Title:
SPEECH PROCESSING DEVICE, SPEECH PROCESSING METHOD, AND RECORDING MEDIUM
Document Type and Number:
WIPO Patent Application WO/2021/024869
Kind Code:
A1
Abstract:
Provided is a speech processing device, for example, capable of performing processing taking into consideration the influence of noise with respect to speech made by an utterance by a person. A speaker extracting unit extracts a speaker area from an image. A first utterance data generating unit, on the basis of the shape of the lips of the speaker, generates first utterance data indicating the content of the utterance by the speaker. A second utterance data generating unit, on the basis of a speech signal corresponding to the utterance by the speaker, generates second utterance data indicating the content of the utterance by the speaker. A comparison unit compares the first utterance data and the second utterance data with each other.
More Like This:
| JP2017098720 | IMAGING APPARATUS |
| JPH04312091 | INFRARED RAY IMAGE PICK-UP DEVICE |
| JP4799910 | Devices and methods for detecting people in the survey area |
Inventors:
SASAKI KAZUYUKI (JP)
Application Number:
PCT/JP2020/028955
Publication Date:
February 11, 2021
Filing Date:
July 29, 2020
Export Citation:
Assignee:
NEC CORP (JP)
International Classes:
H04N7/18; G10L15/24; G10L15/25
Domestic Patent References:
| WO2007114346A1 | 2007-10-11 |
Foreign References:
| JP2010262424A | 2010-11-18 | |||
| JP2019125927A | 2019-07-25 | |||
| JP2018091954A | 2018-06-14 | |||
| JPH08187368A | 1996-07-23 | |||
| JP2011013731A | 2011-01-20 | |||
| JP2011013731A | 2011-01-20 | |||
| JP2019142951A | 2019-08-29 |
Other References:
See also references of EP 4009629A4
Attorney, Agent or Firm:
SHIMOSAKA Naoki (JP)
Download PDF: