Method of recognizing speech and electronic device thereof

Abstract

A method of recognizing a speech and an electronic device thereof are provided. The method includes: segmenting a speech signal into a plurality of sections at preset time intervals; performing a phoneme recognition with respect to one of the plurality of sections of the speech signal by using a first acoustic model; extracting a candidate word of the one of the plurality of sections of the speech signal by using the phoneme recognition result; and performing a speech recognition with respect to the one the plurality of sections the speech signal by using the candidate word.

Description

[0001] This application claims priority from Korean Patent Application No. 10-2012-0076809 filed with the Korean Intellectual Property Office on Jul. 13, 2012, the disclosure of which is hereby incorporated by reference in its entirety. technical field [0002] Methods and apparatus consistent with the exemplary embodiments relate generally to recognizing speech, and more particularly, to recognizing speech uttered by a user by using an acoustic model, a language model, and a pronunciation dictionary. Background technique [0003] Voice recognition is controlled by using electronic devices such as smart phones, navigation systems, and the like. With the improvement of the hardware performance of electronic devices and the increase in the user's demand for speech recognition, the user environment has changed from an isolated word recognition method that recognizes the user's voice with many existing commands to continuous speech recognition that recognizes a variety of natural...

AI Technical Summary

Problems solved by technology

[0005] However, in continuous speech recognition methods, the search space becomes larger and thus, the storage requirement increases

Speech recognition is not feasible or may be greatly degraded due to the increased number of calculations

Images