Voice based question-answering system and method for interactive voice system

A question answering system and voice technology, applied in voice analysis, voice recognition, special data processing applications, etc., can solve problems such as semantic similarity is not considered, and achieve the effect of improving effectiveness, reducing storage capacity requirements, and high precision

Inactive Publication Date: 2015-03-18
CANON KK
View PDF4 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

That is, semantics is also an important aspect for speech-based question answering systems, but in existing methods, only the acoustic and linguis

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 based question-answering system and method for interactive voice system
  • Voice based question-answering system and method for interactive voice system
  • Voice based question-answering system and method for interactive voice system

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0049] Below, will refer to figure 2 and image 3 A first embodiment of the present invention will be described in detail.

[0050] figure 2 A block diagram of the voice-based question answering system 100 according to the first embodiment of the present invention is exemplarily shown.

[0051] like figure 2 As shown, the speech-based question answering system 100 according to the first embodiment of the present invention may include a question answering data storage unit 101 , a speech recognition unit 102 , a semantic similarity calculation unit 103 , and a classification unit 104 .

[0052] Wherein, questions and answers corresponding to the questions are stored in association in the question-answer data storage unit 101 .

[0053] Also, the voice recognition unit 102 is configured to perform voice recognition on questions uttered by the user by using, for example, a language model.

[0054] And, the semantic similarity calculating unit 103 is configured to calculat...

no. 2 example

[0073] Below, will refer to Figure 4 , Figure 5 A second embodiment according to the present invention will be described.

[0074] In the present invention, various semantic similarities can be calculated, specifically, various semantic similarities between the questions uttered by the user and the questions recorded in the question-and-answer data storage unit can be calculated. That is to say, various calculation methods of semantic similarity are within the protection scope of the present invention. However, for the sake of brevity, the following will only refer to Figure 4 , Figure 5 To describe an example of the calculation of semantic similarity.

[0075] Figure 4 A block diagram of an example semantic similarity calculation unit 103 according to an embodiment of the present invention is exemplarily shown.

[0076] like Figure 4 As shown, the semantic similarity calculation unit 103 may include a first bag of words generation component 1031, a first word sel...

no. 3 example

[0124] Below, will refer to Figure 6 , Figure 7 , Figure 8 , Figure 9 A third embodiment according to the present invention will be described. In these drawings for describing the present embodiment, unless otherwise specified, the same reference numerals as those in the first and second embodiments are used to denote components having the same functions.

[0125] first, Figure 6 A block diagram of another speech-based question answering system 200 according to an embodiment of the present invention is exemplarily shown.

[0126] Preferably, the speech-based question answering system 200 may further include a confidence calculation unit 205 . The confidence calculation unit 205 is configured to calculate the confidence for the question uttered by the user based on the recognition result output by the speech recognition unit 102 about the question uttered by the user.

[0127] For example, the question spoken by the user can be determined by dividing the acoustic sco...

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 relates to a voice based question-answering system and a method for an interactive voice system. The voice based question-answering system comprises a question-answering data storing unit, a voice recognizing unit, a semantic similarity calculating unit and a classifying unit, wherein the question-answering data storing unit is used for storing questions and the answers corresponding to the questions by an association manner; the voice recognizing unit is used for performing voice recognition for questions asked by a user through a language model; the semantic similarity calculating unit is used for calculating the semantic similarity of the question asked by the user and each question stored in the question-answering data storing unit according to the recognizing result performed by the voice recognizing unit for the questions asked by the user, wherein the semantic similarity is used for describing the similarity of the questions asked by the user and each question stored in the question-answering data storing unit based on the meanings; the classifying unit is used for classifying the questions asked by the user into the questions in the storing unit and the questions outside the storing unit according to the semantic similarity calculated by the semantic similarity calculating unit.

Description

technical field [0001] The present invention relates to speech-based question answering systems and methods for interactive speech systems. Background technique [0002] In recent years, voice-based question answering systems that can automatically answer questions asked by users have been studied. For this type of system, an example-based answer generation method, which utilizes a question-answer database that includes many question-answer pairs, is an efficient approach. When a question answering system receives a question from a user, it first uses a speech recognizer to identify the question asked by the user, then selects the question in the question answer database that is most similar to the result recognized by the speech recognizer from the question answer database, and Answers paired (ie, corresponding) to the selected question in the question-answering database are provided to the user. [0003] However, the problem with instance-based answer generation methods ...

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
IPC IPC(8): G06F17/30G10L15/32
CPCG06F16/334G06F16/3329G06F16/3344G10L15/32
Inventor 左祥金浩
Owner CANON KK
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