Voice recognition method and system

[0057] Example one

[0058] See figure 1 , figure 1 It is a schematic flowchart of a voice recognition method disclosed in an embodiment of the present invention. Such as figure 1 The voice recognition method shown may specifically include the following steps:

[0059] 101. When receiving the user's voice, detect whether the user's voice is a recognizable voice, if yes, end this process; if not, perform step 102 to step 104.

[0060] In the embodiment of the present invention, the user voice received in step 101 can be received by an electronic device running a voice recognition system when in the voice search mode. The specific implementation of step 101 will be described in the following method embodiments. The embodiments of the present invention will not be repeated. Among them, the above-mentioned recognizable voice may be standard Mandarin that can be recognized by a traditional voice recognition system. If the user voice is a recognizable voice, the user voice can be recognized

[0068] Example two

[0069] See figure 2 , figure 2 It is a schematic flowchart of another voice recognition method disclosed in an embodiment of the present invention. Such as figure 2 The voice recognition method shown may specifically include the following steps:

[0070] 201. When a user voice is received, the initial pinyin is obtained according to the user voice.

[0071] 202. Search for the word corresponding to the initial pinyin in the standard word library.

[0072] 203. When a word corresponding to the initial pinyin is found in the standard word database, it is determined that the user voice is a recognizable voice.

[0073] 204. When the word corresponding to the initial pinyin is not found in the standard word library, it is determined that the user voice is not a recognizable voice.

[0074] In the embodiment of the present invention, the standard word database can be a voice recognition tool of a traditional speech recognition system. The standard word database can recor

[0081] Example three

[0082] See image 3 , image 3 It is a schematic flowchart of another voice recognition method disclosed in an embodiment of the present invention. Such as image 3 The voice recognition method shown may specifically include the following steps:

[0083] For the detailed description of step 301 to step 305, please refer to the description of step 201 to step 205 in the second embodiment, which is not repeated in this embodiment of the present invention.

[0084] 306. Acquire a personalized word library corresponding to the user information.

[0085] 307. Judge whether to find the word corresponding to the initial pinyin in the personalized word library, if yes, end this process; if not, perform step 308 to step 310.

[0086] In the embodiment of the present invention, the personalized word library stores a number of words and each word corresponding to the wrong pinyin caused by the user's accent, and the personalized word library is associated with user information