Intelligent voice understanding system with multiple voice understanding engines and intelligent voice interaction method

Abstract

The invention provides an intelligent voice understanding system with multiple voice understanding engines and an intelligent voice interaction method. The intelligent voice understanding system comprises a first voice understanding engine which processes voice without adopting a transcription mode, a second voice understanding engine which processes voice in a transcription mode and an understanding result judgment unit, a voice processing unit of the first voice understanding engine processes the voice to obtain voice data in a coding sequence form, and a natural language understanding unit acquires an intention corresponding to the voice based on the voice data in the coding sequence form through a natural language understanding model; a voice processing unit of the second voice understanding engine performs transcription processing on the voice to obtain voice data in a text form, and the natural language understanding unit acquires an intention corresponding to the voice based on the voice data in the text form through a natural language understanding model; and the understanding result determination unit determines an intention corresponding to the speech on the basis of the understanding results of the two speech understanding engines.

Description

technical field [0001] The invention relates to intelligent voice processing technology, in particular to an intelligent voice understanding system with multiple voice understanding engines and an intelligent voice interaction method. Background technique [0002] The current intelligent speech processing (NLP) solution is to perform semantic analysis on the basis of the text sequence obtained from speech recognition to realize natural language understanding. Specifically, the speech is first transcribed into text, and then the text sequence is analyzed to obtain the meaning (semantics) expressed by the speech through keyword matching technology, or in combination with context or knowledge graph, or with the help of deep learning technology. This approach relies heavily on the accuracy of speech transcription. [0003] Speech transcription technology itself has significant limitations. The recognition accuracy of speech recognition is affected by many factors, and it is im...

AI Technical Summary

Problems solved by technology

However, for speech interaction scenarios where the accent or dialect is unpredictable, a better transcription model cannot be selected in advance or automatically switched, so when the transcription accuracy rate is reduced due to the transcription model, the speech understanding effect is not satisfactory

In addition, the optimization of the transcription model also requires high training data costs and labor costs

Images