Digital bidirectional intelligent voice explanation system and method thereof

Abstract

The invention provides a digital bidirectional intelligent voice explanation system that comprises a PC server and terminal devices and is based on a TTS. The PC server is used for management and configuration of corresponded files as well as all the terminal devices can work independently; therefore, the system has good stability. According to the current explanation system, pronounced explanation only can be carried out according to a prestored pronunciation text. However, the provided system is different from the current explanation system. All the terminal devices in the system can select to carry out pronunciation according to a prestored pronunciation text or directly carry out voice amplification on on-site sounds of a narrator; and the pronunciation explanation is not influenced by a machine; therefore; demand maximization can be realized; and when there is a fault on the equipment, an emergent measure can be taken. Pronunciation files are stored and managed in a test mode; occupied resources are small; application flexibility and maintainability are strong; and a pronunciation content can be changed by modifying a text. And voice identification key words are stored and managed in a text mode as well as configuration modification can be carried out on the key words according to different demands of venues; and even when exhibits in the venues are changed, rapid configuration can also be carried out by the server and thus the flexibility is strong.

Description

technical field [0001] The invention relates to a voice explanation system, which is mainly used in various venues for intelligent voice explanation of products and exhibits and intelligent human-machine voice interaction. Background technique [0002] With the continuous development of electronic technology and information technology, especially the development of speech recognition algorithm and speech synthesis algorithm, it can replace repetitive human labor and can reflect its humanized operation. There are similar explanation systems on the market, but most of them are based on the way of voice storage and recall. With this architecture, the voice pronunciation is the call of the voice data files stored in the memory in advance. The pronunciation is also relatively rigid, and the system is poor in humanization and maintainability. . There are also systems based on TTS, but the algorithm must be completed on a PC. In specific applications, the cost of the system is hig...

AI Technical Summary

Problems solved by technology

There are similar explanation systems on the market, but most of them are based on the way of voice storage and recall. With this architecture, the voice pronunciation is the call of the voice data files stored in the memory in advance. The pronunciation is also relatively rigid, and the system is poor in humanization and maintainability.

There are also systems based on TTS, but the algorithm must be completed on a PC. In specific applications, the cost of the system is high, especially for systems of a certain scale, and the stability cannot be guaranteed.

Images