Abstract: A voice-based system is configured to process commands in a flexible format, for example, in which a wake word does not necessarily have to occur at the beginning of an utterance. As in natural speech, the system being addressed may be named within or at the end of a spoken utterance rather than at the beginning, or depending on the context, may not be named at all.

Abstract: A voice-based system is configured to process commands in a flexible format, for example, in which a wake word does not necessarily have to occur at the beginning of an utterance. As in natural speech, the system being addressed may be named within or at the end of a spoken utterance rather than at the beginning, or depending on the context, may not be named at all.

Abstract: A voice-based system is configured to process commands in a flexible format, for example, in which a wake word does not necessarily have to occur at the beginning of an utterance. As in natural speech, the system being addressed may be named within or at the end of a spoken utterance rather than at the beginning, or depending on the context, may not be named at all.

Abstract: There is provided a speech dialog system that includes a first microphone, a second microphone, a processor and a memory. The first microphone captures first audio from a first spatial zone, and produces a first audio signal. The second microphone captures second audio from a second spatial zone, and produces a second audio signal. The processor receives the first audio signal and the second audio signal, and the memory contains instructions that control the processor to perform operations of a speech enhancement module, an automatic speech recognition module, and a speech dialog module that performs a zone-dedicated speech dialog.

Abstract: There is provided a speech dialog system that includes a first microphone, a second microphone, a processor and a memory. The first microphone captures first audio from a first spatial zone, and produces a first audio signal. The second microphone captures second audio from a second spatial zone, and produces a second audio signal. The processor receives the first audio signal and the second audio signal, and the memory contains instructions that control the processor to perform operations of a speech enhancement module, an automatic speech recognition module, and a speech dialog module that performs a zone-dedicated speech dialog.

Abstract: Methods and apparatus to process microphone signals by a speech enhancement module to generate an audio stream signal including first and second metadata for use by a speech recognition module. In an embodiment, speech recognition is performed using endpointing information including transitioning from a silence state to a maybe speech state, in which data is buffered, based on the first metadata and transitioning to a speech state, in which speech recognition is performed, based upon the second metadata.

Abstract: Deep Neural Networks (DNNs) with many hidden layers and many units per layer are very flexible models with a very large number of parameters. As such, DNNs are challenging to optimize. To achieve real-time computation, embodiments disclosed herein enable fast DNN feature transformation via optimized memory bandwidth utilization. To optimize memory bandwidth utilization, a rate of accessing memory may be reduced based on a batch setting. A memory, corresponding to a selected given output neuron of a current layer of the DNN, may be updated with an incremental output value computed for the selected given output neuron as a function of input values of a selected few non-zero input neurons of a previous layer of the DNN in combination with weights between the selected few non-zero input neurons and the selected given output neuron, wherein a number of the selected few corresponds to the batch setting.

Abstract: Methods and apparatus to process microphone signals by a speech enhancement module to generate an audio stream signal including first and second metadata for use by a speech recognition module. In an embodiment, speech recognition is performed using endpointing information including transitioning from a silence state to a maybe speech state, in which data is buffered, based on the first metadata and transitioning to a speech state, in which speech recognition is performed, based upon the second metadata.

Abstract: Deep Neural Networks (DNNs) with many hidden layers and many units per layer are very flexible models with a very large number of parameters. As such, DNNs are challenging to optimize. To achieve real-time computation, embodiments disclosed herein enable fast DNN feature transformation via optimized memory bandwidth utilization. To optimize memory bandwidth utilization, a rate of accessing memory may be reduced based on a batch setting. A memory, corresponding to a selected given output neuron of a current layer of the DNN, may be updated with an incremental output value computed for the selected given output neuron as a function of input values of a selected few non-zero input neurons of a previous layer of the DNN in combination with weights between the selected few non-zero input neurons and the selected given output neuron, wherein a number of the selected few corresponds to the batch setting.