The present application discloses a method for determining a delay between signals, an apparatus, a device and a storage medium, and relates to voice technology. In the method, apparatus, device, and storage medium provided by the present disclosure, by performing down-sampling processing on the signals, the amount of calculation for determining the delay can be reduced, thereby improving the determination efficiency. Moreover, signal segments including alignment positions of the two signals can be estimated in the signal through a currently determined delay, and then the processing can be performed again on the signal segments. In this way, a range for determination can be gradually reduced, that is, an accurate delay can be obtained by just processing shorter signals, which not only ensures the accuracy of the determination, but also reduces the amount of data processing.

A noise-cancelling keyboard includes a frame; keys on the frame; a microphone on an underside of the frame and configured to convert noise generated by pressing the keys into an electrical noise signal; a noise reduction device on the underside of the frame and electrically connected to the microphone, the noise reduction device being configured to generate an inverse noise signal combining with the electrical noise signal to form a new sound wave with the noise being substantially canceled; a loudspeaker on the underside of the frame and electrically connected to the noise reduction device, the loudspeaker being configured to convert an electrical audio signal representing the new sound wave into a corresponding sound; and a switch on a top of the frame and electrically interconnected to the noise reduction device and a power supply, the switch being configured to activate or deactivate the noise reduction device.

Personal audio systems and methods are disclosed. A personal audio system includes a voice activity detector to determine whether or not an ambient audio stream contains voice activity, a pitch estimator to determine a frequency of a fundamental component of an annoyance noise contained in the ambient audio stream, and a filter bank to attenuate the fundamental component and at least one harmonic component of the annoyance noise to generate a personal audio stream. The filter bank implements a first filter function when the ambient audio stream does not contain voice activity, or a second filter function when the ambient audio stream contains voice activity.

According to an aspect, a WPE-based dereverberation apparatus using virtual acoustic channel expansion based on a deep neural network includes a signal reception unit for receiving as input a first speech signal through a single channel microphone, a signal generation unit for generating a second speech signal by applying a virtual acoustic channel expansion algorithm based on a deep neural network to the first speech signal and a dereverberation unit for removing reverberation of the first speech signal and generating a dereverberated signal from which the reverberation has been removed by applying a dual-channel weighted prediction error (WPE) algorithm based on a deep neural network to the first speech signal and the second speech signal.

A method, computer program, and computer system is provided for an all-deep-learning based AEC system by recurrent neural networks. The model consists of two stages, echo estimation stage and echo suppression stage, respectively. Two different schemes for echo estimation are presented herein: linear echo estimation by multi-tap filtering on far-end reference signal and non-linear echo estimation by single-tap masking on microphone signal. A microphone signal waveform and a far-end reference signal waveform are received. An echo signal waveform is estimated based on the microphone signal waveform and a far-end reference signal waveform. A near-end speech signal waveform is output based on subtracting the estimated echo signal waveform from the microphone signal waveform, and echoes are suppressed within the near-end speech signal waveform.

A keyword detection method includes: obtaining an enhanced speech signal of a to-be-detected speech signal, the enhanced speech signal corresponding to a target speech speed; performing speed adjustment on the enhanced speech signal to obtain a first speed-adjusted speech signal having a first speech speed, the first speech speed being different from the target speech speed; obtaining a first speech feature signal according to the first speed-adjusted speech signal; obtaining a detection result according to a first keyword detection result corresponding to the first speech feature signal, the detection result indicating whether a target keyword exists in the to-be-detected speech signal; and performing an operation corresponding to the target keyword in response to determining that the target keyword exists according to the detection result.

Provided is an audio signal processing device that receives an operation input made by a user and performs noise removal processing for removing noise from a collected audio signal collected by a microphone, and that changes content of the noise removal processing according to content of the operation input.

Provided are apparatuses and associated methods for video communications and related features. In one embodiment, a big-screen video communications apparatus is provided that includes a projector and speaker for projecting received images and sounds and includes a camera and microphone for capturing images and sounds for transmission.

A computer implemented method, system and computer program product are provided that implement a neural network (NN) audio filter. The method, system and computer program product obtain an electronic audio signal comprising a speech impaired message and apply the audio signal to the NN audio filter to modify the speech impaired message to form an unimpaired message. The method, system and computer program product output the unimpaired message.

A system comprises an ear-worn electronic device configured to be worn by a wearer. The ear-worn electronic device comprises a processor and memory coupled to the processor. The memory is configured to store an annoying sound dictionary representative of a plurality of annoying sounds pre-identified by the wearer. A microphone is coupled to the processor and configured to monitor an acoustic environment of the wearer. A speaker or a receiver is coupled to the processor. The processor is configured to identify different background noises present in the acoustic environment, determine which of the background noises correspond to one or more of the plurality of annoying sounds, and attenuate the one or more annoying sounds in an output signal provided to the speaker or receiver.