Unlock instant, AI-driven research and patent intelligence for your innovation.

A voice recognition service proxy server and proxy method

A proxy server and speech recognition technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of transformation costs, inability to expand, inconvenient docking, etc., and achieve the effect of facilitating service expansion

Active Publication Date: 2021-10-26
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] 2. For ASR services, only the recognized text can be returned, and there is no good expansion. To expand, ASR needs to be coupled with other business modules
Therefore, the docking is inconvenient and there is a cost of transformation
And, for the ASR service, only the recognized text can be returned, and it cannot be well extended

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A voice recognition service proxy server and proxy method
  • A voice recognition service proxy server and proxy method
  • A voice recognition service proxy server and proxy method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments It is a part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of this application.

[0052] figure 1 It is the implementation diagram of the speech recognition service proxy server of the present invention in the integrated speech platform, as figure 1 As shown, it shows media equipment, speech recognition proxy server, service system, ASR server, extended service server, and control server.

[0053] The media device is connected to a voice...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a speech recognition service proxy server and a proxy method. The server includes an MRCP proxy module for receiving a voice stream processing request sent by a media device; sending the voice stream processing request to a service proxy module for processing; Receive the processing result from the service agent module; send the processing result to the service system application corresponding to the voice service request; the service agent module is used to receive the voice flow processing request from the MRCP agent module; communicate with the voice The service server interacts to realize the processing of the voice stream, and returns the processing result to the MRCP agent module. Decoupling between media devices and ASR services is conducive to service expansion; authentication, flow control, security, anti-cheating, etc. are performed on ASR service requests through business proxy services, which can be well applied to public clouds; connected through business proxy services Connect other business modules to expand ASR services, such as search, translation, and intent recognition.

Description

【Technical field】 [0001] The invention relates to computer application technology, in particular to a speech recognition service proxy server and a proxy method. 【Background technique】 [0002] As ASR (Automatic Speech Recognition, Automatic Speech Recognition) technologies mature and combine with each other, ASR-based value-added services continue to emerge and develop rapidly. [0003] In the prior art, media devices can directly connect to ASR services through MRCP (Media Resource Control Protocol, Media Resource Control Protocol). This application method has two disadvantages: [0004] 1. It has good support for private cloud, but not good support for public cloud, because public cloud needs to have authentication, flow control, security, anti-cheating and other mechanisms. The native method needs to support the public cloud, either abandon these mechanisms, or couple these mechanisms with ASR services; [0005] 2. For the ASR service, only the recognized text can be r...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H04L29/08H04L29/06G10L15/26
CPCH04L65/40G10L15/26H04L67/56H04L67/51
Inventor 戴俊常月黄国瑞张伟冬先永春
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD