A voice signal processing method and an electronic device

Abstract

The application provides a voice signal processing method and an electronic device. The method is applied to a controller of the electronic device. The controller acquires a voice signal collected by a collector. If a signal capacity of the voice signal is greater than a sending threshold, the voice signal is sent to a server, so that the server performs voice recognition processing on the voice signal. If the signal capacity of the voice signal is not greater than the sending threshold, the voice signal is not sent to the server. The technical scheme of the application acquires the voice signal collected by the sound collector, and does not directly send the voice signal to the server. Instead, the relationship between the signal capacity of the voice signal and the sending threshold is determined. Only the voice signal with the signal capacity greater than the sending threshold is sent to the server. In this way, the super-short voice instruction is avoided from being sent to the server, the user experience is improved, the server computing pressure is reduced, and the waste of server resources is reduced.

Claims

1. An electronic device, characterized in that, include: The sound acquisition device is configured to collect user voice signals; The controller is configured as follows: Acquire the voice signal collected by the sound acquisition device; When the signal capacity of the voice signal is greater than the transmission threshold, the voice signal is sent to the server so that the server can perform voice recognition processing on the voice signal. When the signal capacity of the voice signal is less than or equal to the transmission threshold, the voice signal is saved locally and not sent to the server. When the signal capacity of the voice signal acquired N times consecutively is less than or equal to the transmission threshold, the voice signals acquired N times consecutively are spliced ​​together and the spliced ​​voice signal is sent to the server so that the server can perform voice recognition processing on the spliced ​​voice signal, where N is a positive integer greater than 1. If the recognition result is received from the server, and the recognition result is a failure, the voice signal saved locally for N consecutive times will be cleared.

2. The electronic device according to claim 1, characterized in that, The electronic device further includes a timer configured to trigger timing when the acquisition of the voice signal begins, wherein the signal capacity is the timing duration, the transmission threshold is the duration threshold, and the controller is configured to: Simultaneously, the voice signal is acquired from the sound acquisition device, and a timing signal is acquired from the timer. When the timing duration of the timing signal is less than or equal to the duration threshold, a first voice signal is acquired, and the acquired first voice signal is saved locally, wherein the first voice signal is the signal acquired from the sound collector from the start of timing to the duration threshold time. When the timing duration of the timing signal exceeds the duration threshold, a first voice signal and a second voice signal are acquired, and the first voice signal and the second voice signal are sent to the server. The second voice signal is the signal acquired from the sound collector after the timing duration exceeds the duration threshold.

3. The electronic device according to claim 2, characterized in that, The controller is also configured to: Upon receiving a control command input by the user via pressing the voice button, the system controls the sound acquisition device to start acquiring voice signals and simultaneously controls the timer to start timing. Upon receiving a control command input by the user via releasing the voice key, the system controls the sound acquisition device to stop acquiring voice signals and simultaneously controls the timer to stop timing.

4. The electronic device according to claim 1, characterized in that, The electronic device further includes a meter configured to trigger metering when the acquisition of the voice signal begins, wherein the signal capacity is the amount of voice data, the transmission threshold is a data volume threshold, and the controller is configured to: Simultaneously, the voice signal is acquired from the sound acquisition device, and the metering signal is acquired from the meter. When the amount of voice data in the metering signal is less than or equal to the data amount threshold, a third voice signal is acquired, and the acquired third voice signal is saved locally. The third voice signal is the signal acquired from the sound acquisition device from the start of metering to the time within the data amount threshold. When the amount of voice data in the metering signal exceeds the data amount threshold, a third voice signal and a fourth voice signal are acquired, and the third voice signal and the fourth voice signal are sent to the server. The fourth voice signal is the signal acquired from the sound collector after the amount of voice data exceeds the data amount threshold.

5. The electronic device according to claim 1, characterized in that, The controller also includes a display, and the controller is further configured to: When the signal capacity of the voice signal is less than or equal to the transmission threshold, the display is controlled to show a prompt message, which is used to prompt the user that the currently input voice signal is invalid.

6. The electronic device according to claim 1, characterized in that, The controller also includes a prompter, and the controller is further configured to: When the signal capacity of the voice signal is greater than the transmission threshold, the prompter is controlled to make a first response, which is used to prompt the user that the currently input voice signal is a valid signal; When the signal capacity of the voice signal is less than or equal to the transmission threshold, the prompter is controlled to make a second response. The second response is used to prompt the user that the currently input voice signal is invalid. The second response is different from the first response.

7. The electronic device according to claim 6, characterized in that, The controller is also configured to: When no voice signal is acquired from the sound acquisition device, the prompter is controlled to make a third response, which is used to prompt the user that no voice signal has been input. The third response is different from the first response and the second response.

8. A speech signal processing method, characterized in that, The method includes: Acquire the voice signal collected by the sound acquisition device; When the signal capacity of the voice signal is greater than the transmission threshold, the voice signal is sent to the server so that the server can perform voice recognition processing on the voice signal. When the signal capacity of the voice signal is less than or equal to the transmission threshold, the voice signal is saved locally and not sent to the server. When the signal capacity of the voice signal acquired N times consecutively is less than or equal to the transmission threshold, the voice signals acquired N times consecutively are spliced ​​together and the spliced ​​voice signal is sent to the server so that the server can perform voice recognition processing on the spliced ​​voice signal, where N is a positive integer greater than 1. If the recognition result is received from the server, and the recognition result is a failure, the voice signal saved locally for N consecutive times will be cleared.

9. The speech signal processing method according to claim 8, characterized in that, The signal capacity is the timing duration, the transmission threshold is the duration threshold, and the method further includes: Simultaneously acquiring the voice signal from the sound acquisition device, a timing signal is acquired from a timer, the timer triggering timing when the acquisition of the voice signal begins; When the timing duration of the timing signal is less than or equal to the duration threshold, a first voice signal is acquired, and the acquired first voice signal is saved locally, wherein the first voice signal is the signal acquired from the sound collector from the start of timing to the duration threshold time. When the timing duration of the timing signal exceeds the duration threshold, a first voice signal and a second voice signal are acquired, and the first voice signal and the second voice signal are sent to the server. The second voice signal is the signal acquired from the sound collector after the timing duration exceeds the duration threshold.

10. The speech signal processing method according to claim 8, characterized in that, The signal capacity is the amount of voice data, the transmission threshold is the data volume threshold, and the method further includes: Simultaneously, the voice signal is acquired from the sound acquisition device, and the metering signal is acquired from the meter. When the amount of voice data in the metering signal is less than or equal to the data amount threshold, a third voice signal is acquired, and the acquired third voice signal is saved locally. The third voice signal is the signal acquired from the sound acquisition device from the start of metering to the time within the data amount threshold. When the amount of voice data in the metering signal exceeds the data amount threshold, a third voice signal and a fourth voice signal are acquired, and the third voice signal and the fourth voice signal are sent to the server. The fourth voice signal is the signal acquired from the sound collector after the amount of voice data exceeds the data amount threshold.

Images