8 results about "Vocal tract" patented technology

Techniques for processing measurement data streams for a person's speech apparatus are disclosed. The measurement data streams can be recorded by different sensor modalities, such as audio recordings or articulatory measurements, for example, which have an observable which quantifies a characteristic property of the vocal tract. The measurement data streams can be processed by means of a machine-learned model in order to obtain a temporal sequence of feature vectors in an articulatory feature space. These specific feature vectors enable a variety of applications, such as articulation training, therapeutic applications in the event of speech restrictions, for instance after a stroke, vocal training or speech synthesis.

This utility model discloses a sound port protection structure for an acoustic product, comprising an acoustic product, a shell, a soft rubber sleeve, and a waterproof cloth. The opening of the shell is equipped with a short vertical baffle, a high vertical baffle, and a horizontal baffle, forming staggered upper and lower sound channels. This utility model has a reasonable structural design. The soft rubber sleeve covers the acoustic product, providing cushioning and shock absorption, thus offering initial protection. Utilizing the properties of the waterproof cloth, it allows sound to pass through while blocking liquids and particles, providing excellent waterproof and dustproof effects. Simultaneously, the structural cooperation of the short, high, and horizontal baffles forms a staggered labyrinthine structure of upper, middle, and lower sound channels. The tortuous and staggered sound channel paths effectively block directly intruding rainwater, washing water jets, and larger dust particles, greatly reducing the risk of high-pressure water directly impacting the waterproof cloth, while sound waves can easily propagate through the tortuous sound channel paths with minimal sound loss, ensuring acoustic performance.

The utility model discloses a mirror leg with acoustic guide sound structure, including mirror leg body, the mirror leg body includes main part and ear bending part, and the main part is equipped with the air inlet and main body cavity that intercommunicate, and the ear bending part is equipped with ear bending cavity, and the main body cavity and ear bending cavity are intercommunicate, be equipped with the acoustic generation unit for generating acoustic signal in the main body cavity, the ear bending part is equipped with the sound outlet, and the ear bending cavity is equipped with the guide sound structure, and the guide sound structure inside forms the acoustic conduction sound channel with the sound outlet intercommunication. The utility model technical scheme is designed in order to solve the problem of low acoustic efficiency, low frequency response weakness and poor wearing adaptability in the prior art.

Systems and methods for providing a binaural virtualization by upmixing the left and right input signals to produce left, right, and center channels, mixing the left and right input signals with the upmixed left and right channels respectively at a proportion given by a center-only reverb amount value, then reverberating the output of the mixing prior to virtualization. This can be further simplified by mode switching between two different filtering modes: a standard mode and a simplified mode.

Audio applications determine the left amplitude of the audio source. LS k ) and the right amplitude of the audio source ( RS k Audio applications determine amplitude differences. D k Audio application computing D k time derivative d(D k ) Audio applications determine LS k and RS k The average value is used to obtain the mid-channel spectrum ( MCS k Audio applications for MCS k Normalization is performed to obtain the normalized value (R). k Audio applications will use d(D) K Divide by R k To obtain the confidence map, the audio application calculates the blending weights by scaling and cropping the confidence map. The audio application then combines the MCS (Multi-Segment Count). k Mixed weights and L t To obtain the modified left channel and combine the MCS k Mixed weights and R t To obtain the modified right channel.

An in-ear headphone that includes a device housing that defines an interior cavity; a primary acoustic port formed through the device housing; an acoustic driver disposed within the device housing and aligned to emit sound through the primary acoustic port; a deformable ear tip having a sound channel formed through its length and coupled to the device housing such that the sound channel is aligned with the primary acoustic port; and a magnetic alignment system comprising a first set of magnets coupled to the device housing and a second set of magnets coupled to the deformable ear tip, the magnetic alignment system configured to removably couple the deformable ear tip to the device housing and align the ear tip so that it can only be coupled to the device housing in a single orientation.