Disclosed is a method for managing acoustic feedback in real-time audio communications in a communications system, the method comprising determining, by means of a detection module, whether a first communication device is in loudspeaker mode, whether the first communication device is in real-time audio communications with a second communication, and whether the first communication device and the second communication device are in a same acoustic space. Upon determining that this is the case a request signal for requesting one or more measures against acoustic feedback is provided to a mitigation module. Further disclosed are a device and a system configured to perform the method, a non-transitory computer-readable medium, an encoder and a decoder.

Systems and methods for detecting volume level changes in communications are described herein. In some embodiments, a system comprises a computer system. The computer system comprises at least one processor and a memory coupled to the at least one processor. The memory stores program instructions that are executable by the at least one processor to cause the computer system to perform tasks. The tasks include recording a communication that comprises audio, and analyzing the audio of the communication. The analysis of the audio is operable to detect a change in a volume level of the audio that indicates an occurrence of a potential event of interest. The tasks also include creating and storing an information record corresponding to the communication in a second database. The information record includes an indication of the detected change in the volume level.

A device, system and method for adjusting volume on talkgroups is provided. A controller determines that a given user is communicating in a talkgroup that includes a plurality of participants different from the given user, the controller having access to a memory storing historical biometric data indicative of stress for the given user. When a comparison of current biometric data of the given user with the historical biometric data indicates that the given user is in a stressed state: differentially increasing volume, in the talkgroup, of one participant, of the plurality of participants, relative to other participants of the plurality of participants, based on context data of one or more of the talkgroup and the plurality of participants.

A dynamic optical microphone system may include an acoustic microphone that receives an audio signal and a laser microphone that transmits a laser beam and receives optical feedback from a human struck by the laser beam. The system may include a depth sensor that determines a distance to the human and a camera that tracks human faces. A processor may be communicatively coupled to the acoustic microphone, laser microphone, depth sensor, camera, and a memory storing computer executable instructions. The processor may determine a direction to a human, direct the laser beam at a voice box of the human, determine a distance to the human using the depth sensor, adjust an intensity of the laser beam based on the distance, receive optical feedback and isolate a voice signal through the optical feedback from background noise in the audio signal.

A dynamic optical microphone system may include an acoustic microphone that receives an audio signal and a laser microphone that transmits a laser beam and receives optical feedback from a human struck by the laser beam. The system may include a depth sensor that determines a distance to the human and a camera that tracks human faces. A processor may be communicatively coupled to the acoustic microphone, laser microphone, depth sensor, camera, and a memory storing computer executable instructions. The processor may determine a direction to a human, direct the laser beam at a voice box of the human, determine a distance to the human using the depth sensor, adjust an intensity of the laser beam based on the distance, receive optical feedback and isolate a voice signal through the optical feedback from background noise in the audio signal.

A method includes receiving a first instance of raw audio data corresponding to a voice-based command and receiving a second instance of the raw audio data corresponding to an utterance of audible contents for an audio-based communication spoken by a user. When a voice filtering recognition routine determines to activate voice filtering for at least the voice of the user, the method also includes obtaining a respective speaker embedding of the user and processing, using the respective speaker embedding, the second instance of the raw audio data to generate enhanced audio data for the audio-based communication that isolates the utterance of the audible contents spoken by the user and excludes at least a portion of the one or more additional sounds that are not spoken by the user The method also includes executing.

A two-way conversation assisting device includes a first microphone that enters a first voice, a first loudspeaker that outputs the first voice, a second microphone that enters a second voice, a second loudspeaker that outputs the second voice, and a first echo and crosstalk canceller. The first echo and crosstalk canceller estimates and calculates, using an input signal into the second loudspeaker, a first interference signal indicative of degrees of a first echo caused when the second voice output from the second loudspeaker enters into the first microphone and first crosstalk caused when the second voice enters into the first microphone, and removes the calculated first interference signal from an output signal of the first microphone.

A two-way conversation assisting device includes a first microphone that enters a first voice, a first loudspeaker that outputs the first voice, a second microphone that enters a second voice, a second loudspeaker that outputs the second voice, and a first echo and crosstalk canceller. The first echo and crosstalk canceller estimates and calculates, using an input signal into the second loudspeaker, a first interference signal indicative of degrees of a first echo caused when the second voice output from the second loudspeaker enters into the first microphone and first crosstalk caused when the second voice enters into the first microphone, and removes the calculated first interference signal from an output signal of the first microphone.

A system for enhancing tonal quality for ringback signals in a telecommunications network by adjusting audio processing during an alerting interval of a telecommunications session (e.g. during a telephone call). The system may be embodied in a telecommunications switching device and include a ringback manager process that provides the ability to adjust audio processing (e.g., by signaling to in-path equipment) which enhances the tonal quality of the ringback signal. As an example, a telephone system (e.g. equipment associated with establishment and operation of telephone communications sessions) can disable or attenuate operation of voice quality enhancement processing such as echo cancellation, noise reduction, adaptive level control, and the like, during the ringback or alerting interval or period of a telephone call so that the ringback tone provided to the calling party is not distorted by such processing.

Systems and processes for language processing with radio devices are provided. For example, radio broadcast information is received at a first electronic device, and a vocabulary is modified based on the received radio broadcast information. A speech input is received from a user of the first electronic device. A user intent of the speech input is obtained based on the modified vocabulary. A request is transmitted, based on the user intent, to a second electronic device.