Speech processing method and terminal

Abstract

A voice processing method and a terminal. The method comprises: retrieving voice information, of which the usage frequency reaches a designated value in a server end, and locally saving the voice information (S11); after input information is received, recognizing voice feature information from the information and converting same into a voice instruction (S12); and according to the voice instruction, performing matching in the locally saved voice information, and if no corresponding voice information is matched, sending the voice instruction for matching to the server end (S13). The method and terminal can increase voice recognition flexibility, controllability, expansibility and resource reusability on the premise of guaranteeing the recognition rate.

Description

Technical field [0001] The present invention relates to the field of communication technology, in particular to a method and terminal for voice processing. Background technique [0002] After entering the 1990s, great progress has been made in the system framework of speech recognition and the application and productization of speech recognition technology. The application field of speech recognition technology is very wide, such as industrial control, education, communication and so on. As 3G mobile phones gradually enter the lives of ordinary consumers, people can use mobile phones to perform more and more functions. With the development and progress of the times, voices are converted into text or pinyin; the technology of converting text or pinyin into voice is becoming more and more. The more mature, the larger the capacity of the speech model library. Generally speaking, the speech model library involved in speech recognition and speaker recognition has a larger amount of i...

AI Technical Summary

Problems solved by technology

[0004] However, such a speech recognition method is likely to cause the problem of untimely query response due to network connection reasons during speech recognition, especially when the network link is not in a good condition, it is easy to fail to recognize or misrecognize, making it wrong. operate

In addition, when the device performs speech recognition and judgment, the voice signal is input. Due to the large amount of information in the speech model database stored on the server side, the speech recognition query and matching process takes a long time, which easily leads to a decrease in response speed and even a decline in the recognition rate during judgment.

Images