VOICE RECOGNITION METHOD AND APPARATUS, COMPUTER DEVICE, AND COMPUTER-READABLE STORAGE MEDIUM

摘要

A voice recognition method and apparatus, a computer device, and a computer-readable storage medium. The method comprises: obtaining voice data to be recognized; performing feature extraction on the voice data to obtain voice features of at least two voice segments; inputting the voice features of the at least two voice segments into a voice recognition model, so that cascaded hidden layers of the voice recognition model sequentially process the voice features of each voice segment to obtain hidden layer features of each voice segment, the hidden layer features of an i-th voice segment being determined on the basis of n voice segments behind the i-th voice segment in time sequence and the voice features of the i-th voice segment; and obtaining text information corresponding to the voice data on the basis of the hidden layer features of each voice segment. In the method, text information corresponding to a voice segment is determined by combining multiple voice segments behind same, and information hereinafter is fully obtained in a voice recognition process, thereby improving the accuracy of voice recognition.