Method, apparatus, system and storage medium for implementing a far-field speech function
View Patent ↗The present disclosure provides a method, apparatus for implementing a far-field speech function, system and a storage medium, wherein the method comprises: a speech detecting unit located on a smart device performing speech signal detection in real time; upon detecting an awakening word, the speech detecting unit awakening an algorithm unit located on the smart device and being in a standby state; the speech detecting unit transmitting the obtained speech signal to the algorithm unit so that the algorithm unit performs arithmetic processing for the speech signal in a predetermined manner, and sends a processed speech signal to a control system of the smart device, to complete a corresponding control operation. The solution of the present disclosure can be applied to save energy consumption and improve the acoustic effect, break away from the constraints of the remote controller and facilitate the user's operation.
1. A method for implementing a far-field speech function for a smart TV, wherein the method comprises:
a speech detecting unit including a microphone array located on the smart TV performing speech signal detection in real time; wherein the microphone array comprises a plurality of microphones each having an awakening function;
upon detecting an awakening word by a microphone of the microphone array, the microphone awakening an algorithm unit located on the smart TV and being in a standby state; wherein the plurality of microphones are connected to the algorithm unit with a distributed wired AND gate architecture;
the speech detecting unit transmitting the obtained speech signal to the algorithm unit so that the algorithm unit performs arithmetic processing for the speech signal in a predetermined manner including echo removal, reverberation removal and sound source positioning, and sends a processed speech signal to a control system of the smart TV, to complete a corresponding control operation.
2. The method according to claim 1 , wherein
the microphone of the speech detecting unit awakening an algorithm unit in a standby state upon detecting an awakening word comprises:
awakening the algorithm unit in the standby state when one or more microphones in the microphone array detects the awakening word.
3. The method according to claim 1 , wherein
the speech detecting unit transmitting the obtained speech signal to the algorithm unit comprises:
the speech detecting unit transparently transmits the obtained speech signal to the algorithm unit.
4. A method for implementing a far-field speech function for a smart TV, wherein the method comprises:
an algorithm unit located on the smart TV obtaining an awakening signal sent from a microphone of a microphone array comprising a plurality of microphones each having an awakening function included in a speech detecting unit located on the smart TV, converting from a standby state into an activated state, the awakening signal being sent to the algorithm unit when the speech detecting unit performs speech signal detection in real time and detects an awakening word; wherein the plurality of microphones are connected to the algorithm unit with a distributed wired AND gate architecture;
the algorithm unit obtaining a speech signal sent from the speech detecting unit and obtained by the speech detecting unit;
the algorithm unit performing arithmetic processing for the speech signal in a predetermined manner including echo removal, reverberation removal and sound source positioning, and sends a processed speech signal to a control system of the smart TV, to complete a corresponding control operation.
5. The method according to claim 4 , wherein
the algorithm unit obtaining an awakening signal sent from the speech detecting unit, and converting from a standby state into an activated state comprises:
converting from a standby state to an activated state, upon obtaining the awakening signal sent from one or more microphones in the microphone array after detecting the awakening word.
6. A speech detecting unit of a smart TV, comprising:
a memory;
a microphone array comprising a plurality of microphones each having an awakening function;
a processor; and
a computer program which is stored on the memory and runs on the processor,
wherein the processor, upon executing the program, implements a method for implementing a far-field speech function, wherein the method comprises:
performing speech signal detection in real time with the microphone array;
upon detecting an awakening word by a microphone of the microphone array, the microphone awakening an algorithm unit in a standby state; wherein the plurality of microphones are connected to the algorithm unit with a distributed wired AND gate architecture;
transmitting the obtained speech signal to the algorithm unit so that the algorithm unit performs arithmetic processing for the speech signal in a predetermined manner including echo removal, reverberation removal and sound source positioning, and sends a processed speech signal to a control system of the smart TV, to complete a corresponding control operation.
7. The speech detecting unit according to claim 6 , wherein the awakening an algorithm unit in a standby state upon detecting an awakening word comprises:
awakening the algorithm unit in the standby state when one or more microphones in the microphone array detects the awakening word.
8. The speech detecting unit according to claim 6 , wherein the speech detecting unit transmitting the obtained speech signal to the algorithm unit comprises:
the speech detecting unit transparently transmits the obtained speech signal to the algorithm unit.
