# US 2023/0402049 A1 · Microphone system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0402049 A1
- Document ID: US20230402049A1
- Status: Published application
- Kind: A1
- Application number: 18/320,656
- Filed: 2023-05-19
- Published: 2023-12-14
- Earliest claimed: 2022-06-09
- Assignees: Denso Corporation; Toyota Jidosha Kabushiki Kaisha; MIRISE Technologies Corporation
- Applicants: Denso Corporation; Toyota Jidosha Kabushiki Kaisha; MIRISE Technologies Corporation
- Inventors: Tomoki TANEMURA; Takashi TAKAZAWA; Yoshinori TSUCHIYA; Masaaki KAWAUCHI
- Web page: https://patentgrep.com/patent/US20230402049A1

## CPC

- G10L 21/0216: characterised by the method used for estimating noise
- G10L 21/0224: Processing in the time domain
- G10L 25/51: for comparison or discrimination
- G10L 25/84: for discriminating voice from noise
- H04R 1/406: {microphones}
- H04R 3/005: {for combining the signals of two or more microphones (specially adapted for hearing aids H04R25/407)}
- G10L 2021/02082: {the noise being echo, reverberation of the speech}
- G10L 2021/02166: {Microphone arrays; Beamforming}
- H04R 2410/01: Noise reduction using microphones having different directional characteristics
- H04R 2499/13: Acoustic transducers and sound field adaptation in vehicles
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- H04R: LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS (producing sounds with frequency not determined by supply frequency G10K)

## Abstract

A microphone system causes a microphone disposed in an acoustic space to collect sound, classifies a sound included in a sound data related to the sound collected by the microphone into a type of speech sound of a human present in the acoustic space and a type of noise that is a sound other than the speech sound based on a value related to a reflection sound reflected in the acoustic space, and outputs data related to the classified speech sound to a speech recognition device.

## Claims

### Claim 1

A microphone system comprising:
a sound collection unit configured to cause a microphone disposed in an acoustic space to collect a sound;
a clustering unit configured to classify a sound included in a sound data related to the sound collected by the microphone into a type of speech sound of a human present in the acoustic space and a type of noise that is a sound other than the speech sound, based on a value related to a reflection sound reflected in the acoustic space; and
an output unit configured to output data related to the classified speech sound to a speech recognition device.

### Claim 2 (depends on 1)

The microphone system according to claim 1, further comprising:
a calculation unit configured to calculate a transfer function that is a value related to a ratio of an amplitude of a collected reference sound to an amplitude of a reference sound, the collected reference sound being a sound collected by the microphone when the reference sound is generated, wherein
the clustering unit is configured to classify the sound using the value related to the reflection sound reflected in the acoustic space and a reflection threshold value, and
the clustering unit is configured to correct the reflection threshold value based on the transfer function so as to increase a signal-to-noise ratio of the classified speech sound to be larger than that before the reflection threshold value is corrected.

### Claim 3 (depends on 1)

The microphone system according to claim 1, further comprising:
a calculation unit configured to calculate a transfer function that is a value based on an occupant position in a vehicle cabin of the vehicle, a number of occupant in the vehicle cabin, and an opening degree of a side window of the vehicle, wherein
the clustering unit is configured to classify the sound using the value related to the reflection sound reflected in the acoustic space and a reflection threshold value, and
the clustering unit is configured to correct the reflection threshold value based on the transfer function so as to increase a signal-to-noise ratio of the classified speech sound to be larger than that before the reflection threshold value is corrected.

### Claim 4 (depends on 1)

The microphone system according to claim 1, wherein
the clustering unit is configured to classify the sound using the value related to the reflection sound reflected in the acoustic space and a reflection threshold value, and
the clustering unit is configured to correct the reflection threshold value based on a position of the microphone so as to increase a signal-to-noise ratio of the classified speech sound to be larger than that before the reflection threshold value is corrected.

### Claim 5 (depends on 1)

The microphone system according to claim 1, wherein
the clustering unit is configured to classify the sound included in the sound data into the type of speech sound and the type of noise based on a value related to an arrival time difference of sounds, which are other than the speech sound, generated in the acoustic space and arrived at a same microphone.

### Claim 6 (depends on 5)

The microphone system according to claim 5, further comprising:
a calculation unit configured to calculate a transfer function that is a value related to a ratio of an amplitude of a collected reference sound to an amplitude of a reference sound, the collected reference sound being a sound collected by the microphone when the reference sound is generated, wherein
the clustering unit is configured to classify the sound using the value related to the arrival time difference and a time difference threshold value, and
the clustering unit is configured to correct the time difference threshold value based on the transfer function so as to increase a signal-to-noise ratio of the classified speech sound to be larger than that before the time difference threshold value is corrected.

