Speech information processing method and device

Abstract

The invention discloses a speech information processing method and device. The method comprises the steps that: the recording thread in a control terminal is always maintained at a starting state in the process that a preset speech input method is started when a speech input trigger operation is detected; the first speech information inputted in the process that the preset speech input method is started is recorded through the recording thread; the caching is carried out continuously in the recording process of the first voice information, and the cache data with a first preset time length is obtained. Through the technical scheme of the invention, through continuously caching in the recording process of the first voice information, the cache data with a first preset time length is obtained, a part of voice information lost due to the early or delay triggering of a preset recording button in each recording process can be obtained from the cache data, while the voice information in each recording process is completed, and the alignment of the recording time point of each recording process is realized.

Description

technical field [0001] The present invention relates to the technical field of terminals, in particular to a method and device for processing voice information. Background technique [0002] At present, when using the voice input method for voice recognition, the recording is started only when the recording button is pressed, and then the recorded voice is recognized as text and then output, while the recording scheme in the related technology corresponds to two threads , a recording thread and a recognition thread. The specific recording process is as follows: when the recording button is pressed, the recording thread and the recognition thread corresponding to the voice input method are started, and the recording thread is responsible for starting the terminal recording to record the input voice information. The recognition thread is responsible for taking voice information from the recording thread and sending it to the server for recognition. After the recognition is com...

AI Technical Summary

Problems solved by technology

[0002] At present, when using the voice input method for voice recognition, the recording is started only when the recording button is pressed, and then the recorded voice is recognized as text and then output, while the recording scheme in the related technology corresponds to two threads , a recording thread and a recognition thread. The specific recording process is as follows: when the recording button is pressed, the recording thread and the recognition thread corresponding to the voice input method are started, and the recording thread is responsible for starting the terminal recording to record the input voice information. The recognition thread is responsible for taking voice information from the recording thread and sending it to the server for recognition. After the recognition is completed, the recognized text is obtained from the server and output. However, it takes a certain amount of time for the recording thread to start recording at the terminal. Therefore, in the related art The recording solution may cause recording delay. At the same time, the recording thread in the related art does not buffer the recorded voice information. Therefore, if the user presses / lifts the recording button during a recording, the action is slightly delayed or advanced. , it will cause the loss of part of the voice information in the recording process

Images