Systems and methods are disclosed for providing voice and noise activity detection with audio automixers that can reject errant non-voice or non-human noises while maximizing signal-to-noise ratio and minimizing audio latency.

Systems and methods are disclosed for providing voice and noise activity detection with audio automixers that can reject errant non-voice or non-human noises while maximizing signal-to-noise ratio and minimizing audio latency.

Embodiments described herein provide a system, apparatus and methods to enable a diver to communicate more clearly with other divers or locations Embodiments process the speech to add clarity, or otherwise convert speech into an outputted form that is more intelligible e.g. so as to simulate the diver's unhindered speech. Embodiments provide hardware and software for receiving and recognizing hindered speech of a diver (e.g., speech hindered by a mouthpiece) and then augmenting the speech with generated output sounds corresponding to the intended speech sound or generating or replacing at least some of the diver's speech with synthesized words. The output sounds may be in the speaker's own voice or a synthesized voice. Embodiments may be configured to add clarity to and/or augment speech that is hindered by the wearing of a mouthpiece from a snorkel, SCUBA or other diving apparatus.

Systems and methods are disclosed for providing voice and noise activity detection with audio automixers that can reject errant non-voice or non-human noises while maximizing signal-to-noise ratio and minimizing audio latency.

Described herein is a system for device arbitration using acoustic characteristics of a physical space, such as a user's household. The system generates a matrix of inter-device attenuation factors. The inter-device attenuation factors are determined using the attenuation experienced by a first device versus the attenuation experienced by a second device. Once the matrix is generated, an attenuation vector representing the attenuation corresponding to an input audio signal is determined and compared to the matrix. Based on the comparison, the system selects a device for further processing.

A method includes extracting, from multiple microphone input, a hyperset of features of acoustic sources, using the extracted features to identify separable clusters associated with acoustic scenarios, and classifying subsequent input as one of the acoustic scenarios using the hyperset of features. The acoustic scenarios include a desired spatially moving/non-moving talker, and an undesired spatially moving/non-moving acoustic source. The hyperset of features includes both spatial and voice biometric features. The classified acoustic scenario may be used in a robotics application or voice assistant device desired speech enhancement or interference signal cancellation. Specifically, the classification of the acoustic scenarios can be used to adapt a beamformer, e.g., step size adjustment. The hyperset of features may also include visual biometric features extracted from one or more cameras viewing the acoustic sources. The spatial and biometric features may be separately extracted, clustered, classified and their separate classifications fused, e.g., using frame synchronization.

A communication assembly for avoiding interferences due to oxygen flow noise, including a) a breathing mask having a body having a face shell having a breathing cavity and a regulator delivering a breathing gas, b) a microphone configured to capture a sound signal in the breathing cavity, c) a test button for supplying the breathing cavity with breathing gas, d) an attenuation device, e) a sound monitoring system, f) a controller configured to the attenuation device operate in an active mode when a flow noise though the breathing cavity during inhalation by the user is detected, and an inactive mode when a vocal sound or a flow noise in the breathing cavity in a stowed configuration is detected, and g) a transmitter for transmitting an output signal.

Systems and methods are disclosed for providing voice and noise activity detection with audio automixers that can reject errant non-voice or non-human noises while maximizing signal-to-noise ratio and minimizing audio latency.

The present application relates to a lexicon learning-based heliumspeech unscrambling method in saturation diving. In a system including divers, a correction network, and an unscrambling network, a common working language lexicon for saturation diving operation is established and is read by the divers respectively in different environments, to generate supervision signals and vector signals of the correction network, and the correction network learns heliumspeeches of the different divers at different diving depths to obtain a correction network parameter, and corrects a heliumspeech of a diver to obtain a corrected speech; and the unscrambling network learns the corrected speech and completes unscrambling of the heliumspeech.

A system and method for selectively enhancing an audio signal to make sounds, particularly speech sounds, more distinguishable. The system and method are designed to divide an input auditory signal into a plurality of spectral channels having associated unenhanced signals and perform enhancement processing on a first subset of the spectral channels and not perform enhancement processing on a second subset of the spectral channels. The enhancement processing is performed by determining an output gain for at least the first subset of spectral channels based on a time-varying history of energy of the unenhanced signals associated with each channel in the first subset of the spectral channels and applying the output gain for each of the first subset of the spectral channels to the unenhanced signals to form enhanced signals associated with each of the first subset of the spectral channels. The system and method are then designed to combine the plurality of enhanced signals associated with each of the first subset of the spectral channels and the unenhanced signals associated with each of the second subset of the spectral channels to form a selectively enhanced output auditory signal.