### Claim 7 (depends on 5)

The microphone system according to claim 5, further comprising:
a calculation unit configured to calculate a transfer function that is a value based on an occupant position in a vehicle cabin of the vehicle, a number of occupant in the vehicle cabin, and an opening degree of a side window of the vehicle, wherein
the clustering unit is configured to classify the sound using the value related to the arrival time difference and a time difference threshold value, and
the clustering unit is configured to correct the time difference threshold value based on the transfer function so as to increase a signal-to-noise ratio of the classified speech sound to be larger than that before the time difference threshold value is corrected.

### Claim 8 (depends on 5)

The microphone system according to claim 5, wherein
the clustering unit is configured to classify the sound using the value related to the arrival time difference and a time difference threshold value, and
the clustering unit is configured to correct the time difference threshold value based on a position of the microphone so as to increase a signal-to-noise ratio of the classified speech sound to be larger than that before the time difference threshold value is corrected.

### Claim 9 (depends on 1)

The microphone system according to claim 1, wherein
the clustering unit is configured to classify the sound included in the sound data into the type of speech sound and the type of noise based on a value related to a sound pressure of the sound data.

### Claim 10 (depends on 9)

The microphone system according to claim 9, further comprising:
a calculation unit configured to calculate a transfer function that is a value related to a ratio of an amplitude of a collected reference sound to an amplitude of a reference sound, the collected reference sound being a sound collected by the microphone when the reference sound is generated, wherein
the clustering unit is configured to classify the sound using the value related to the sound pressure of the sound data and a sound pressure threshold value, and
the clustering unit is configured to correct the sound pressure threshold value based on the transfer function so as to increase a signal-to-noise ratio of the classified speech sound to be larger than that before the sound pressure threshold value is corrected.

### Claim 11 (depends on 9)

The microphone system according to claim 9, further comprising:
a calculation unit configured to calculate a transfer function that is a value based on an occupant position in a vehicle cabin of the vehicle, a number of occupant in the vehicle cabin, and an opening degree of a side window of the vehicle, wherein
the clustering unit is configured to classify the sound using the value related to the sound pressure of the sound data and a sound pressure threshold value, and
the clustering unit is configured to correct the sound pressure threshold value based on the transfer function so as to increase a signal-to-noise ratio of the classified speech sound to be larger than that before the sound pressure threshold value is corrected.

### Claim 12 (depends on 9)

The microphone system according to claim 9, wherein
the clustering unit is configured to classify the sound using the value related to the sound pressure of the sound data and a sound pressure threshold value, and
the clustering unit is configured to correct the sound pressure threshold value based on a position of the microphone so as to increase a signal-to-noise ratio of the classified speech sound to be larger than that before the sound pressure threshold value is corrected.

### Claim 13 (depends on 1)

The microphone system according to claim 1, wherein
the clustering unit is configured to classify the sound into the type of speech sound and the type of noise based on a value related to an utterance pitch that is an interval between notes of utterance by the human.

### Claim 14 (depends on 13)

The microphone system according to claim 13, further comprising:
a calculation unit configured to calculate a transfer function that is a value related to a ratio of an amplitude of a collected reference sound to an amplitude of a reference sound, the collected reference sound being a sound collected by the microphone when the reference sound is generated, wherein
the clustering unit is configured to classify the sound using the value related to the utterance pitch and a pitch threshold value, and
the clustering unit is configured to correct the pitch threshold value based on the transfer function so as to increase a signal-to-noise ratio of the classified speech sound to be larger than that before the pitch threshold value is corrected.

### Claim 15 (depends on 13)

The microphone system according to claim 13, further comprising:
a calculation unit configured to calculate a transfer function that is a value based on an occupant position in a vehicle cabin of the vehicle, a number of occupant in the vehicle cabin, and an opening degree of a side window of the vehicle, wherein
the clustering unit is configured to classify the sound into the type of speech sound and the type of noise using the value related to the utterance pitch and a pitch threshold value, and
the clustering unit is configured to correct the pitch threshold value based on the transfer function so as to increase a signal-to-noise ratio of the classified speech sound to be larger than that before the pitch threshold value is corrected.

### Claim 16 (depends on 13)

The microphone system according to claim 13, wherein
the clustering unit is configured to classify the sound using the value related to the utterance pitch and a pitch threshold value, and
the clustering unit is configured to correct the pitch threshold value based on a position of the microphone so as to increase a signal-to-noise ratio of the classified speech sound to be larger than that before the pitch threshold value is corrected.

### Claim 17 (depends on 1)

The microphone system according to claim 1, wherein
the microphone is one of a plurality of microphones, and
the clustering unit is configured to classify the sound included in the sound data into the type of speech sound and the type of noise based on a value related to an arrival time difference of the speech sound between at least two of the plurality of microphones.

### Claim 18 (depends on 17)

The microphone system according to claim 17, further comprising:
a calculation unit configured to calculate a transfer function that is a value related to a ratio of an amplitude of a collected reference sound to an amplitude of a reference sound, the collected reference sound being a sound collected by the microphone when the reference sound is generated, wherein
the clustering unit is configured to classify the sound using the value related to the arrival time difference and an utterance threshold value, and
the clustering unit is configured to correct the utterance threshold value based on the transfer function so as to increase a signal-to-noise ratio of the classified speech sound to be larger than that before the utterance threshold value is corrected.

