Answer obtaining method and device for speech data, storage medium and computer equipment

Abstract

Disclosed are an answer obtaining method and device for speech data, a storage medium and computer equipment. The answer obtaining method for the speech data comprises the steps of converting the obtained speech data into a speech identifier text, wherein the speech identifier text comprises at least one word speech identifier; utilizing the word speech identifiers in the speech identifier text for word matching to obtain a character text, wherein the character text comprises semantic identifier words matched with the word speech identifiers; conducting semantic understanding processing on thecharacter text to obtain the semantics of the speech data. By means of the technical scheme, the accuracy of speech and semantic identification can be improved, accurate knowledge points of speech input are obtained accordingly, and the accuracy of obtaining answers from the speech data is improved.

Description

technical field

[0001] The invention relates to the technical field of speech recognition, in particular to a method and device for obtaining answers to speech data, storage media, and computer equipment. Background technique

[0002] With the development of speech recognition technology, speech recognition has been applied in many fields. Usually, the semantic understanding method and system based on voice interaction outputs a response to the input voice so that the user can perform further operations.

[0003] In the prior art, the speech recognition processing process and the semantic understanding processing process are serial and independent of each other. Speech recognition is responsible for using speech recognition technology to recognize interactive speech into text, and semantic understanding is responsible for using semantic understanding technology to give semantic understanding responses based on speech recognition text. Specifically, in the speech recognitio...

Images