SPEECH CONTROL METHOD AND DEVICE, ELECTRONIC DEVICE, AND READABLE STORAGE MEDIUM

1 . A speech control method, applied to an electronic device, and comprising:

controlling the electronic device to operate in a first operating state, and acquiring an audio clip according to a wake word in the first operating state;

obtaining a first control intent corresponding to the audio clip;

performing a first control instruction matching the first control intent, and controlling the electronic device to switch from the first operating state to a second operating state;

continuously acquiring audio within a preset time period to obtain an audio stream, and obtaining a second control intent corresponding to the audio stream; and

performing a second control instruction matching the second control intent.

2 . The speech control method according to claim 1 , wherein continuously acquiring the audio within the preset time period to obtain the audio stream, and obtaining the second control intent corresponding to the audio stream comprises:

reading configuration information of the second operating state to obtain the preset time period, wherein the preset time period is set in response to a user operation;

continuously acquiring the audio within the preset time period to obtain the audio stream, and obtaining the second control intent corresponding to the audio stream; and

controlling the electronic device to switch from the second operating state to the first operating state when the second control intent is not obtained within the preset time period.

3 . The speech control method according to claim 2 , wherein obtaining the second control intent corresponding to the audio stream comprises:

performing speech recognition on the audio stream to obtain an information stream;

obtaining at least one candidate intent based on the information stream; and

selecting the second control intent matching a current scene from the at least one candidate intent.

4 . The speech control method according to claim 3 , after obtaining the at least one candidate intent based on the information stream, further comprising:

controlling the electronic device to reject responding to the candidate intent that does not match the current scene.

5 . The speech control method according to claim 1 , before controlling the electronic device to switch from the first operating state to the second operating state, further comprising:

determining that the first control intent matches the current scene.

6 . A speech control device, applied to an electronic device, and comprising:

at least one processor; and

a memory, configured to store executable instructions, and coupled to the at least one processor;

wherein when the instructions are executed by the at least one processor, the at least one processor is caused to:

control the electronic device to operate in a first operating state, and acquire an audio clip according to a wake word;

obtain a first control intent corresponding to the audio clip;

perform a first control instruction matching the first control intent, control the electronic device to switch from the first operating state to a second operating state, continuously acquire audio within a preset time period to obtain an audio stream, and obtain a second control intent corresponding to the audio stream; and

perform a second control instruction matching the second control intent.

7 . The speech control device according to claim 6 , wherein the at least one processor is configured to:

read configuration information of the second operating state to obtain the preset time period, wherein the preset time period is set in response to a user operation;

continuously acquire the audio within the preset time period to obtain the audio stream, and obtain the second control intent corresponding to the audio stream; and

control the electronic device to switch from the second operating state to the first operating state when the second control intent is not obtained within the preset time period.

8 . The speech control device according to claim 7 , wherein the at least one processor is further configured to:

perform speech recognition on the audio stream to obtain an information stream;

obtain at least one candidate intent based on the information stream; and

select the second control intent matching a current scene from the at least one candidate intent.

9 . The speech control device according to claim 8 , wherein the at least one processor is further configured to:

control the electronic device to reject responding to the candidate intent that does not match the current scene.

10 . The speech control device according to claim 6 , wherein the at least one processor is configured to:

determine that the first control intent matches the current scene.

11 . A non-transitory computer readable storage medium having computer instructions stored thereon, wherein when the computer instructions are executed by a processor, the processor is caused execute a speech control method, wherein the speech control method is applied to an electronic device, and comprises:

controlling the electronic device to operate in a first operating state, and acquiring an audio clip according to a wake word in the first operating state;

obtaining a first control intent corresponding to the audio clip;

performing a first control instruction matching the first control intent, and controlling the electronic device to switch from the first operating state to a second operating state;

continuously acquiring audio within a preset time period to obtain an audio stream, and obtaining a second control intent corresponding to the audio stream; and

performing a second control instruction matching the second control intent.

12 . The non-transitory computer readable storage medium according to claim 11 , wherein continuously acquiring the audio within the preset time period to obtain the audio stream, and obtaining the second control intent corresponding to the audio stream comprises:

reading configuration information of the second operating state to obtain the preset time period, wherein the preset time period is set in response to a user operation;

continuously acquiring the audio within the preset time period to obtain the audio stream, and obtaining the second control intent corresponding to the audio stream; and

controlling the electronic device to switch from the second operating state to the first operating state when the second control intent is not obtained within the preset time period.

13 . The non-transitory computer readable storage medium according to claim 12 , wherein obtaining the second control intent corresponding to the audio stream comprises:

performing speech recognition on the audio stream to obtain an information stream;

obtaining at least one candidate intent based on the information stream; and

selecting the second control intent matching a current scene from the at least one candidate intent.

14 . The non-transitory computer readable storage medium according to claim 13 , after obtaining the at least one candidate intent based on the information stream, further comprising:

controlling the electronic device to reject responding to the candidate intent that does not match the current scene.

15 . The non-transitory computer readable storage medium according to claim 11 , before controlling the electronic device to switch from the first operating state to the second operating state, further comprising:

determining that the first control intent matches the current scene.