Voice recognition apparatus, voice recognition method and recording medium

A sound recognition and sound signal technology, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as difficult to determine unknown word models, achieve the effect of preventing wrong recognition and improving accuracy

Inactive Publication Date: 2010-01-13
FUJITSU LTD
View PDF3 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] In the above-mentioned voice recognition device, the unknown word model and the weight multiplied by the unknown word model are mostly manually determined and registered according to a certain method. In this case, it is difficult to determine the most appropriate unknown word model

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 method and recording medium
  • Voice recognition apparatus, voice recognition method and recording medium
  • Voice recognition apparatus, voice recognition method and recording medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach 1

[0026] Hereinafter, the voice recognition device disclosed in the present application will be described in detail with reference to the drawings showing Embodiment 1. FIG. figure 1 It is a block diagram showing the configuration of the voice recognition device according to the first embodiment. The voice recognition device 1 according to Embodiment 1 is, for example, a known personal computer, and has a control unit 10, a ROM (Read Only Memory: Read Only Memory) 11, a RAM (Random Access Memory: Random Access Memory) 12, and a hard disk drive (hereinafter , referred to as HDD) 13, operation unit 14, and display unit 15, etc., and each part of these hardware is connected to each other via a bus 1a.

[0027] The control unit 10 is a CPU or an MPU (Micro Processor Unit: microprocessor), etc., reads a control program stored in the ROM 11 or HDD 13 in advance into an appropriate RAM 12, executes the control program, and controls each of the above-mentioned hardware. part of the act...

Embodiment approach 2

[0084] Hereinafter, a voice recognition device according to Embodiment 2 will be described. Here, the voice recognition device according to Embodiment 2 can use the same method as described in Embodiment 1 above. figure 1 The voice recognition device 1 shown is realized by the same configuration, and thus the same configurations are given the same reference numerals and their descriptions are omitted.

[0085] The speech recognition device 1 of the above-mentioned first embodiment is configured as follows: for a recognized word to which a discarded word is desired to be added, speech recognition processing is performed on speech data of a plurality of discarded word candidates, and as a result, the recognized word to which a discarded word is desired to be added is recognized. Words with a large number of pronunciations are set as discarded words. The speech recognition device 1 of the second embodiment is configured as follows: speech recognition processing is performed on t...

Embodiment approach 3

[0110] Hereinafter, a voice recognition device according to Embodiment 3 will be described. Here, the voice recognition device according to Embodiment 3 can use the same method as described in Embodiment 1 above. figure 1 The voice recognition device 1 shown is realized by the same configuration, and thus the same configurations are given the same reference numerals and their descriptions are omitted.

[0111] The voice recognition device 1 of the third embodiment is the same as the voice recognition device 1 of the above-mentioned first embodiment, and performs voice recognition processing on the voice data of a plurality of discarded word candidates, and as a result, recognizes the pronunciation of the recognized word for which a discarded word is desired to be added. Most words are determined as discarded words. Here, in the voice recognition device 1 according to Embodiment 3, the control unit 10 extracts a part of words specified as discarded words, and registers them as...

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 present invention provides a voice recognition apparatus and a voice recognition method. An extraction unit respectively extractes feature amounts from a plurality of voice data relative to a plurality of rejected words when the rejected words are applied to recognition words registered in the word dictionary. A collation unit calculates a degree of similarity between the voice signal and each of the recognition words and reject words stored in the word dictionary by using the feature amount extracted by the extraction unit. A result determination unit determines whether or not a word having a high calculated degree of similarity corresponds to a reject word, when the word is determined as the reject word. A reject word generation unit generates an acoustic model from a voice signal having a high degree of similarity to the recognition word to which the reject word is added, calculated by the collation unit, and stores the generated acoustic model in the word dictionary as a reject word relating to the recognition word.

Description

technical field [0001] The present invention relates to a voice recognition device that judges which of the recognition words the voice signal is based on the similarity between the voice signal and pre-registered recognition words and outputs a recognition result, a voice recognition method of the voice recognition device, and a record There is a recording medium of a computer program for realizing the voice recognition device with a computer. Background technique [0002] In the existing voice recognition device, there is a device that prepares in advance a word dictionary in which information on recognized words is registered, and a discarded word dictionary in which information on discarded words is registered (for example, refer to Japanese Patent Application Laid-Open No. 2001-147698 Gazette, Japanese Patent No. 3105863). Such a voice recognition device compares voice information input by a speaker with information registered in a word dictionary and a dictionary of d...

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): G10L15/26G10L15/06
CPCG10L15/08G10L2015/025
Inventor 原田将治
Owner FUJITSU LTD
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