Systems, apparatuses, and methods are described for a privacy blocking device configured to prevent receipt, by a listening device, of video and/or audio data until a trigger occurs. A blocker may be configured to prevent receipt of video and/or audio data by one or more microphones and/or one or more cameras of a listening device. The blocker may use the one or more microphones, the one or more cameras, and/or one or more second microphones and/or one or more second cameras to monitor for a trigger. The blocker may process the data. Upon detecting the trigger, the blocker may transmit data to the listening device. For example, the blocker may transmit all or a part of a spoken phrase to the listening device.

In order to detect a replay attack in a speaker recognition system, at least one feature is identified in a detected magnetic field. It is then determined whether the at least one identified feature of the detected magnetic field is indicative of playback of speech through a loudspeaker. If so, it is determined that a replay attack may have taken place.

A sound masking system according to the invention is disclosed in which one or more sound masking loudspeaker assemblies are coupled to one or more electronic sound masking signal generators. The loudspeaker assemblies in the system of the invention have a low directivity index and preferably emit an acoustic sound masking signal that has a sound masking spectrum specifically designed to provide superior sound masking in an open plan office. Each of the plurality of loudspeaker assemblies is oriented to provide the acoustic sound masking signal in a direct path into the predetermined area in which masking sound is needed. In addition, the sound masking system of the invention can include a remote control function by which a user can select from a plurality of stored sets of information for providing from a recipient loudspeaker assembly an acoustic sound masking signal having a-selected sound masking spectrum.

Systems, apparatuses, and methods are described for a privacy blocking device configured to prevent receipt, by a listening device, of video and/or audio data until a trigger occurs. A blocker may be configured to prevent receipt of video and/or audio data by one or more microphones and/or one or more cameras of a listening device. The blocker may use the one or more microphones, the one or more cameras, and/or one or more second microphones and/or one or more second cameras to monitor for a trigger. The blocker may process the data. Upon detecting the trigger, the blocker may transmit data to the listening device. For example, the blocker may transmit all or a part of a spoken phrase to the listening device.

A microphone jammer includes a base and a signal generator mounted to the base. The signal generator is configured to generate an ultrasonic signal. The jammer also includes one or more transducers mounted to the base and configured to transmit the ultrasonic signal. The one or more transducers are mounted in a curved layout about the base.

A wireless sound-emitting device includes a housing adapted to be coupled to a wall at a source of electric power, a loudspeaker positioned at a periphery of the housing, a control module outputting an electric audio signal to the at least one loudspeaker, and a wireless communications module in electrical communication with the control module. The loudspeaker emits acoustic signals in a direction parallel to the wall, when the housing is coupled to the wall, with the acoustic signals reflecting off the wall. The device may produce a sound masking noise or play a sound recorded on an internal memory. The device may include an electric plug or be adapted to replace an electric outlet faceplate. The device may have electric pass-through outlets and may be powered by the source of electric power. The device may be controlled remotely, for example via an Internet of Things (IoT) platform.

A method of phrase extraction for ASR models includes obtaining audio data characterizing an utterance and a corresponding ground-truth transcription of the utterance and modifying the audio data to obfuscate a particular phrase recited in the utterance. The method also includes processing, using a trained ASR model, the modified audio data to generate a predicted transcription of the utterance, and determining whether the predicted transcription includes the particular phrase by comparing the predicted transcription of the utterance to the ground-truth transcription of the utterance. When the predicted transcription includes the particular phrase, the method includes generating an output indicating that the trained ASR model leaked the particular phrase from a training data set used to train the ASR model.

A speech reproduction device for reproducing speech based on a received speech signal so that the reproduced speech is intelligible in a clear speech zone and unintelligible in a masked speech zone includes an audio processing module configured for receiving the speech signal; a set of speech loudspeakers configured for reproducing the speech based on one or more speech loudspeaker signals; and a set of masking sound loudspeakers configured for producing a masking sound based on one or more masking sound loudspeaker signals, wherein the masking sound masks the speech in the masked speech zone; wherein the audio processing module includes a speech signal analysis module configured for producing one or more analysis signals based on spectral and/or temporal characteristics of the speech signal; wherein the audio processing module includes a masking sound generator configured for producing one or more masking sound signals based on the one or more analysis signals.

A system and method to prevent eavesdropping by a device. An anti-eavesdrop component is installed on the device. The anti-eavesdrop component is configured to actively prevent the device from capturing audio from the environment. In response to installing the anti-eavesdrop component, the device recognizes the anti-eavesdrop component as a primary audio input for the device. The anti-eavesdrop component then proceeds to block the device from capturing outside audio by injecting noise or otherwise interfering with the primary audio input.

A sound masking system includes a self-amplified loudspeaker emitter unit, with a driver and enlarged ported enclosure, sufficient to provide a frequency range down to a low frequency, such as about 125 Hz. To deliver the power, the power distribution architecture includes audio power amplifiers in the emitter housing of each loudspeaker. Raw power is delivered to each emitter unit through a cable and connectors, such as an Ethernet cable and connectors, in the same cable with the sound masking and audio signals. Inside the emitter units are electronics that efficiently convert the raw power and low level signal to drive the loudspeaker directly. The power comes from a typical desktop power supply, from which the power is combined with the sound masking and audio signals using a power injector unit that distributes the combined power and signals to loudspeakers. The loudspeakers can connect to an individually addressed sound masking network.