Storage medium, sound source direction estimation method, and sound source direction estimation device

Patent metadata

Field	Value
Publication number	US-11295755-B2
Application number	US-201916532188-A
Country	US
Kind code	B2
Filing date	Aug 5, 2019
Priority date	Aug 8, 2018
Publication date	Apr 5, 2022
Grant date	Apr 5, 2022

Abstract

A non-transitory computer-readable storage medium storing a program that causes a processor included in a computer mounted on a sound source direction estimation device to execute a process, the process includes calculating a sound pressure difference between a first voice data acquired from a first microphone and a second voice data acquired from a second microphone and estimating a sound source direction of the first voice data and the second voice data based on the sound pressure difference, outputting an instruction to execute a voice recognition on the first voice data or the second voice data in a language corresponding to the estimated sound source direction, and controlling a reference for estimating a sound source direction based on the sound pressure difference, based on a time length of the voice data used for the voice recognition based on the instruction and a voice recognition time length.

First claim

What is claimed is:

1. A non-transitory computer-readable storage medium storing a program that causes a processor included in a computer mounted on a sound source direction estimation device to execute a process, the process comprising:
calculating a sound pressure difference between a first voice data acquired from a first microphone and a second voice data acquired from a second microphone to estimate a sound source direction based on the sound pressure difference between the first voice data and the second voice data;
estimating, by using the estimated sound source direction, a language from among a plurality of languages each corresponding to a respective individual sound source, the estimated language being a language corresponding to a sound source located in the estimated sound source direction;
outputting an instruction to execute, on at least any one of the first voice data or the second voice data, a voice recognition in the estimated language; and
controlling a reference for estimating a sound source direction based on the sound pressure difference, based on a time length of the voice data used for the voice recognition based on the instruction and a voice recognition time length, wherein
the process of estimating the sound source direction of the first voice data and the second voice data calculates a sound pressure difference between the first voice data acquired from the first microphone and the second voice data acquired from the second microphone, and estimates the sound source direction of the first voice data and the second voice data based on a comparison result between a first threshold value for determining the sound source direction of the first voice data and the second voice data, and the sound pressure difference, and
the process of controlling the reference updates the first threshold value when the voice recognition time length with respect to the time length of the voice data used for the voice recognition based on the instruction, is larger than a second threshold value for determining whether a language of the first voice data or the second voice data to be input to the voice recognition is different from the language corresponding to the sound source direction.

2. The non-transitory computer-readable storage medium according to claim 1 , wherein
the process of outputting the instruction to execute the voice recognition
when the sound pressure difference obtained by subtracting a sound pressure of the second voice data from a sound pressure of the first voice data is equal to or larger than the first threshold value,
estimates that a voice is uttered from a first sound source present in a direction according to a directivity of the first microphone or a directivity based on the first microphone and a sound path structure where the first microphone is installed, and
outputs the instruction to execute the voice recognition in a language corresponding to the first sound source on the first voice data, and
when the sound pressure difference is less than the first threshold value,
estimates that a voice is uttered from a second sound source present in a direction according to a directivity of the second microphone or a directivity based on the second microphone and a sound path structure where the second microphone is installed, and
outputs the instruction to execute the voice recognition in a language corresponding to the second sound source on the second voice data.

3. The non-transitory computer-readable storage medium according to claim 1 , wherein
the process of controlling the reference
increases the first threshold value when the sound pressure difference obtained by subtracting a sound pressure of the second voice data from a sound pressure of the first voice data is equal to or larger than the first threshold value and the voice recognition time length with respect to the time length of the voice data used for the voice recognition is larger than the second threshold value, and
decreases the first threshold value when the sound pressure difference is less than the first threshold value and the voice recognition time length with respect to the time length of the voice data used for the voice recognition is larger than the second threshold value.

4. The non-transitory computer-readable storage medium according to claim 1 , wherein
the process of controlling the reference calculates the sound pressure difference for a plurality of frames, and updates the first threshold value based on an average value of the calculated sound pressure differences for the plurality of frames.

5. The non-transitory computer-readable storage medium according to claim 1 , wherein
the process of controlling the reference updates the first threshold value so that a difference between the sound pressure difference and the first threshold value becomes large when the voice recognition time length with respect to the time length of the voice data used for the voice recognition is equal to or less than the second threshold value, and the difference between the sound pressure difference and the first threshold value is equal to or less than a predetermined value.

6. The non-transitory computer-readable storage medium according to claim 1 , wherein
the process of outputting the instruction to execute the voice recognition outputs the instruction to execute the voice recognition in a language corresponding to a sound source different from the estimated sound source when the voice recognition time length with respect to the time length of the voice data used for the voice recognition is larger than a third threshold value which is equal to or larger than the second threshold value.

7. The non-transitory computer-readable storage medium according to claim 1 , wherein
the process of controlling the reference sets the first threshold value based on a difference between the sound pressure differences under a plurality of noise conditions.

8. A sound source direction estimation method comprising:
calculating a sound pressure difference between a first voice data acquired from a first microphone and a second voice data acquired from a second microphone to estimate a sound source direction based on the sound pressure difference between the first voice data and the second voice data;
estimating, by using the estimated sound source direction, a language from among a plurality of languages each corresponding to a respective individual sound source, the estimated language being a language corresponding to a sound source located in the estimated sound source direction;
outputting an instruction to execute, on at least any one of the first voice data or the second voice data, a voice recognition in the estimated language; and
controlling a reference for estimating a sound source direction based on the sound pressure difference, based on a time length of the voice data used for the voice recognition based on the instruction and a voice recognition time length, wherein
the process of estimating the sound source direction of the first voice data and the second voice data
calculates the sound pressure difference between the first voice data acquired from the first microphone and the second voice data acquired from the second microphone, and
estimates the sound source direction of the first voice data and the second voice data based on a comparison result between a first threshold value for determining the sound source direction of the first voice data and the second voice data, and the sound pressure difference, and
the process of controlling the reference updates the first threshold value when the voice recognition time length with respect to the time length of the voice data used for the voice recognition based on the instruction, is larger than

Assignees

• Fujitsu Ltd

Inventors

• Washio Nobuyuki
• Suzuki Masanao
• Shioda Chisato

Classifications

• G06F40/263

  Language identification · CPC title

• H04R3/005 Primary

  for combining the signals of two or more microphones (specially adapted for hearing aids H04R25/407) · CPC title

• G10L15/00

  Speech recognition (G10L17/00 takes precedence) · CPC title

• G10L25/78

  Detection of presence or absence of voice signals (switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10) · CPC title

• G01S3/801

  Details {(G01S3/82, G01S3/84, G01S3/86 take precedence)} · CPC title