Voice interaction system and method

Abstract

The invention discloses a voice interaction system and a voice interaction method. The voice interaction system comprises a preprocessing module, an acoustic model library, a language model library, an identification module and an interaction center, wherein the preprocessing module comprises a voice preprocessing module and an endpoint detection module; the acoustic model library comprises an HMMmodel matching unit, a TDNN model matching unit, an HMM model database and an ANN model database; the language model library comprises a N-Gram model database and a Rule-based model database; the identification module comprises an MFCC parameter feature extraction unit and an identification control unit; and the interaction center comprises a semantic understanding module, an interaction processing module, a response information library and a semantic dictionary database. The voice interaction system and the voice interaction method utilize a feedback module to monitor identification information and a feedback instruction of a client, demonstrate the identification information to the client by means of the identification control unit, control and change a voice matching model and the language model library, and optimize the interactive identification accuracy rate of the voice interaction system.

Description

technical field [0001] The invention relates to the field of voice interaction, in particular to a voice interaction system and method. Background technique [0002] As artificial intelligence enters daily life, people's understanding of voice interaction is getting deeper and deeper, and at the same time, the requirements for voice interaction systems in artificial intelligence are also getting higher and higher. Existing patent CN107146622A A refrigerator, a voice interaction system, a voice interaction method, computer equipment, and a computer-readable storage medium, wherein the voice interaction system includes: a voice collection module for collecting and preprocessing voice signals, and preprocessing The final speech signal is sent to the speech recognition module; the speech recognition module is used to convert the preprocessed speech signal into text information, and sends the text information to the processing module and the semantic understanding module respecti...

AI Technical Summary

Problems solved by technology

However, there are also the following disadvantages: when the customer interacts with the system and the answer is irrelevant or the voice information of the customer is obviously not recognized or understood, the customer often has nothing to do, which greatly reduces the performance of human-computer interaction

Images