Huawei Technologies Co., Limited

Tencent Technology (shenzhen) Company Limited

Tencent Technology Company Limited

Kaiyu Jiang

Hui Jin

Xiaoguang Wu

Weiwei Li

Liwen Tan

Dan Su

Jimeng Zheng

Lianwu Chen

Meng Yu

Rilin Chen

Zhiyi Duan

Yunfei Xu

Lisheng Tian

This application discloses a multi-sound area-based speech detection method and related apparatus, and a storage medium, which is applied to the field of artificial intelligence. The method includes: obtaining sound area information corresponding to N sound areas including multiple users speaking simultaneously; generating a control signal corresponding to each target detection sound area according to user information corresponding to the target detection sound area; processing multi-user speech input signals by using the control signals, to obtain a speech output signal corresponding to each target detection sound area; generating a speech detection result of the target detection sound area according to the speech output signal corresponding to the target detection sound area; and selecting, among the multiple users, a main speaker based on the user information, the speech output signals and speech detection results of multiple users in the N sound areas.

Multi-register-based speech detection method and related apparatus, and storage medium

An electronic device obtains audio signals collected by different microphones in a microphone array. The device filters the audio signals using a first filter to obtain a first target beam. The first filter is configured to suppress an interference speech in the audio signals and enhance a target speech in the audio signals. The device filters the audio signals using a second filter to obtain a first interference beam. The second filter is configured to suppress the target speech and enhance the interference speech. The device a second interference beam of the first interference beam using a third filter. The device determines a difference between the first target beam and the second interference beam as a first audio processing output. The device adaptively updates at least one of the second filter and the third filter, and updates the first filter according to the updated second filter and/or third filter.

Audio signal processing method, apparatus and device, and storage medium

A call prompt methods and terminals. One example method includes displaying a first interface on a display screen of a first terminal, showing that the first terminal is in a call with a second terminal via a CDMA communication network, while the first terminal is in the call with the second terminal, displaying a second interface on the display screen that prompts that a third terminal is initiating a call to the first terminal. Outputting a sound that includes a prompt tone and a call voice between the first terminal and the second terminal, the prompt tone that the third terminal is initiating a call to the first terminal, and when the call initiated by the third terminal is rejected by the first terminal's user, continuing output the call voice between the first terminal and the second terminal, and stopping output the prompt tone.

Call prompt method

Methods, systems, and apparatus for call prompting when a call initiated by a terminal is unconnected during a call between two other terminals. In one example method, a first interface, indicating that the first terminal is in a call with a second terminal, is displayed on the first terminal. If a third terminal initiates a call to the first terminal, a second interface, indicating the call initiated by the third terminal, is displayed on the first terminal, and a sound, which includes a call voice and a prompt tone of the initiated call, is output. If the third terminal's initiated call is rejected, the call voice is output on the first terminal, and the prompt tone stops being output. If the third terminal stops initiating the call, the first interface is displayed on the first terminal, and the call voice between the first terminal and the terminal continues being output.

A method and an apparatus for controlling a multi-microphone noise-canceling sound pickup range of a terminal, and belongs to the field of terminal technologies, where the method includes transmitting a first non-voice signal, receiving a second non-voice signal that is obtained after the first non-voice signal is reflected by a reflecting object, determining, according to the first non-voice signal and the second non-voice signal, whether a posture with which a user holds a terminal during a call is a normal posture, and adjusting a multi-microphone noise-canceling sound pickup range of the terminal when the posture with which the user holds the terminal during the call is not a normal posture. Hence, accuracy of adjusting a multi-microphone noise-canceling sound pickup range of a terminal can be improved. The apparatus includes a transmission module, a receiving module, a first determining module, and an adjustment module.

Method and apparatus for controlling multi-microphone noise-canceling sound pickup range of terminal

Growing community of inventors

Shenzhen, China

Kaiyu Jiang