Voice identification method and voice identification device

Abstract

The invention relates to the information processing technology field and particularly relates to a voice identification method and a voice identification device. The method comprises steps that: voice data is acquired; the type of the voice data is automatically determined according to attribute information of the voice data; an acoustic model in matching with the type of the voice data is selected to carry out voice identification. Through the technical scheme, the corresponding acoustic model is established according to the type of the voice data, so establishment of the acoustic model is more accurate, the corresponding acoustic model in matching with the type of the voice data is selected to carry out voice identification, and thereby voice identification is more accurate.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to View More

AI Technical Summary

Benefits of technology

This patented technology allows users to easily recognize their own speech through unique features such as speaking patterns or pronunciation differences between them. It uses this knowledge from training models on specific datasets containing these variations to improve accuracy when recognizing spoken words over time.

Problems solved by technology

This patented technical problem addressed in this patents relates to how accurately an audio module can recognize voice patterns that are unique across multiple languages without being affected by factors like background noise levels.

Images