Speech recognition method for name, speech recognition system and speech recognition device
A speech recognition and name technology, applied in speech recognition, speech analysis, instruments, etc., can solve problems that affect misjudgment of speech recognition, environmental noise, speech recognition process, recognition process, etc., to improve user experience and improve recognition accuracy The effect of rate and recognition efficiency
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment approach 1
[0077] The word search tree is a Chinese character search tree. The middle node of the Chinese character search tree stores each character (Chinese character) of the name, and the leaf node stores the list of entities that match the name. When the Chinese character search tree stores the accurate name, it also stores The nickname of a person's name provides data support for future identification and error correction.
[0078] The Chinese character search tree includes the following specific implementation methods:
[0079] Such as Figure 4 As shown, Ci represents a character of a person's name, and the leftmost name in the above figure is composed of sequential connections of C1, C2 and C3.
[0080] Figure 4 The middle leaf node of the middle root node represents the nickname of the person's name, which is generally a string after removing the surname. If there is only one Chinese character left after removing the surname, it will not be stored. The list(j) stored in the l...
Embodiment approach 2
[0082] The word search tree is a pinyin search tree. The middle node of the pinyin tree stores each letter of the full spelling (including accurate pinyin and fuzzy pinyin) of a person's name. Like the Chinese character tree, the leaf node stores a list of entities that match the full spelling. The extended rules of fuzzy sounds are shown in Table 1, and the rules cover the conversion of the two pronunciations before and after.
[0083] Table 1
[0084]
[0085] After defining the structure of the trie tree and the expansion rules of fuzzy sounds, the system uses specific data to start building the trie tree. The following example illustrates the process of building the trie tree.
[0086] Such as Figure 4 As shown, assume that enterprise A has contacts {Zhang Junlin (E1), Li Mei (E2)}, and enterprise B has contacts {Wang Limei (E3), Zhang Junlin (E4), Wang Yin (E5)}, because the pinyin tree uses For full spelling and fuzzy sounds, the trie tree built will be very large,...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


