Inventor · Munich, DE

Georg Stemmer

20Patents
5h-index
23Co-inventors
61Inventor score

Filing activity: Sep 17, 2013 → Nov 22, 2019

Most-cited inventions

PatentTitleAreaCited byStatus
US9520128B2 Frame skipping with extrapolation and outputs on demand neural network for automatic speech recognition Physics 32 Active
US10657952B2 Score trend analysis for reduced latency automatic speech recognition Physics 6 Active
US10373630B2 Systems and methods for energy efficient and low power distributed automatic speech recognition on wearable devices Electricity 6 Active
US9899034B2 Technologies for robust crying detection using temporal characteristics of acoustic features Physics 5 Active
US9740678B2 Method and system of automatic speech recognition with dynamic vocabularies Physics 5 Active
US10403268B2 Method and system of automatic speech recognition using posterior confidence scores Physics 4 Active
US10255911B2 System and method of automatic speech recognition using parallel processing for weighted finite state transducer-based speech decoding Physics 4 Active
US9530404B2 System and method of automatic speech recognition using on-the-fly word lattice generation with word histories Physics 4 Active
US10325590B2 Language model modification for local speech recognition systems using remote sources Physics 3 Active
US9672810B2 Optimizations to decoding of WFST models for automatic speech recognition Physics 3 Active
US10217458B2 Technologies for improved keyword spotting Physics 3 Active
US10255909B2 Statistical-analysis-based reset of recurrent neural networks for automatic speech recognition Physics 3 Active
US10672380B2 Dynamic enrollment of user-defined wake-up key-phrase for speech enabled computer system Physics 2 Active
US11308978B2 Systems and methods for energy efficient and low power distributed automatic speech recognition on wearable devices Electricity 1 Active
US10803381B2 Fixed point integer implementations for neural networks Physics 1 Active
US9449594B2 Adaptive phase difference based noise reduction for automatic speech recognition (ASR) Physics 1 Active
US12125482B2 Adaptively recognizing speech using key phrases Physics 0 Active
US11031005B2 Continuous topic detection and adaption in audio environments Physics 0 Active
US10127902B2 Optimizations to decoding of WFST models for automatic speech recognition Physics 0 Active
US10147423B2 Context-aware query recognition for electronic devices Physics 0 Active

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