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

Speech recognition apparatus and method

A technology of speech recognition equipment and grammar, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of ineffective addition/deletion of vocabulary, excessive storage and calculation amount, etc.

Inactive Publication Date: 2009-09-23
KK TOSHIBA
View PDF1 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method has another problem that, although the processing is simple, it requires more memory and calculation than the case of considering the combination of common prefixes / common endings
[0011] As mentioned above, there is no way to efficiently perform vocabulary addition / deletion

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 apparatus and method
  • Speech recognition apparatus and method
  • Speech recognition apparatus and method

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0046] First, a method of expressing vocabulary with a network will be described, and problems of the prior art will be described in detail based on the expression method.

[0047] In general, expressing the vocabulary used in speech recognition with a network has the following two advantages.

[0048] (i) Different words with a common prefix can share data with a common prefix (nodes and arcs of the network), and / or different words with a common suffix can share data with a common suffix. Therefore, vocabulary can be saved with a smaller memory capacity.

[0049] (ii) By sharing a common prefix and / or a common suffix, the word score (word score) calculation necessary for speech recognition can be shared. Therefore, the word score can be calculated with a smaller calculation amount.

[0050] Meanwhile, according to the method of expressing vocabulary in a tree structure, prefixes are shared but suffixes are not. Thus, a tree structure is a type of network.

[0051] Figur...

no. 2 example

[0138] Hereinafter, the second embodiment will be described around main points different from the first embodiment.

[0139] This embodiment differs from the first embodiment in that it is not necessary to have any grammatical frames as independent data.

[0140] In the case of a simple sentence pattern in which the grammatical frame only includes the subnetwork X like the first embodiment, the grammatical frame does not need to be stored in the grammatical storage unit 11 . That is, it is apparent from the above description that even if the grammatical frame is not stored as data, the same grammatical network as when using the grammatical frame can be obtained by generating the grammatical network by directly adding / deleting words to the prefix part / suffix part. through with Figures 9 to 11 Add / delete vocabulary is implemented in the same process as in .

[0141] According to this embodiment, a grammar network like the first embodiment can be established, and the same effe...

no. 3 example

[0143] Hereinafter, the third embodiment will be described around the main points of difference from the first embodiment.

[0144] Although the first embodiment has been described around an example where there is a separate sub-network for operating a vocabulary, this embodiment can also be described around a case where a grammatical framework including a plurality of sub-networks is used.

[0145] Figure 14 An example of a syntax frame containing a plurality of sub-networks is shown. Figure 14 is an example of a grammatical frame expressing the "X-no-Y" (no) sentence pattern. This instance is also an instance containing a vocabulary fixed node.

[0146] exist Figure 14 In , the head node (161 in the figure) indicates the initial condition node, and the tail node (162 in the figure) indicates the final condition node. X (163 in the figure) and Y (165 in the figure) are sub-networks. That is, the grammatical frame indicates each setting vocabulary in the sub-networks X...

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

A speech recognition apparatus includes a storage unit which store vocabularies, each of vocabularies including plural word body data, each of the word body data obtained by removing a specific word head from a word or sentence, and store at least one word head portion including labeled nodes to express at least one common word head common to at least two of the vocabularies, an instruction receiving unit which receive an instruction of a target vocabulary and an instruction of a operation, a grammar network generating unit which generate, when adding is instructed, a grammar network containing the word head portion, the target vocabulary and connection information indicating that each of the word body data contained in the target vocabulary is connected to a specific one of the labeled nodes contained in the word head portion, and a speech recognition unit which execute speech recognition using the generated grammar network.

Description

[0001] Cross References to Related Applications [0002] This application is based upon and claims the benefit of priority from prior Japanese Patent Application No. 2008-071568 filed on March 19, 2008, the entire contents of which are incorporated herein by reference. technical field [0003] The invention relates to a speech recognition device and a speech recognition method. Background technique [0004] As a technique related to a speech recognition device, a technique of generating grammar for speech recognition can be used. The grammar (or speech recognition grammar) mentioned here means data or information by which one or more speech recognition target vocabulary is provided. The vocabulary mentioned here means a group of words or sentences. The speech recognition device regards each of one or more vocabularies provided by the grammar when performing speech recognition as a speech recognition target vocabulary. [0005] As one of grammar generation techniques, avai...

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 Applications(China)
IPC IPC(8): G10L15/28G10L15/22G10L15/18G10L15/193
CPCG10L15/183G10L2015/228
Inventor 馆森三庆田中信一
Owner KK TOSHIBA