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

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

Active Publication Date: 2018-06-22
CHANJET INFORMATION TECH CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] (2) Speaker restriction: the voice device can recognize the voice information of the specified voice, intonation and timbre;
[0014] (2) The amount of voice information is large, which is affected by the way the user issues voice commands, which will affect the recognition process or even misjudgment;
[0015] (3) The phonetic characteristics of a single letter or word or word are affected by the context, which will affect the misjudgment of speech recognition;
[0016] (4) The impact of confusing sounds on speech, specifically, like phonetic characters, front and back nasal sounds, flat tongue sounds and confusing sounds, will affect the misjudgment of speech recognition;
[0017] (5) Environmental noise and interference have a serious impact on the speech recognition process

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
  • Speech recognition method for name, speech recognition system and speech recognition device
  • Speech recognition method for name, speech recognition system and speech recognition device
  • Speech recognition method for name, speech recognition system and speech recognition device

Examples

Experimental program
Comparison scheme
Effect test

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,...

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 provides a name voice recognition method, a name voice recognition system and name voice recognition equipment. The name voice recognition method comprises the following steps: obtaining a voice character string of a name; establishing a word searching tree according to the voice character string; judging whether the word searching tree is matched with pre-stored name information or not; prompting a voice recognition result of the name to a user when name information is matched with the pre-stored name information. With the adoption of the technical scheme, the recognition accuracy and the recognition efficiency in a voice recognition process are improved; meanwhile, the requirements on intonation, speed and tone of a voice instruction sent by the user are reduced, and use experiences of the user are improved.

Description

technical field [0001] The present invention relates to the technical field of voice recognition, in particular to a name voice recognition method, a name voice recognition system and a name voice recognition device. Background technique [0002] With the rapid improvement of computer processing power, speech recognition technology has developed rapidly, and it is changing the production and life style of human beings day by day, and is widely used in fields such as speech input system, speech control system and intelligent dialogue query system. [0003] Speech recognition technology is a technology that converts speech signals into corresponding text or commands through the process of recognition and analysis. The specific process includes: [0004] (1) Acquisition and preprocessing steps: After the unknown voice is converted into an electrical signal by the microphone, it is added to the input of the recognition system, and the electrical signal is subjected to noise redu...

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): G10L15/28
Inventor θ–›δΌšθ
Owner CHANJET INFORMATION TECH CO LTD