Abstract: An electronic device includes a processor, and a memory containing instructions that, when executed by the processor, cause the electronic device to learn a sound emitted by a legacy device and to issue an output when the electronic device subsequently hears the sound. For example, the electronic device can receive a training input and extract a compact representation of a sound in the training input, which the device stores. The device can receive an audio signal corresponding to an observed acoustic scene and extract a representation of the observed acoustic scene from the audio signal. The electronic device can determine whether the sound is present in the observed acoustic scene at least in part from a comparison of the representation of the observed acoustic scene with the representation of the sound. The electronic device emits a selected output responsive to determining that the sound is present in the acoustic scene.

Abstract: Techniques for monitoring an audio stream for triggering events are disclosed, where the triggering events may include a particular sound identified in the audio stream. In addition, the techniques include detecting the particular sound in the audio stream and/or providing an event notification to a user device via a network connection. A user device can request permission to initiate a two-way audio stream between the computing device and the user device. Further, the techniques may include receiving an indication to initiate the two-way audio stream with the user device. In addition, the techniques may include providing an alert that permission has been granted to initiate the two-way audio stream. Also, the device may include initiating the two-way audio stream with the user device.

Abstract: The subject disclosure provides systems and methods for generating and storing learned embeddings of audio inputs to an electronic device. The electronic device may generate and store encoded versions of audio inputs and learned embeddings of the audio inputs. When a new audio input is obtained, the electronic device can generate an encoded version of the new audio input, compare the encoded version of the new audio input to the stored encoded versions of prior audio inputs, and if the encoded version of the new audio input matches one of the stored encoded versions of the prior audio inputs, the electronic device can provide a stored learned embedding that corresponds to the one of the stored encoded versions of the prior audio inputs to a detection model at the electronic device. The cached embeddings can be provided to locally trained models for detecting individual sounds using electronic devices.

Abstract: An electronic device has one or more microphones that pick up a sound. At least one feature extractor processes the audio signals from the microphones, that contain the picked up the sound, to determine several features for the sound. The electronic device also includes a classifier that has a machine learning model which is configured to determine a sound classification, such as artificial versus natural for the sound, based upon at least one of the determined features. Other aspects are also described and claimed.

Abstract: An electronic device includes a processor, and a memory containing instructions that, when executed by the processor, cause the electronic device to learn a sound emitted by a legacy device and to issue an output when the electronic device subsequently hears the sound. For example, the electronic device can receive a training input and extract a compact representation of a sound in the training input, which the device stores. The device can receive an audio signal corresponding to an observed acoustic scene and extract a representation of the observed acoustic scene from the audio signal. The electronic device can determine whether the sound is present in the observed acoustic scene at least in part from a comparison of the representation of the observed acoustic scene with the representation of the sound. The electronic device emits a selected output responsive to determining that the sound is present in the acoustic scene.

Abstract: An electronic device includes a processor, and a memory containing instructions that, when executed by the processor, cause the electronic device to learn a sound emitted by a legacy device and to issue an output when the electronic device subsequently hears the sound. For example, the electronic device can receive a training input and extract a compact representation of a sound in the training input, which the device stores. The device can receive an audio signal corresponding to an observed acoustic scene and extract a representation of the observed acoustic scene from the audio signal. The electronic device can determine whether the sound is present in the observed acoustic scene at least in part from a comparison of the representation of the observed acoustic scene with the representation of the sound. The electronic device emits a selected output responsive to determining that the sound is present in the acoustic scene.

Abstract: The subject disclosure provides systems and methods for providing locally trained models for detecting individual sounds using electronic devices. Local detection of individual sounds with a detection model at an electronic device can be provided by obtaining training samples for the detection model with the electronic device, and generating additional negative and positive training samples based on the obtained training samples. A two-stage detection process may be provided, in which a trigger model at a device compares an audio input to a reference sound to trigger a detection model at the device. The detection of individual sounds with a detection model at an electronic device can also leverage audio capture capabilities of multiple devices in an acoustic scene to capture multiple concurrent training samples.

Abstract: An electronic device has one or more microphones that pick up a sound. At least one feature extractor processes the audio signals from the microphones, that contain the picked up the sound, to determine several features for the sound. The electronic device also includes a classifier that has a machine learning model which is configured to determine a sound classification, such as artificial versus natural for the sound, based upon at least one of the determined features. Other aspects are also described and claimed.

Abstract: A system and method to process audio data received over the ARC or eARC interface of HDMI from audio sources are provided. A media device may receive compressed audio data in a number of data formats. The media device may convert between the audio formats provided by the audio sources and the audio formats supported by audio playback devices. The media device may inspect frames of audio data to determine if the frames are to be decoded. The frame may be decoded and subsequently encoded into the data formats supported by the audio playback devices. To reduce latency, the media device may enable a pass-through mode to bypass the decoding of the frames to allow the frames to be decoded at the audio playback devices. A bi-directional loopback application may route audio data received over the ARC or eARC interface from the audio sources to the audio playback devices.

Abstract: The embodiments set forth a technique for enabling a computing device to securely configure a peripheral computing device. According to some embodiments, the method can include the steps of (1) approving a request received from the peripheral computing device to engage in a setup procedure for the peripheral computing device, (2) receiving, from the peripheral computing device: (i) an audio signal that encodes a password and timing information, and (ii) a light signal. Additionally, the method can involve, in response to identifying that the timing information correlates with the light signal: (3) extracting the password from the audio signal, and (4) establishing a communication link with the peripheral computing device based on the password. In turn, the method can involve (5) providing configuration information to the peripheral computing device over the communication link.