9. An algorithm unit of a smart TV, comprising:
a memory;
a processor; and
a computer program which is stored on the memory and runs on the processor,
wherein the processor, upon executing the program, implements a method for implementing a far-field speech function, wherein the method comprises:
obtaining an awakening signal sent from a microphone of a microphone array comprising a plurality of microphones each having an awakening function included in a speech detecting unit, converting from a standby state into an activated state, the awakening signal being sent to the algorithm unit when the speech detecting unit performs speech signal detection in real time and detects an awakening word; wherein the plurality of microphones are connected to the algorithm unit with a distributed wired AND gate architecture;
obtaining a speech signal sent from the speech detecting unit and obtained by the speech detecting unit;
performing arithmetic processing for the speech signal in a predetermined manner including echo removal, reverberation removal and sound source positioning, and sends a processed speech signal to a control system of the smart TV, to complete a corresponding control operation.
10. The algorithm unit according to claim 9 , wherein
the algorithm unit obtaining an awakening signal sent from the speech detecting unit, and converting from a standby state into an activated state comprises:
converting from a standby state to an activated state, upon obtaining the awakening signal sent from one or more microphones in the microphone array after detecting the awakening word.
11. A system for implementing a far-field speech function for a smart TV, wherein the system comprises:
a speech detecting unit comprising a first memory, a microphone array comprising a plurality of microphones each having an awakening function, a first processor and a first computer program which is stored on the first memory and runs on the first processor, wherein the first processor, upon executing the first program, implements a first method for implementing a far-field speech function, wherein the first method comprises:
performing speech signal detection in real time;
upon detecting an awakening word by a microphone of the microphone array, the microphone awakening an algorithm unit in a standby state; wherein the plurality of microphones are connected to the algorithm unit with a distributed wired AND gate architecture;
transmitting the obtained speech signal to the algorithm unit so that the algorithm unit performs arithmetic processing for the speech signal in a predetermined manner including echo removal, reverberation removal and sound source positioning, and sends a processed speech signal to a control system of the smart TV, to complete a corresponding control operation; and
the algorithm unit comprising a second memory, a second processor and a second computer program which is stored on the second memory and runs on the second processor, wherein the second processor, upon executing the second program, implements a second method for implementing a far-field speech function, wherein the second method comprises:
obtaining an awakening signal sent from the microphone of the speech detecting unit, converting from the standby state into the activated state, the awakening signal being sent to the algorithm unit when the speech detecting unit performs speech signal detection in real time and detects the awakening word;
obtaining the speech signal sent from the speech detecting unit and obtained by the speech detecting unit;
performing arithmetic processing for the speech signal in a predetermined manner, and sends the processed speech signal to the control system of the smart TV, to complete the corresponding control operation.
12. A non-transitory computer-readable storage medium on which a computer program is stored, wherein the program, when executed by a processor, implements a method for implementing a far-field speech function for a smart TV, wherein the method comprises:
a speech detecting unit including a microphone array on the smart TV performing speech signal detection in real time; wherein the microphone array comprises a plurality of microphones each having an awakening function;
upon detecting an awakening word by a microphone of the microphone array, the microphone awakening an algorithm unit located on the smart TV and being in a standby state; wherein the plurality of microphones are connected to the algorithm unit with a distributed wired AND gate architecture;
the speech detecting unit transmitting the obtained speech signal to the algorithm unit so that the algorithm unit performs arithmetic processing for the speech signal in a predetermined manner including echo removal, reverberation removal and sound source positioning, and sends a processed speech signal to a control system of the smart TV, to complete a corresponding control operation.
13. A non-transitory computer-readable storage medium on which a computer program is stored, wherein the program, when executed by a processor, implements a method for implementing a far-field speech function of a smart TV, wherein the method comprises:
an algorithm unit located on the smart TV obtaining an awakening signal sent from a microphone of a microphone array comprising a plurality of microphones each having an awakening function included in a speech detecting unit located on the smart TV, converting from a standby state into an activated state, the awakening signal being sent to the algorithm unit when the speech detecting unit performs speech signal detection in real time and detects an awakening word; wherein the plurality of microphones are connected to the algorithm unit with a distributed wired AND gate architecture;
the algorithm unit obtaining a speech signal sent from the speech detecting unit and obtained by the speech detecting unit;
the algorithm unit performing arithmetic processing for the speech signal in a predetermined manner including echo removal, reverberation removal and sound source positioning, and sends a processed speech signal to a control system of the smart TV, to complete a corresponding control operation.