Abstract: Techniques related to implementing neural networks for speech recognition systems are discussed. Such techniques may include processing a node of the neural network by determining a score for the node as a product of weights and inputs such that the weights are fixed point integer values, applying a correction to the score based a correction value associated with at least one of the weights, and generating an output from the node based on the corrected score.

Abstract: Technologies for identifying sounds are disclosed. A sound identification device may capture sound data, and split the sound data into frames. The sound identification device may then determine an acoustic feature vector for each frame, and determine parameters based on how each acoustic feature varies over the duration of time corresponding to the frames. The sound identification device may then determine if the sound matches a pre-defined sound based on the parameters. In one embodiment, the sound identification device may be a baby monitor, and the pre-defined sound may be a baby crying.

Abstract: A method in a computing device for decoding a weighted finite state transducer (WFST) for automatic speech recognition is described. The method includes sorting a set of one or more WFST arcs based on their arc weight in ascending order. The method further includes iterating through each arc in the sorted set of arcs according to the ascending order until the score of the generated token corresponding to an arc exceeds a score threshold. The method further includes discarding any remaining arcs in the set of arcs that have yet to be considered.

Abstract: A language model is modified for a local speech recognition system using remote speech recognition sources. In one example, a speech utterance is received. The speech utterance is sent to at least one remote speech recognition system. Text results corresponding to the utterance are received from the remote speech recognition system. A local text result is generated using local vocabulary. The received text results and the generated text result are compared to determine words that are out of the local vocabulary and the local vocabulary is updated using the out of vocabulary words.

Abstract: A system, article, and method of automatic speech recognition with dynamic vocabularies is described herein.

Abstract: A systems, article, and method of automatic speech recognition using on-the-fly word lattice generation with word histories.

Abstract: Techniques related to implementing neural networks for speech recognition systems are discussed. Such techniques may include implementing frame skipping with approximated skip frames and/or distances on demand such that only those outputs needed by a speech decoder are provided via the neural network or approximation techniques.

Abstract: A system, article, and method of environment-sensitive automatic speech recognition.

Abstract: Embodiments of a system and method for adapting a phase difference-based noise reduction system are generally described herein. In some embodiments, spatial information associated with a first and second audio signal are determined, wherein the first and second audio signals including a target audio inside a beam and noise from outside the beam. A signal-to-noise ratio (SNR) associated with the audio signals is estimated. A mapping of phase differences to gain factors is adapted for determination of attenuation factors for attenuating frequency bins associated with noise outside the beam. Spectral subtraction is performed to remove estimated noise from the single-channel signal based on a weighting that affects frequencies associated with a target signal less. Frequency dependent attenuation factors are applied to attenuate frequency bins outside the beam to produce a target signal having noise reduced.

Abstract: A systems, article, and method of automatic speech recognition using on-the-fly word lattice generation with word histories.

Abstract: A method in a computing device for decoding a weighted finite state transducer (WFST) for automatic speech recognition is described. The method includes sorting a set of one or more WFST arcs based on their arc weight in ascending order. The method further includes iterating through each arc in the sorted set of arcs according to the ascending order until the score of the generated token corresponding to an arc exceeds a score threshold. The method further includes discarding any remaining arcs in the set of arcs that have yet to be considered.

Abstract: Techniques related to implementing neural networks for speech recognition systems are discussed. Such techniques may include implementing frame skipping with approximated skip frames and/or distances on demand such that only those outputs needed by a speech decoder are provided via the neural network or approximation techniques.

Abstract: Embodiments of a system and method for adapting a phase difference-based noise reduction system are generally described herein. In some embodiments, spatial information associated with a first and second audio signal are determined, wherein the first and second audio signals including a target audio inside a beam and noise from outside the beam. A signal-to-noise ratio (SNR) associated with the audio signals is estimated. A mapping of phase differences to gain factors is adapted for determination of attenuation factors for attenuating frequency bins associated with noise outside the beam. Spectral subtraction is performed to remove estimated noise from the single-channel signal based on a weighting that affects frequencies associated with a target signal less. Frequency dependent attenuation factors are applied to attenuate frequency bins outside the beam to produce a target signal having noise reduced.