Novel service robot speech recognition method

Abstract

The invention belongs to the field of speech recognition and discloses a novel service robot speech recognition method. According to the invention, a voice conversational system utilizes voice separation and text processing, and the performance of the voice conversational system is improved. The method mainly includes the following aspects: 1, a sound source separation link is added in a novel service robot speech recognition system on the basis of a traditional speech recognition system so as to solve a problem of mixed sound stream recognition by the system; 2, a text screening link is addedin the novel service robot speech recognition system on the basis of the traditional speech recognition system so as to solve a problem of meaningless text filtering by the system. Therefore, the error response rate of robot is reduced. Experiments show that mixed sound recognition rate of the novel service robot speech recognition system is greatly improved and text error response is improved distinctively compared with the traditional speech recognition system.

Description

technical field [0001] The invention belongs to the field of speech recognition, and relates to a novel service robot speech recognition method. Background technique [0002] Speech recognition is to enable machines to understand what people say, and its fundamental purpose is to study a machine with auditory function, so that the machine can directly accept people's speech, understand people's intentions and make corresponding responses. At present, many algorithms have been proposed for speech recognition, but these studies are basically based on a relatively pure speech environment. Once there is noise interference or other people's voices in the environment, speech recognition will be seriously affected. Because most speech recognition systems for speech recognition are basically built in a "pure" environment without interference, noise and reverberation. However, there are inevitably interference and noise in the implementation environment, including other people's voi...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the deficiencies of existing man-machine dialogue systems, the present invention proposes to apply methods such as sound source separation and text processing to the man-machine dialogue system, so as to solve the problem that the man-machine dialogue system is helpless to the mixed sound stream and the problem of wrong response to garbage text

The new service robot speech recognition system adds a sound source separation link on the basis of the traditional speech recognition system, which solves the problem of the system's recognition of mixed sound streams, and adds a text screening link to solve the system's filtering of "meaningless" text. Eliminate problems and improve the robot's false response rate

Images