Intelligent Speech Recognition Method Based on Three-Level Feature Acquisition

Abstract

The present application discloses an intelligent speech recognition method, device, computer equipment and storage medium based on three-level feature collection. The method includes: performing sound collection and processing to obtain a first sound signal; performing image processing on the speaker's lips Acquisition and processing to obtain the second image signal; sending a signal acquisition request to the intraoral sensor cluster; acquiring the third sensing signal set sent by the intraoral sensor cluster; combining the first sound signal, the second sensing signal subset and the third sensing signal set Input the sensing signal subset into the first semantic recognition model to obtain the first recognized text; input the second image signal, the first sensing signal subset and the second sensing signal subset into the second semantic recognition model to obtain second recognition text; calculate the text similarity value between the first recognition text and the second recognition text; if the text similarity value is greater than the text similarity threshold, then use the first recognition text as the intelligent speech recognition result.

Description

technical field [0001] The present application relates to the computer field, in particular to an intelligent speech recognition method, device, computer equipment and storage medium based on three-level feature collection. Background technique [0002] Speech recognition technology is used to recognize collected speech, which has been widely used in various fields, such as in the field of intelligent robots. Due to the application of speech recognition technology, voice communication between natural people and intelligent robots has become possible. However, the recognition accuracy of traditional speech recognition schemes still has deficiencies, such as the inability to accurately distinguish speech with small differences (for example, for retroflex and flat tongue, when the speaker's pronunciation is lighter and more ambiguous, the traditional Speech recognition schemes are difficult to accurately identify). Therefore, the recognition accuracy of traditional speech reco...

AI Technical Summary

Problems solved by technology

However, traditional speech recognition schemes still have deficiencies in their recognition accuracy, for example, they cannot accurately distinguish speech with small differences (for example, for retroflex and flat tongue, when the speaker's pronunciation is lighter and more ambiguous, the traditional Speech recognition schemes are difficult to accurately identify)

Therefore, the recognition accuracy of traditional speech recognition schemes needs to be improved

Images