Zte Corporation

Shenzhen Horizon Robotics Technology Co., Ltd.

Changbao Zhu

Hao Yuan

Dongping Jiang

Embodiments of the present disclosure disclose a speech interaction method and apparatus. The method includes: acquiring videos shot by a camera device in a target space and at least one channel of audio acquired by at least one audio acquisition device; determining to-be-recognized audio that respectively corresponds to each of the sound areas in the target space based on the at least one channel of audio; determining a target sound area from the target space based on the video and at least one channel of to-be-recognized audio; performing speech recognition on the at least one channel of to-be-recognized audio to obtain a recognition result; and controlling a speech interaction-targeting device in the target sound area for speech interaction in a preset mode according to the recognition result. The speech interaction method and apparatus in the embodiments of the present disclosure may detect a target object by the method of integration of an image and speech, a speech control mode corresponding to the target object is automatically entered according to a detection result, making objects on the speech recognition and corresponding speech control for various types more targeted, and helping to avoid misoperation caused by recognized sound of the target object during speech control.

Speech interaction method and apparatus, computer readable storage medium and electronic device

A method for acquiring the number of modified frames for active sound, and a method and apparatus for voice activity detection are disclosed. Firstly, a first voice activity detection decision result and a second voice activity detection decision result are obtained (), the number of hangover frames for active sound is obtained (), and the number of background noise updates is obtained (), and then the number of modified frames for active sound is calculated according to the first voice activity detection decision result, the number of background noise updates and the number of hangover frames for active sound (), and finally, a voice activity detection decision result of a current frame is calculated according to the number of modified frames for active sound and the second voice activity detection decision result ().

Voice activity modification frame acquiring method, and voice activity detection method and apparatus

Provided are a Voice Activity Detection (VAD) method and apparatus. The method includes that: at least one first class feature in a first feature category, at least one second class feature in a second feature category and at least two existing VAD judgment results are acquired, the first class feature and the second class feature are features used for VAD detection (S); and VAD is carried out according to the first class feature, the second class feature and the at least two existing VAD judgment results, to obtain a combined VAD judgment result (S).

Voice activity detection method and apparatus

Disclosed are a voice activity detection method and device, wherein the method includes: obtaining a combined VAD judgment result according to the number of continuous active frames, an average total SNR of all sub-bands, a tonal signal flag, and at least two existing VAD judgment results (). The method and device are suitable for voice service, solve the problem of inaccurate VAD detection and realize highly accurate VAD judgment.

Voice activity detection method and device

The present document relates to a voice activity detection (VAD) method and methods used for voice activity detection and apparatus thereof, the VAD method includes: obtaining sub-band signals and spectrum amplitudes of a current frame; computing values of a energy feature and a spectral centroid feature of the current frame according to the sub-band signals; computing a signal to noise ratio parameter of the current frame according to a background noise energy estimated from a previous frame, an energy of SNR sub-bands and a energy feature of the current frame; computing a VAD decision result according to a tonality signal flag, a signal to noise ratio parameter, a spectral centroid feature, and a frame energy feature. The methods and apparatus of the present document can improve the accuracy of non-stationary noise (such as office noise) and music detection.

Growing community of inventors

Shenzhen, China

Changbao Zhu