Abstract: Techniques are provided for defending against an ultrasonic attack on a speech enabled device. A methodology implementing the techniques according to an embodiment includes detecting voice activity in an audio signal received by the device and generating an ultrasonic jamming signal in response to the detection. The jamming signal is broadcast over a loudspeaker for up to the duration of the detected voice activity to defend against the ultrasonic attack. According to another embodiment, the ultrasonic jamming signal is generated in response to detection of a wake-on-voice key phrase in the received audio signal, and the jamming signal is broadcast over the loudspeaker for a time duration selected to be less than or equal to a time window during which spoken commands are accepted by the device following the wake-on-voice key phrase detection. The jamming signal may include white or colored noise, combinations of tones, and/or a periodic sweep frequency.

Abstract: A mechanism is described for facilitating automatic gain adjustment in audio systems according to one embodiment. A method of embodiments, as described herein, includes determining status of one or more of gain settings, mute settings, and boost settings associated with one or more microphones based on a configuration of a computing device including a voice-enabled device. The method may further comprise recommending adjustment of microphone gain based on the configuration and the status of one or more of the gain, mute, and boost settings, and applying the recommended adjustment of the microphone gain.

Abstract: A mechanism is described for facilitating context-based cancellation and amplification of acoustical signals in acoustical environments according to one embodiment. An apparatus of embodiments, as described herein, includes detection and recognition logic to detect an acoustical signal being emitted by an acoustical signal source; evaluation, estimation, and footprint logic to classify the acoustical signal as an emergency acoustical signal or a non-emergency acoustical signal, wherein the classification is based on a footprint or a footprint identification (ID) associated with the acoustical signal; acoustical signal cancellation logic to cancel the acoustical signal if the acoustical signal is regarded as the non-emergency acoustical signal based on the footprint or the footprint ID; and acoustical signal amplification logic to amplify the acoustical signal if the acoustical signal is classified as the emergency acoustical signal based on the footprint or the footprint ID.

Abstract: A mechanism is described for facilitating multi-modal dereverberation in far-field audio systems according to one embodiment. A method of embodiments, as described herein, includes performing geometry estimation of a geographical space based on visuals of the space received from one or more cameras of a computing device. The method may further include computing reverberation time based on the geometry estimation that is further based on the visuals, and computing and applying dereverberation based on the reverberation time.

Abstract: Techniques for improving speech recognition are described. An example of an electronic device includes an extracting unit to extract a reference spectral profile from a reference signal and a device spectral profile from a device signal. A comparing unit compares the reference spectral profile and the device spectral profile. A delta calculating unit calculates a delta between the reference spectral profile and the device spectral profile. A design unit designs a correction filter based on the computed delta.

Abstract: For a multiple microphone system, a phase response mismatch may be corrected. One embodiment includes receiving audio from a first microphone and from a second microphone, the microphones being coupled to a single device for combining the received audio, recording the received audio from the first microphone and the second microphone before combining the received audio, detecting a phase response mismatch in the recording at the device between the audio received at the second microphone and the audio received at the first microphone, if a phase response mismatch is detected, then estimating a phase delay between the second microphone and the first microphone, and storing the estimated phase delay for use in correcting the phase delay in received audio before combining the received audio.

Abstract: An apparatus for acoustical environment understanding in machine-human speech communication is described herein. The apparatus includes one or more microphones to receive audio signals and a sound level metering unit. The sound level metering unit is to determine an environmental sound level based on the audio signals. The apparatus also includes an artificial speech generator that is to render artificial speech based on the environmental sound level.

Abstract: System and techniques for a microphone board for far field automatic speech recognition are described herein. The microphone board may include a first plurality of microphones disposed along a circumference of a circle on a surface and a second plurality of microphones disposed along a line on the surface. First connections to the first plurality of microphones may be grouped together and second connections to the second plurality of microphones are grouped together. The first connections and the second connections may be provided to an external entity of the surface via a connector.

Abstract: System and techniques for automatic gain control for speech recognition are described herein. An audio signal may be obtained. A signal-to-noise ratio (SNR) may be derived from the audio signal. The SNR may be compared to a threshold. A stored gain value may be updated when the SNR is beyond the threshold and the stored gain value may be applied to a descendant (e.g., later) of the audio signal otherwise.

Abstract: System and techniques for automatic speech recognition pre-processing are described herein. First, a plurality of audio channels may be obtained. Then, reverberations mat be removed from the audio channels. The plurality of audio channels may be partitioned into beams after reverberations are removed. A partition corresponding to a beam in the beams may be selected based on a noise level. An audio signal may be filtered from the selected partition. The filtered audio signal may be provided to an external entity via an output interface of the pre-processing pipeline.

Abstract: System and techniques for automatic speech recognition de-reverberation are described herein. A portion of an audio stream may be obtained. here, the portion of the audio stream is a proper subset of the audio stream. A filter may be created by applying Generalized Weighted Prediction Error (GWPE) to the portion of the audio stream. The filter may be applied to the audio stream to remove reverberation. The filtered version of the audio stream may then be provided to an audio stream consumer.

Abstract: Techniques for improving speech recognition are described. An example of an electronic device includes an extracting unit to extract a reference spectral profile from a reference signal and a device spectral profile from a device signal. A comparing unit compares the reference spectral profile and the device spectral profile. A delta calculating unit calculates a delta between the reference spectral profile and the device spectral profile. A design unit designs a correction filter based on the computed delta.