Abstract: A system and method of performing low-power keyword detection is provided. An acoustic signal is obtained comprising speech by an electronic device. The acoustic signal is preprocessed by transforming the acoustic signal to a frequency domain representation. The frequency domain representation is divided into a plurality of frequency bands. The plurality of frequency bands is provided to a neural network. At least one of a plurality of keywords or absence of any of the plurality of keywords is predicted. The acoustic signal can then be provided for additional processing by a higher power processing core.

Abstract: There is provided a system and method for recognizing tone patterns in spoken languages using sequence-to-sequence neural networks in an electronic device. The recognized tone patterns can be used to improve the accuracy for a speech recognition system on tonal languages.

Abstract: There is provided a system and method for processing and/or recognizing acoustic signals. The method comprises obtaining at least one pre-existing speech recognition model; adapting and/or training the at least one pre-existing speech recognition model incrementally when new, previously unseen, user-specific data is received, the data comprising input acoustic signals and/or user action demonstrations and/or semantic information about a meaning of the acoustic signals, wherein the at least one model is incrementally updated by associating new input acoustic signals with input semantic frames to enable recognition of changed input acoustic signals. The method further comprises adapting to a user's vocabulary over time by learning new words and/or removing words no longer being used by the user, generating a semantic frame from an input acoustic signal according to the at least one model, and mapping the semantic frame to a predetermined action.

Abstract: There is provided a system and method for recognizing tone patterns in spoken languages using sequence-to-sequence neural networks in an electronic device. The recognized tone patterns can be used to improve the accuracy for a speech recognition system on tonal languages.

Abstract: A system and method of performing low-power keyword detection is provided. An acoustic signal is obtained comprising speech by an electronic device. The acoustic signal is preprocessed by transforming the acoustic signal to a frequency domain representation. The frequency domain representation is divided into a plurality of frequency bands. The plurality of frequency bands is provided to a neural network. At least one of a plurality of keywords or absence of any of the plurality of keywords is predicted. The acoustic signal can then be provided for additional processing by a higher power processing core.

Abstract: The present disclosure relates to speech recognition systems and methods that enable personalized vocal user interfaces. More specifically, the present disclosure relates to combining a self-learning speech recognition system based on semantics with a speech-to-text system optionally integrated with a natural language processing system. The combined system has the advantage of automatically and continually training the semantics-based speech recognition system and increasing recognition accuracy.

Abstract: There is provided a system and method for processing and/or recognizing acoustic signals. The method comprises obtaining at least one pre-existing speech recognition model; adapting and/or training the at least one pre-existing speech recognition model incrementally when new, previously unseen, user-specific data is received, the data comprising input acoustic signals and/or user action demonstrations and/or semantic information about a meaning of the acoustic signals, wherein the at least one model is incrementally updated by associating new input acoustic signals with input semantic frames to enable recognition of changed input acoustic signals. The method further comprises adapting to a user's vocabulary over time by learning new words and/or removing words no longer being used by the user, generating a semantic frame from an input acoustic signal according to the at least one model, and mapping the semantic frame to a predetermined action.

Abstract: The present disclosure relates to speech recognition systems and methods that enable personalized vocal user interfaces. More specifically, the present disclosure relates to combining a self-learning speech recognition system based on semantics with a speech-to-text system optionally integrated with a natural language processing system. The combined system has the advantage of automatically and continually training the semantics-based speech recognition system and increasing recognition accuracy.