Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Voice recognition device and voice recognition method, language model generating device and language model generating method, and computer program

A language model, speech recognition technology, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as laborious, difficult to specify intention, difficulty, etc.

Inactive Publication Date: 2010-09-29
SONY CORP
View PDF8 Cites 212 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0020] However, even though large amounts of learning data can be collected from media such as books, newspapers, and magazines, as well as from text on websites, selecting the phrases a speaker is likely to utter is laborious and makes large corpora completely incompatible with meaning. Figure 1 To is also difficult
Furthermore, it is difficult to specify the intent of each text or classify text by intent
In other words, it is not possible to collect a corpus that exactly matches the speaker's intent

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 device and voice recognition method, language model generating device and language model generating method, and computer program
  • Voice recognition device and voice recognition method, language model generating device and language model generating method, and computer program
  • Voice recognition device and voice recognition method, language model generating device and language model generating method, and computer program

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] The present invention relates to speech recognition technology, and has main features of focusing on a specific task, accurately estimating the intention in what a speaker utters, thereby solving the following two points.

[0063] (1) Simply and appropriately collect a corpus with what a speaker might say for each intent.

[0064] (2) Matching arbitrary intentions to utterances (which are inconsistent with the task) is not enforced, but rather ignored.

[0065] Embodiments for solving these two points will be described in detail below with reference to the accompanying drawings.

[0066] figure 1 The functional structure of the speech recognition device according to the embodiment of the present invention is schematically shown. The voice recognition device 10 in the drawing is equipped with a signal processing section 11 , an acoustic score calculation section 12 , a language score calculation section 13 , a dictionary 14 and a decoder 15 . The speech recognition d...

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 discloses a voice recognition device and a voice recognition method, a language model generating device and a language model generating method, and computer program. The speech recognition device includes one intention extracting language model and more in which an intention of a focused specific task is inherent, an absorbing language model in which any intention of the task is not inherent, a language score calculating section that calculates a language score indicating a linguistic similarity between each of the intention extracting language model and the absorbing language model, and the content of an utterance, and a decoder that estimates an intention in the content of an utterance based on a language score of each of the language models calculated by the language score calculating section.

Description

technical field [0001] The present invention relates to a speech recognition device and a speech recognition method for recognizing the content of a speaker's utterance, a language model generation device and a language model generation method, and a computer program, and more particularly, to a method for estimating a speaker's intention and A speech recognition device, a speech recognition method, a language model generation device, a language model generation method, and a computer program for grasping tasks executed by a system through speech input. [0002] More precisely, the present invention relates to a speech recognition device and a speech recognition method, a language model generation device and a language model generation method, and a computer program for accurately estimating intent in speech content using a statistical language model, and more particularly, to Speech recognition device and speech recognition method, language model generation device and languag...

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): G10L15/00G10L15/18G10L15/183
CPCG10L15/1815G10L15/183
Inventor 前田幸德本田等南野活树
Owner SONY CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products