Processing voice
AssigneeBeijing Xiaomi Mobile Software Co., Ltd.
InventorsZhao WANG, Lingsong ZHOU
Life of this patent
Estimating the term…
Abstract
A method and an apparatus for processing voice are provided. The method is applied to a decision-making device in communication with a distributed microphone array and the distributed microphone array comprises a plurality of sub-arrays. The method comprises: obtaining, for each sub-array, an awakening voice signal received by each microphone of the sub-array; determining, for each sub-array, a frequency domain signal corresponding to each awakening voice signal of the sub-array, and a first cross-correlation function between every two frequency domain signals; determining an awakened sub-array based on each first cross-correlation function for each sub-array.
Claims18
A method of processing voice, the method being applied to a decision-making device in communication with a distributed microphone array, the distributed microphone array comprising a plurality of sub-arrays, and the method comprising:
- obtaining, for each sub-array, an awakening voice signal received by each microphone of each sub-array;
- determining, for each sub-array, a frequency domain signal corresponding to each awakening voice signal of each sub-array, and a first cross-correlation function between every two frequency domain signals;
- and
- determining an awakened sub-array to be awakened by a corresponding awakening voice signal in the plurality of sub-arrays based on each first cross-correlation function for each sub-array.
An apparatus for processing voice, the apparatus being applied to a decision-making device in communication with a distributed microphone array, the distributed microphone array comprising a plurality of sub-arrays, and the apparatus comprising:
- a processor, and
- a storage medium storing instructions executable by the processor;
- wherein, when the processor executes the instructions, the processor is caused to:
- obtain, for each sub-array, an awakening voice signal received by each microphone of the sub-array;
- determine, for each sub-array, a frequency domain signal corresponding to each awakening voice signal of the sub-array, and a first cross-correlation function between every two frequency domain signals;
- and
- determine an awakened sub-array by a corresponding awakening voice signal in the sub-arrays based on each first cross-correlation function of each sub-array.
A system for processing voice, the system comprising:
- a decision-making device in communication with a distributed microphone array, the distributed microphone array comprising a plurality of sub-arrays, wherein the system is configured to
- obtain a digital voice signal from each microphone of each sub-array when each sub-array receives an awakening voice signal;
- determine a frequency domain signal corresponding to each digital voice signal of each sub-array, and a first cross-correlation function between every two frequency domain signals;
- and
- select an awakened sub-array corresponding to the awakening voice signal in the plurality of sub-arrays based on each first cross-correlation function for each sub-array.
Dependencies are inferred from the claim text.