KEYWORD EXTRACTING DEVICE

• US 20090150155A1
• Filed: 03/14/2008
• Published: 06/11/2009
• Est. Priority Date: 03/29/2007
• Status: Active Grant

• Current Assignee: Sovereign Peak Ventures, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Panasonic Corporation (Panasonic Holdings Corporation)
• Inventors: Konuma, Tomohiro, Nomura, Kazuya, Endo, Mitsuru, Yamada, Maki, Morii, Keiko
• Granted Patent: US 8,370,145 B2
• Time in Patent Office: Days
• US Class Current: 704/255
• CPC Class Codes: G10L 15/04 Segmentation; Word boundary detection
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 2015/088 Word spotting

Abstract

The present invention aims at extracting a keyword of conversation without preparations by advanced anticipation of keywords of conversation. A keyword extracting device of the present invention includes an audio input section 101 by way of which a speech sound made by a speaker is input; a speech segment determination section 102 that determines a speech segment for each speaker in connection with the input speech sound; a speech recognition section 103 that recognizes a speech sound of the determined speech segment for each speaker; an interrupt detection section 104 that detects a feature of a speech response suggesting presence of a keyword on the basis of a response of another speaker to speech sounds of respective speakers; namely, an interrupt where a preceding speech and a subsequent speech overlap; a keyword extraction section 105 that extracts the keyword from the speech in the speech segment specified on the basis of an interrupt; a keyword search section 106 that performs keyword search by means of the keyword; and a display section 107 that displays a result of keyword search.

Claims

1. A keyword extracting device, comprising:

an audio input section that inputs speech sound of speakers;

a speech segment determination section that determines a speech segment for each speaker in connection with the input speech sound;

a speech recognition section that recognizes the speech sound of the determined speech segment for each speaker;

a speech response feature extraction section that extracts a feature of a speech response suggesting presence of a keyword on the basis of a response from another speaker to the speech sound of each speaker; and

a keyword extraction section that extracts the keyword from the speech sound of the speech segment specified on the basis of the feature of the extracted speech response.

2. The keyword extracting device according to claim 1, wherein the speech sound of the speakers include speech sound of a preceding speech and speech sound of a subsequent speech;

wherein the speech response feature extraction section includes an interrupt detection section that detects, on the basis of the speech sound of the preceding speech and the speech sound of the subsequent speech, an interrupt where the preceding speech and the subsequent speech overlap each other, when the subsequent speech is commenced in the middle of the preceding speech; and

wherein the keyword extraction section extracts the keyword from the speech sound of the preceding speech that is specified on the basis of the detected interrupt and that overlaps the subsequent speech.

3. The keyword extracting device according to claim 1, wherein the speech sound of the speakers include speech sound of a preceding speech and speech sound of a subsequent speech;

wherein the speech response feature extraction section includes;

a pitch determination section that determines a pitch of the speech sound on the basis of the speech sound of the preceding speech and the speech sound of the subsequent speech; and

a pattern determination section that determines, from the determined pitch, a pitch pattern including a descending pitch at an end of the preceding speech and an ascending pitch of the speech immediately subsequent to the preceding speech; and

wherein the keyword extraction section extracts the keyword from the speech sound of the preceding speech which is specified on the basis of the determined pitch pattern and which is indicated by the pitch pattern.

4. The keyword extracting device according to claim 1, wherein the speech sound of the speakers include speech sound of a preceding speech and speech sound of a subsequent speech;

wherein the speech response feature extraction section extracts a functional phrase of predetermined type from the speech sound of the subsequent speech on the basis of the speech sound of the preceding speech and the speech sound of the subsequent speech; and

wherein the keyword extraction section extracts the keyword from the speech sound of the preceding speech immediately preceding the subsequent speech including the extracted functional phrase.

5. The keyword extracting device according to claim 1, wherein the speech response feature extraction section detects exciting reaction of a person other than the speakers located in the vicinity of speech segments of the respective speakers;

and

wherein the keyword extraction section extracts the keyword from the speech sound corresponding to the exciting reaction.

6. The keyword extracting device according to any one of claims 2 through 5, wherein the keyword extraction section extracts, as the keyword, a constituent element at the end of the preceding speech when the keyword is extracted.

7. The keyword extracting device according to claim 1, wherein the speech sound of the speakers include speech sound of a preceding speech and speech sound of a subsequent speech;

wherein the speech response feature extraction section extracts a functional phrase of a predetermined type from the speech sound of the preceding speech on the basis of the speech sound of the preceding speech and the speech sound of the subsequent speech; and

wherein the keyword extraction section extracts the keyword from the speech sound of the subsequent speech immediately subsequent to the preceding speech including the extracted functional phrase.

8. The keyword extracting device according to claim 1, wherein the speech response feature extraction section recognizes facial expression of another speaker responsive to speech sounds of the respective speakers and extracts a point of change in the recognized facial expression;

and

wherein the keyword extraction section extracts, as a keyword, a constituent element in the speech segment corresponding to the extracted point of change in facial expression.

9. The keyword extracting device according to claim 3, wherein the keyword extraction section extracts, as the keyword, a constituent element at the end of the preceding speech when the keyword is extracted.

10. The keyword extracting device according to claim 4, wherein the keyword extraction section extracts, as the keyword, a constituent element at the end of the preceding speech when the keyword is extracted.

11. The keyword extracting device according to claim 5, wherein the keyword extraction section extracts, as the keyword, a constituent element at the end of the preceding speech when the keyword is extracted.