A method for speech recognition

A speech recognition and grammar technology, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as undefined methods for users to directly input speech, and achieve the effect of simplifying the input method
CN100426377CActive Publication Date: 2008-10-15HUAWEI TECH CO LTD
2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Patents(China)
Current Assignee / Owner
HUAWEI TECH CO LTD
Publication Date
2008-10-15

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

A method, apparatus and system can accomplish the function of speech recognition; a media resource control device controls a media resource-processing device by H.248 protocol to accomplish the recognition of speech, which was input by the user. The method comprises: the media resource processing device receiving the H.248 message with speech recognition indications and correlation parameters from the media resource control device; and the speech recognition can be processed based on the indications and parameters; and the result of recognition can be sent to the media resource control device. Otherwise, the apparatus and the system, which can accomplish the function of speech recognition, can be provided.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to a method for realizing the speech recognition function, in particular to a method for realizing the speech recognition function using the H.248 protocol as a control protocol. Background technique

[0002] The speech recognition function refers to the recognition of the speech input by the user according to the specified grammar, and converts it into text. For example, in an interactive application, the system first plays a prompt to the user: "Do you need water, cola, or juice?". The user can answer by voice. The user's pronunciation can only be the voice including the keywords "water, cola, juice, no need". The system can recognize the user's voice and then provide the user with the selected products.

[0003] In fixed or mobile network applications, when user input is required, there are generally two methods:

[0004] One method is that the user inputs a DTMF (Dual Tone Multi-Frequency, Dual Tone Multi-Frequency) tone. F...

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