable resolution game2025
Accelerated training of neural networks with regularization links2025
Creating diverse neural networks with node tying2025
Training an autoencoder with a classifier2025
Locating a decision boundary for complex classifier2025
Deep learning with judgment2025
Targeted incremental growth with continual learning in deep neural networks2025
Node-splitting for neural networks based on magnitude of norm of vector of parti2024
Data-dependent node-to-node knowledge sharing by regularization in deep learning2024