Voice analysis device and voice analysis system

Patent metadata

Field	Value
Publication number	US-9704504-B2
Application number	US-201514791794-A
Country	US
Kind code	B2
Filing date	Jul 6, 2015
Priority date	Mar 3, 2015
Publication date	Jul 11, 2017
Grant date	Jul 11, 2017

Abstract

The voice analysis device includes: a voice information acquiring unit that acquires a voice signal generated by plural voice acquiring units disposed at different distances from a speaking section of a speaker and acquiring voice of the speaker; and an identification unit that identifies the speaker corresponding to the voice having been acquired, on the basis of intensities of respective peaks in a frequency spectrum of a first enhanced waveform and a frequency spectrum of a second enhanced waveform. The first enhanced waveform is a waveform where a voice signal of a predetermined target speaker has been enhanced, and the second enhanced waveform is a waveform where a voice signal of a speaker other than the target speaker has been enhanced.

First claim

What is claimed is:

1. A voice analysis device comprising:
a voice information acquiring unit, comprising a plurality of microphones disposed at different distances from a speaking section of a speaker, that acquires a voice signal generated by the microphones and representing a voice of the speaker;
an identification unit, comprising a processor, that identifies the speaker corresponding to the voice represented by the acquired voice signal, on the basis of intensities of respective peaks detected in a frequency spectrum of a first enhanced waveform and a frequency spectrum of a second enhanced waveform, the first enhanced waveform being a waveform where a voice signal of a predetermined target speaker has been enhanced, the second enhanced waveform being a waveform where a voice signal of a speaker other than the target speaker has been enhanced; and
an output unit configured to output the identity of the speaker identified by the identification unit.

2. The voice analysis device according to claim 1 , wherein
the identification unit finds peaks at the same frequency in at least two of frequency spectra containing a frequency spectrum of a waveform of the voice signal acquired by the voice information acquiring unit, the frequency spectrum of the first enhanced waveform, and the frequency spectrum of the second enhanced waveform, and identifies which speaker has a speaking voice corresponding to the voice having been acquired, on the basis of the intensities of the peaks at the same frequency.

3. The voice analysis device according to claim 2 , wherein
the identification unit identifies which speaker has the speaking voice corresponding to the voice having been acquired, on the basis of a magnitude relationship between the intensities of the peaks at the same frequency.

4. The voice analysis device according to claim 3 , wherein
the identification unit identifies the voice having been acquired, as a speaking voice of the predetermined target speaker in a case where a ratio between the intensities of the peaks at the same frequency in the waveform of the voice signal acquired by the voice information acquiring unit and the first enhanced waveform exceeds a predetermined first threshold.

5. The voice analysis device according to claim 3 , wherein
the identification unit identifies the voice having been acquired, as speaking voice of a speaker other than the predetermined target speaker in a case where a ratio between the intensities of the peaks at the same frequency in the waveform of the voice signal acquired by the voice information acquiring unit and the second enhanced waveform exceeds a predetermined second threshold.

6. The voice analysis device according to claim 3 , wherein
the identification unit identifies the voice having been acquired, as a simultaneous speaking voice of the predetermined target speaker and the speaker other than the predetermined target speaker in a case where the ratio between the intensities of the peaks at the same frequency in the waveform of the voice signal acquired by the voice information acquiring unit and the first enhanced waveform exceeds the first threshold and the ratio between the intensities of the peaks at the same frequency in the waveform of the voice signal acquired by the voice information acquiring unit and the second enhanced waveform exceeds the second threshold.

7. A voice analysis system comprising:
a plurality of voice acquiring units, comprising a plurality of microphones, that are disposed at different distances from a speaking section of a speaker and acquire a voice signal representing a voice of the speaker; and
an identification unit, comprising a processor, that identifies the speaker corresponding to the acquired voice, on the basis of intensities of respective peaks detected in frequency spectra of a first enhanced waveform and frequency spectra of a second enhanced waveform, the first enhanced waveform being a waveform where a voice signal of a predetermined target speaker has been enhanced, the second enhanced waveform being a waveform where a voice signal of a speaker other than the target speaker has been enhanced; and
an output unit configured to output the identity of the speaker identified by the identification unit.

8. The voice analysis device according to claim 1 , wherein the output unit transmits data including data representing the identity of the speaker to an external device.

9. The voice analysis device according to claim 1 , wherein the output unit comprises one of a display, a printer, and an audio device.

Assignees

• Inagi Seiya
• Harada Haruo
• Yoneyama Hirohito
• Shimotani Kei
• Fujii Akira
• Iida Kiyoshi
• Fuji Xerox Co Ltd

Inventors

• Inagi Seiya
• Harada Haruo
• Yoneyama Hirohito
• Shimotani Kei
• Fujii Akira
• Iida Kiyoshi

Classifications

• G10L17/00 Primary

  Speaker identification or verification techniques · CPC title

• G10L25/18

  the extracted parameters being spectral information of each sub-band · CPC title

• G10L17/06

  Decision making techniques; Pattern matching strategies · CPC title

• G10L25/21

  the extracted parameters being power information · CPC title

• G10L21/02 Primary

  Speech enhancement, e.g. noise reduction or echo cancellation (reducing echo effects in line transmission systems H04B3/20; echo suppression in hands-free telephones H04M9/08) · CPC title