A throat microphone may include one or more transducers that are in contact with the skin in the region of the larynx of person, and may provide a vibration signal to a processing unit. The vibration signal may also include energy and information relating to secondary physiological phenomena such as breathing and heartbeat, in addition to the desired sonic signal. The processing unit may utilize information relating to the secondary physiological phenomena to control a filter that outputs the desired sonic signal.

A wearable device using a bone conduction speaker, including a wearable band worn on an arm of a user, a communication module attached to the wearable band, an audio processor configured to process an audio signal transmitted and received through the communication module, a microphone configured to transmit a voice signal, which is input in sound by the user, to the audio processor, a bone conduction speaker configured to output a reception audio signal, which is processed by the audio processor, in bone conduction mode, and an echo canceller configured to cancel the voice signal in an audio signal output from the bone conduction speaker, is provided.

A wearable device using a bone conduction speaker, including a wearable band worn on an arm of a user, a communication module attached to the wearable band, an audio processor configured to process an audio signal transmitted and received through the communication module, a microphone configured to transmit a voice signal, which is input in sound by the user, to the audio processor, a bone conduction speaker configured to output a reception audio signal, which is processed by the audio processor, in bone conduction mode, and an echo canceller configured to cancel the voice signal in an audio signal output from the bone conduction speaker, is provided.

MEMS microphone and vibration sensor dies and packages are described. In an embodiment, a MEMS microphone and vibration sensor die includes a die substrate, a MEMS microphone on the die substrate and a MEMS vibration sensor on the die substrate. The MEMS vibration sensor may include a plurality of beams with different proof masses corresponding to different resonant frequencies, wherein the different proof masses comprise a same material as the die substrate.

MEMS microphone and vibration sensor dies and packages are described. In an embodiment, a MEMS microphone and vibration sensor die includes a die substrate, a MEMS microphone on the die substrate and a MEMS vibration sensor on the die substrate. The MEMS vibration sensor may include a plurality of beams with different proof masses corresponding to different resonant frequencies, wherein the different proof masses comprise a same material as the die substrate.

MEMS microphone and vibration sensor dies and packages are described. In an embodiment, a MEMS microphone and vibration sensor die includes a die substrate, a MEMS microphone on the die substrate and a MEMS vibration sensor on the die substrate. The MEMS vibration sensor may include a plurality of beams with different proof masses corresponding to different resonant frequencies, wherein the different proof masses comprise a same material as the die substrate.

MEMS microphone and vibration sensor dies and packages are described. In an embodiment, a MEMS microphone and vibration sensor die includes a die substrate, a MEMS microphone on the die substrate and a MEMS vibration sensor on the die substrate. The MEMS vibration sensor may include a plurality of beams with different proof masses corresponding to different resonant frequencies, wherein the different proof masses comprise a same material as the die substrate.

Disclosed herein are methods and apparatuses for the transmission of audio information from a bone-conduction headset to a user. The bone-conduction headset may be mounted on a glasses-style support structure. The bone-conduction transducer may be mounted near where the glasses-style support structure approach a wearer's ears. In one embodiment, an apparatus has a bone-conduction transducer with a diaphragm configured to vibrate based on a magnetic field. The magnetic field being based off an applied electric field. The apparatus may also have an anvil coupled to the diaphragm. The anvil may be configured to conduct the vibration from the bone-conduction transducer. Additionally, the anvil may be coupled to a metallic component. The metallic component may be configured to couple to a magnetic field created by the bone-conduction transducer.

Disclosed herein are methods and apparatuses for the transmission of audio information from a bone-conduction headset to a user. The bone-conduction headset may be mounted on a glasses-style support structure. The bone-conduction transducer may be mounted near where the glasses-style support structure approach a wearer's ears. In one embodiment, an apparatus has a bone-conduction transducer with a diaphragm configured to vibrate based on a magnetic field. The magnetic field being based off an applied electric field. The apparatus may also have an anvil coupled to the diaphragm. The anvil may be configured to conduct the vibration from the bone-conduction transducer. Additionally, the anvil may be coupled to a metallic component. The metallic component may be configured to couple to a magnetic field created by the bone-conduction transducer.

Systems and methods are provided for performing operations comprising: detecting, by one or more electromyograph (EMG) electrodes of an EMG communication device, subthreshold muscle activation signals of one or more muscles associated with speech production, the subthreshold muscle activation signals being generated in response to inner speech of a user; applying a machine learning technique to the subthreshold muscle activation signals to estimate one or more speech features corresponding to the subthreshold muscle activation signals, the machine learning technique being trained to establish a relationship between a plurality of training subthreshold muscle activation signals and ground truth speech features; generating visual or audible output based on the one or more speech features; and causing the visual or audible output to be processed by a messaging application to engage a feature of the messaging application.