Voice recognition implementing method and system based on confidence coefficient

Abstract

The invention relates to a voice recognition implementing method and system based on a confidence coefficient. The method comprises the following steps: carrying out voice recognition of phoneme synchronous decoding from voice of a use to obtain a word graph acoustic information structure which is synchronous to decoding information generated phoneme, generating a confusion network on the basis of the word graph acoustic information structure so as to establish a competitive relation between voice recognition candidate results, namely a competition probability of the confusion network; meanwhile, establishing full search space of voice recognition by using an auxiliary search network based on a linguistic model; calculating to obtain complete lossless full search space probability; recording a search process of the generated full search space by voice recognition of phoneme synchronous decoding; carrying out path recalling by a whole search history so as to obtain the full search space probability; and finally, fusing the competition probability of the confusion network and the full search space probability to obtain a judgment result of voice recognition. On the one hand, correct confidence coefficient can be given for a voice recognition result so as to improve user experiences of voice recognition; and on the other hand, consumption of calculation and memory resources of voice recognition confidence coefficient algorithm can be reduced remarkably.

Description

technical field [0001] The present invention relates to an accurate and efficient Confidence Measure (CM) technology applied to speech recognition (Speech Recognition), specifically a phoneme synchronous decoding (Phone Synchronous Decoding), word graph and confusion network (Lattice and Confusion Network), a speech recognition implementation method and system for an auxiliary search space (Auxiliary Search Space). Background technique [0002] Speech recognition is an artificial intelligence technology that allows machines to convert speech signals into corresponding text or commands through the process of recognition and understanding. The existing speech recognition technology still cannot be completely correct. The confidence level is a technology used to judge the reliability of the speech recognition result of the speech recognition system itself, and is generally given by the reliability of the recognition result or the probability value of the recognition result. ...

AI Technical Summary

Problems solved by technology

[0004] The present invention aims at the incomplete characterization of the competition results of the decoding space in the prior art, resulting in inaccurate confidence; it relies on retraining each model of speech recognition, adding a large amount of additional processing; the process of constructing the decoding space has a large amount of calculation, resulting in Speech recognition takes more time, which is not conducive to improving user experience and other defects. A method and system for implementing speech recognition based on confidence is proposed. On the one hand, it can give the correct confidence for the result of speech recognition, thereby improving the user experience of speech recognition. , on the other hand can significantly reduce the computational and memory resource consumption of the speech recognition confidence algorithm

Images