### Claim 19 (depends on 17)

The microphone system according to claim 17, further comprising:
a calculation unit configured to calculate a transfer function that is a value based on an occupant position in a vehicle cabin of the vehicle, a number of occupant in the vehicle cabin, and an opening degree of a side window of the vehicle, wherein
the clustering unit is configured to classify the sound using the value related to the arrival time difference and an utterance threshold value, and
the clustering unit is configured to correct the utterance threshold value based on the transfer function so as to increase a signal-to-noise ratio of the classified speech sound to be larger than that before the utterance threshold value is corrected.

### Claim 20 (depends on 17)

The microphone system according to claim 17, wherein
the clustering unit is configured to classify the sound using the value related to the arrival time difference and an utterance threshold value, and
the clustering unit is configured to correct the utterance threshold value based on a position of the microphone so as to increase a signal-to-noise ratio of the classified speech sound to be larger than that before the utterance threshold value is corrected.

### Claim 21 (depends on 1)

The microphone system according to claim 1, wherein
the clustering unit is configured to classify the sound into the type of speech sound and the type of noise based on a value related to a frequency component of the sound data.

### Claim 22 (depends on 21)

The microphone system according to claim 21, further comprising:
a calculation unit configured to calculate a transfer function that is a value related to a ratio of an amplitude of a collected reference sound to an amplitude of a reference sound, the collected reference sound being a sound collected by the microphone when the reference sound is generated, wherein
the clustering unit is configured to classify the sound using the value related to the frequency component and a frequency threshold value, and
the clustering unit is configured to correct the frequency threshold value based on the transfer function so as to increase a signal-to-noise ratio of the classified speech sound to be larger than that before the frequency threshold value is corrected.

### Claim 23 (depends on 21)

The microphone system according to claim 21, further comprising:
a calculation unit configured to calculate a transfer function that is a value based on an occupant position in a vehicle cabin of the vehicle, a number of occupant in the vehicle cabin, and an opening degree of a side window of the vehicle, wherein
the clustering unit is configured to classify the sound using the value related to the frequency component and a frequency threshold value, and
the clustering unit is configured to correct the frequency threshold value based on the transfer function so as to increase a signal-to-noise ratio of the classified speech sound to be larger than that before the frequency threshold value is corrected.

### Claim 24 (depends on 21)

The microphone system according to claim 21, wherein
the clustering unit is configured to classify the sound using the value related to the frequency component and a frequency threshold value, and
the clustering unit is configured to correct the frequency threshold value based on the position of the microphone so as to increase a signal-to-noise ratio of the classified speech sound to be larger than that before the frequency threshold value is corrected.

### Claim 25 (depends on 1)

The microphone system according to claim 1, wherein
the clustering unit is configured to classify the sound included in the sound data into the type of speech sound and the type of noise based on a state of an audio of the vehicle, a state of an air conditioner of the vehicle, a speed of the vehicle, and a state of a road surface on which the vehicle travels.

### Claim 26 (depends on 1)

The microphone system according to claim 1, further comprising:
a changing unit configured to change a number of the microphone used to collect the sound to be larger than that of a current number, in response to a value related to a signal-to-noise ratio of the classified speech sound being less than a threshold value, so as to increase the signal-to-noise ratio of the classified speech sound to be larger than that before the number of microphone is increased.

### Claim 27 (depends on 26)

The microphone system according to claim 26, wherein
the changing unit is configured to change a number of increase in the microphone used to collect the sound according to a value related to a number of the type of noise.

### Claim 28 (depends on 26)

The microphone system according to claim 26, wherein
the changing unit is configured to change a number of increase in the microphone used to collect the sound according to a value related to a sound pressure of the noise.

### Claim 29 (depends on 26)

The microphone system according to claim 26, wherein
the changing unit is configured to change a number of increase in the microphone used to collect the sound according to a value related to a sound pressure of the speech sound.

### Claim 30 (depends on 2)

The microphone system according to claim 2, wherein
the reference sound is an ultrasonic wave having a frequency of 20 kHz or more.

### Claim 31 (depends on 3)

The microphone system according to claim 3, further comprising:
an estimation unit configured to estimate the occupant position and the number of occupant based on a value related to transmission and reception of ultrasonic waves having a frequency of 20 kHz or more.

### Claim 32 (depends on 1)

The microphone system according to claim 1, wherein
the clustering unit is configured to estimate the value related to the reflection sound reflected in the acoustic space based on the sound data, a size of the acoustic space, a position of an object in the acoustic space, and a size of the object in the acoustic space.

### Claim 33

A microphone system comprising:
a processor and a memory configured
to cause a microphone disposed in an acoustic space to collect a sound;
to classify a sound included in a sound data related to the sound collected by the microphone into a type of speech sound of a human present in the acoustic space and a type of noise that is a sound other than the speech sound, based on a value related to a reflection sound reflected in the acoustic space; and
to output data related to the classified speech sound to a speech recognition device.
