Speech recognition

Industry

  • CPC
  • G10L15/00
This industry / category may be too specific. Please go to a parent level for more data

Current Industry

Sub Industries

G10L15/005Language recognition G10L15/01Assessment or evaluation of speech recognition systems G10L15/02Feature extraction for speech recognition Selection of recognition unit G10L15/04Segmentation Word boundary detection G10L15/05Word boundary detection G10L15/06Creation of reference templates Training of speech recognition systems G10L15/063Training G10L15/065Adaptation G10L15/07to the speaker G10L15/075supervised G10L15/08Speech classification or search G10L15/083Recognition networks G10L15/10using distance or distortion measures between unknown speech and reference templates G10L15/12using dynamic programming techniques G10L15/14using statistical models G10L15/142Hidden Markov Models [HMMs] G10L15/144Training of HMMs G10L15/146with insufficient amount of training data G10L15/148Duration modelling in HMMs G10L15/16using artificial neural networks G10L15/18using natural language modelling G10L15/1807using prosody or stress G10L15/1815Semantic context G10L15/1822Parsing for meaning understanding G10L15/183using context dependencies G10L15/187Phonemic context G10L15/19Grammatical context G10L15/193Formal grammars G10L15/197Probabilistic grammars G10L15/20Speech recognition techniques specially adapted for robustness in adverse environments G10L15/22Procedures used during a speech recognition process G10L15/222Barge in G10L15/24Speech recognition using non-acoustical features G10L15/25using position of the lips, movement of the lips or face analysis G10L15/26Speech to text systems G10L15/265Speech recognisers specially adapted for particular applications G10L15/28Constructional details of speech recognition systems G10L15/285Memory allocation or algorithm optimisation to reduce hardware requirements G10L15/30Distributed recognition G10L15/32Multiple recognisers used in sequence or in parallel Score combination systems therefor G10L15/34Adaptation of a single recogniser for parallel processing