Multilingual speech recognition method and system based on soft queuing call center

A speech recognition and multilingual technology, which is applied in the direction of special services for subscribers, devices for providing special services by branch offices, and data exchange details, etc. It can solve problems such as the inability to realize multilingual speech recognition

Active Publication Date: 2011-11-30
CHINA TELECOM CORP LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the multilingual speech recognition ASR function cannot be realized

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
  • Multilingual speech recognition method and system based on soft queuing call center
  • Multilingual speech recognition method and system based on soft queuing call center
  • Multilingual speech recognition method and system based on soft queuing call center

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Figure 5 It is a flow chart of a multilingual voice recognition method based on soft queuing call center in the present invention, comprising the following steps:

[0030] In step 501, the call is connected to the soft queuing machine, and the soft queuing machine sends a routing request to the computer telecommunications integration server CTI;

[0031] The telephone user dials the service hotline of the call center, and the soft queue machine identifies the type of multilingual call and connects to the call center. When connecting to the call, the soft queuing machine can identify the language attribute according to network attributes such as the user's access number, call source, and access trunk, and carry the language attribute in the routing request. The language call can be at least one of the following: Chinese, English, French, Japanese. Of course, language expansion can also be performed as needed.

[0032] In step 502, establish a call connection between ...

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 present invention proposes a multilingual speech recognition method and system based on a soft queuing call center, comprising the following steps: connecting the call to a soft queuing machine, and sending a routing request to a computer telecommunications integration server CTI by the soft queuing machine; The call connection between the soft queuing machine and the interactive voice response server IVR; when multilingual calls are made between the soft queuing machine and the IVR, the IVR sends a request for calling the multilingual process to the application server; the multilingual process will be indicated by the application server The language tag of the language process is passed to the IVR; according to the language tag, the IVR calls the automatic speech recognition ASR client to the different language grammar ports of the multilingual speech recognition ASR server in the background; calls the compilation server corresponding to the language grammar port, according to different The grammar file and the language model recognize the speech, and return the recognized text to the IVR. The invention can realize multilingual speech recognition function.

Description

technical field [0001] The invention relates to the field of soft queuing call centers, in particular to a multilingual speech recognition method and system based on soft queuing call centers. Background technique [0002] Talking to a machine so it can understand what you say has been a long-held dream. Speech recognition technology is to allow machines to convert speech signals into corresponding text or commands through the process of recognition and understanding. ASR (Automatic Speech Recognize, Automatic Speech Recognition) provides a "user-friendly" human-computer interaction method, which can recognize the phrase spoken by the caller, and convert the voice text into action instructions or information that the automatic system can execute. The ASR automatic speech recognition feature uses natural language understanding (NLU) technology to allow callers to make requests to the system in their own language. [0003] The voice recognition system provides efficient and ...

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): H04L12/16H04M3/51H04M3/493
Inventor 陈健邵伟翔
Owner CHINA TELECOM CORP LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products