Voice inputting method and device

Abstract

The invention relates to computer voice inputting technology, in particular to a voice inputting method and a voice inputting device for converting speaking voice into relevant characters and mainly aims to provide a voice inputting method which can lower voice recognition error rate and has an intelligent recognition function. The voice inputting method comprises the following steps of: 1) acquiring voice made by a user by using a voice acquisition device; 2) filtering out noise in the acquired voice; 3) recognizing relevant characters according to a voice-character database; 4) correcting input characters according to an input context to obtain correct characters; and 5) displaying all obtained input characters or inputting all the obtained input characters into a file. The invention provides high-resolution and high-quality voice inputting technology for greatly lowering the voice inputting error rate of computers and other electronic devices, so that the way of inputting characters by voice can be accepted generally.

Description

technical field [0001] The invention relates to a computer voice input technology, in particular to a voice input method and device for converting spoken voice into corresponding characters. Background technique [0002] The emergence of computers has provided great convenience for people to write and write, and it allows anyone who knows a little about computers to write any documents and letters conveniently. By far the best and most widely used method of writing on a computer is with a keyboard. But this method has two disadvantages, one is slow, especially the user keyboard input Chinese, because the keyboard is designed for inputting Western characters in essence; When there is a higher input speed requirement. [0003] Because the text input speed is slow with the keyboard, and the speed of people's speech is far faster than the speed of keyboard input, so it is not suitable for recording meetings and conversations. And for people who have not been specially trained...

AI Technical Summary

Problems solved by technology

When the words spoken by people are input into the computer through the microphone and converted into numerical phonemes, due to the quality of the microphone, the audio collection process and the digital-to-analog conversion, noise will inevitably be generated. These noises are superimposed on the speech signal and account for the input phoneme. A considerable proportion, resulting in a false speech input signal, which inevitably leads to error-prone speech recognition

Images