Abstract: Techniques to use an embedded passcode within an audio ringtone to establish a secure connection for arbitrary phone relay are described. The use of an embedded passcode enables encrypted ad-hoc connections for the relay of audio of an incoming telephone call to a secondary device, such as a virtual assistant enabled smart speaker device.

Abstract: The embodiments set forth a technique for enabling a computing device to securely configure a peripheral computing device. According to some embodiments, the method can include the steps of (1) approving a request received from the peripheral computing device to engage in a setup procedure for the peripheral computing device, (2) receiving, from the peripheral computing device: (i) an audio signal that encodes a password and timing information, and (ii) a light signal. Additionally, the method can involve, in response to identifying that the timing information correlates with the light signal: (3) extracting the password from the audio signal, and (4) establishing a communication link with the peripheral computing device based on the password. In turn, the method can involve (5) providing configuration information to the peripheral computing device over the communication link.

Abstract: A system and method to mitigate the temporary loss of the input sampling clocks when receiving audio data over the ARC or eARC interface of HDMI are provided. A media device may substitute an externally generated clock derived from a local crystal oscillator of the media device for the missing input sampling clock. The external clock may be synchronized to the frequency of the input sampling clock. The media device may synchronize the external clock to the audio data when there is a loss of the input sampling clock. When the input sampling clock of the audio data reappears, the media device may switch back from the external clock to the input sampling clock. When transitioning between the input sampling clock and the external clock, the media device may insert zero padding into the audio data samples to mute any potential glitch in the sound from an audio playback device.

Abstract: A system and method to mitigate the temporary loss of the input sampling clocks when receiving audio data over the ARC or eARC interface of HDMI are provided. A media device may substitute an externally generated clock derived from a local crystal oscillator of the media device for the missing input sampling clock. The external clock may be synchronized to the frequency of the input sampling clock. The media device may synchronize the external clock to the audio data when there is a loss of the input sampling clock. When the input sampling clock of the audio data reappears, the media device may switch back from the external clock to the input sampling clock. When transitioning between the input sampling clock and the external clock, the media device may insert zero padding into the audio data samples to mute any potential glitch in the sound from an audio playback device.

Abstract: A system and method to process audio data received over the ARC or eARC interface of HDMI from audio sources are provided. A media device may receive compressed audio data in a number of data formats. The media device may convert between the audio formats provided by the audio sources and the audio formats supported by audio playback devices. The media device may inspect frames of audio data to determine if the frames are to be decoded. The frame may be decoded and subsequently encoded into the data formats supported by the audio playback devices. To reduce latency, the media device may enable a pass-through mode to bypass the decoding of the frames to allow the frames to be decoded at the audio playback devices. A bi-directional loopback application may route audio data received over the ARC or eARC interface from the audio sources to the audio playback devices.

Abstract: An electronic device includes a processor, and a memory containing instructions that, when executed by the processor, cause the electronic device to learn a sound emitted by a legacy device and to issue an output when the electronic device subsequently hears the sound. For example, the electronic device can receive a training input and extract a compact representation of a sound in the training input, which the device stores. The device can receive an audio signal corresponding to an observed acoustic scene and extract a representation of the observed acoustic scene from the audio signal. The electronic device can determine whether the sound is present in the observed acoustic scene at least in part from a comparison of the representation of the observed acoustic scene with the representation of the sound. The electronic device emits a selected output responsive to determining that the sound is present in the acoustic scene.

Abstract: Methods and systems provide control of media synchronization using time stamp pairs. In an embodiment, a first device may request a time stamp from a second device. The first device may determine any de-synchronization between the first and second devices based on the requested time stamp and characteristics of the request. The first device may define a rate scalar based on the determined de-synchronization. A sample rate conversion may be performed for the first device based on the rate scalar such that the outputs of the first device and the second device are synchronized.

Abstract: Techniques to use an embedded passcode within an audio ringtone to establish a secure connection for arbitrary phone relay are described. The use of an embedded passcode enables encrypted ad-hoc connections for the relay of audio of an incoming telephone call to a secondary device, such as a virtual assistant enabled smart speaker device.

Abstract: An electronic device has one or more microphones that pick up a sound. At least one feature extractor processes the audio signals from the microphones, that contain the picked up the sound, to determine several features for the sound. The electronic device also includes a classifier that has a machine learning model which is configured to determine a sound classification, such as artificial versus natural for the sound, based upon at least one of the determined features. Other aspects are also described and claimed.

Abstract: The embodiments set forth a technique for enabling a computing device to securely configure a peripheral computing device. According to some embodiments, the method can include the steps of (1) approving a request received from the peripheral computing device to engage in a setup procedure for the peripheral computing device, (2) receiving, from the peripheral computing device: (i) an audio signal that encodes a password and timing information, and (ii) a light signal. Additionally, the method can involve, in response to identifying that the timing information correlates with the light signal: (3) extracting the password from the audio signal, and (4) establishing a communication link with the peripheral computing device based on the password. In turn, the method can involve (5) providing configuration information to the peripheral computing device over the communication link.