Voice recognition apparatus

A voice recognition and dictionary technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of increasing the time to recognize the dictionary, increasing the generation of the recognition dictionary, and unable to reduce the number of words to be recognized, so as to reduce the usage capacity and shorten the time. Effect

Inactive Publication Date: 2012-11-07
MITSUBISHI ELECTRIC CORP
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] However, in Patent Document 1, since the vocabulary to be recognized is selected based on the history of previous voice recognition and vocabulary retrieval results, there is a problem that the number of vocabulary to be recognized cannot be narrowed down according to the content of the conversation. The generated growth of the recognition lexicon increases
[0007] Similarly, in Patent Document 2, the number of words to be recognized cannot be reduced based on the content of the user's action history, which may increase the time required to generate a recognition dictionary.

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
  • Voice recognition apparatus
  • Voice recognition apparatus
  • Voice recognition apparatus

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach 1

[0024] figure 1 It is a block diagram showing the configuration of the voice recognition device according to Embodiment 1 of the present invention. Voice recognition device 1 in Embodiment 1 uses the following recognition dictionaries for voice recognition: a recognition dictionary created in advance before performing voice recognition by dialogue with the user; and a recognition dictionary created during dialogue with the user. In the present invention, a so-called statically generated recognition dictionary is referred to as a "statically generated dictionary" before voice recognition is performed through dialogue with the user. The dictionaries are called "dynamically generated dictionaries".

[0025] The recognition dictionary static generation determination unit 2 is a component that determines whether it is necessary to statically generate a recognition dictionary using the vocabulary based on the number of vocabulary that can be used for speech recognition. The recogn...

Embodiment approach 2

[0054] figure 2 It is a block diagram showing the configuration of the voice recognition device according to Embodiment 2 of the present invention. Such as figure 2 As shown, the voice recognition device 1A in Embodiment 2 further includes a dynamically generated dictionary management unit (storage management unit) 11 and a dynamically generated dictionary temporary storage unit in addition to the structure of the voice recognition device 1 shown in the above-mentioned Embodiment 1. (temporary storage unit) 12. In addition, in figure 2 in, right with figure 1 The same or equivalent structures are marked with the same reference numerals, and descriptions are omitted.

[0055] The dynamically generated dictionary management unit 11 is a component that manages storage processing of the dynamically generated dictionary generated by the recognition dictionary dynamically generated unit 8 in the dynamically generated dictionary temporary storage unit 12 . The dynamically gen...

Embodiment approach 3

[0070] image 3 It is a block diagram showing the configuration of the voice recognition device according to Embodiment 3 of the present invention. The voice recognition device 1B in Embodiment 3 is a device that performs voice recognition while switching recognition target vocabulary by using a dialogue with the user, and is assumed to be a music search (for example, songs in the entire device, songs after selecting an artist, selecting an album, etc.) A voice recognition device that changes the vocabulary to be recognized for each dialogue situation (scene where voice recognition is performed) along the hierarchical structure of the vocabulary.

[0071] Such as image 3 As shown, the voice recognition device 1B includes: a recognition dictionary static generation determination unit 2a, a recognition dictionary static generation unit 3a, a recognition object vocabulary storage unit 4a, a static generation dictionary storage unit 5a, a dialog management unit 6a, and a recogni...

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

For a vocabulary of which the number of words to be recognized exceeds a threshold value, a recognition dictionary (statically generated dictionary) is generated in advance, and for a vocabulary of which the number of words to be recognized is less than the threshold value, a recognition dictionary (dynamically generated dictionary) is generated during a dialogue.

Description

technical field [0001] The present invention relates to a voice recognition device for voice recognition of an input voice. Background technique [0002] In the conventional voice recognition device, in the case of voice recognition in which the range of words to be recognized by dialogue is gradually narrowed by large vocabulary recognition, a voice recognition dictionary corresponding to the content of the dialogue is generally created in advance (hereinafter referred to as recognition vocabulary). dictionary). Therefore, when it is necessary to generate recognition dictionaries corresponding to various dialogue contents, a large-capacity storage device is required to store the pre-generated recognition dictionaries. [0003] In addition to the above-mentioned case of generating a recognition dictionary in advance, there is a case of generating a recognition dictionary by collecting recognition target vocabulary online according to the progress of a conversation with a us...

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): G10L15/06G10L15/22
CPCG10L15/22G10L2015/228
Inventor 山崎道弘丸田裕三
Owner MITSUBISHI ELECTRIC CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap