# US 11,310,593 B2 · Voice input device and method for estimation of utterance direction

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

- Number: US 11,310,593 B2
- Document ID: US11310593B2
- Status: Granted
- Kind: B2
- Application number: 16/753,236
- Filed: 2018-09-27
- Published: 2020-10-15
- Granted: 2022-04-19
- Earliest claimed: 2017-10-11
- Assignees: Sony Corporation
- Applicants: Sony Corporation
- Inventors: Kazuya Tateishi; Shusuke Takahashi; Akira Takahashi; Kazuki Ochiai
- Web page: https://patentgrep.com/patent/US11310593B2

## CPC

- H04R 1/406: {microphones}
- G01S 3/8006: {Multi-channel systems specially adapted for direction-finding, i.e. having a single aerial system capable of giving simultaneous indications of the directions of different signals}
- G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback}
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 15/28: Constructional details of speech recognition systems
- G10L 21/0208: Noise filtering
- G10L 25/51: for comparison or discrimination
- H04R 1/028: {associated with devices performing functions other than acoustics, e.g. electric candles}
- H04R 1/323: {for loudspeakers (H04R1/34 and H04R1/40 take precedence)}
- H04R 3/005: {for combining the signals of two or more microphones (specially adapted for hearing aids H04R25/407)}
- H04R 2201/025: Transducer mountings or cabinet supports enabling variable orientation of transducer of cabinet
- H04R 2201/028: Structural combinations of loudspeakers with built-in power amplifiers, e.g. in the same acoustic enclosure (H04R2499/10 takes precedence; Single (sub)woofer with two or more satellite loudspeakers for mid- and high-frequency band reproduction driven via the (sub)woofer H04R2205/026)
- H04R 2201/401: 2D or 3D arrays of transducers
- 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)
- G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

The present technology relates to a voice input device and method that facilitate estimation of an utterance direction. The voice input device includes a fixed part disposed at a predetermined position, a movable part movable with respect to the fixed part, a microphone array attached to the fixed part, an utterance direction estimation unit that estimates an utterance direction on the basis of a voice from an utterer that is input from the microphone array, and a driving unit that drive the movable part according to the estimated utterance direction. The voice input device can be used by installation in, for example, a smart speaker, a voice agent, a robot, and the like.

## Claims

### Claim 1

A voice input device, comprising:
a fixed part configured to be disposed at a determined position;
a movable part movable with respect to the fixed part;
a microphone array attached to the fixed part;
a Central Processing Unit (CPU) configured to:
determine, based on a signal of a voice from an utterer, a first signal having a peak that exceeds a threshold value, wherein the voice is input from the microphone array;
estimate a horizontal angle corresponding to the determined first signal having the peak that exceeds the threshold value as a first horizontal angle in an utterance direction;
calculate a second signal at a horizontal angle and an elevation angle within a range of the first horizontal angle;
detect a peak value of the second signal for the horizontal angle and the elevation angle within the range of the first horizontal angle; and
estimate a direction corresponding to the peak value of the second signal as the utterance direction of the voice from the utterer; and
a driving unit configured to drive the movable part based on the estimated utterance direction.

### Claim 2 (depends on 1)

The voice input device according to claim 1, wherein
the CPU is further configured to:
recognize the voice from the utterer, wherein the voice is input from the microphone array; and
control a front driving unit based on a result of the recognition of the voice from the utterer.

### Claim 3 (depends on 2)

The voice input device according to claim 2, wherein the CPU is further configured to recognize the voice from the utterer based on an internal voice recognition engine or an external voice recognition engine connected to the voice input device.

### Claim 4 (depends on 1)

The voice input device according to claim 1, wherein the microphone array includes a plurality of microphones arranged in a plane.

### Claim 5 (depends on 1)

The voice input device according to claim 1, wherein the movable part is symmetric with respect to a rotation center.

### Claim 6

A voice input method of a voice input device, the voice input method comprising:
determining, based on a signal of a voice from an utterer, a first signal having a peak that exceeds a threshold value, wherein
the voice is input from a microphone array attached to a fixed part of the voice input device,
the fixed part is configured to be disposed at a determined position, and
a movable part is movable with respect to the fixed part;
estimating a horizontal angle corresponding to the determined first signal having the peak that exceeds the threshold value as a first horizontal angle in an utterance direction;
calculating a second signal at a horizontal angle and an elevation angle within a range of the first horizontal angle;
detecting a peak value of the second signal for the horizontal angle and the elevation angle within the range of the first horizontal angle;
estimating a direction corresponding to the peak value of the second signal as the utterance direction of the voice from the utterer; and
driving the movable part based on the estimated utterance direction.

### Claim 7

A non-transitory computer-readable medium having stored thereon computer-executable instructions, that when executed by a processor, cause the processor to execute operations, the operations comprising:
determining, based on a signal of a voice from an utterer, a first signal having a peak that exceeds a threshold value, wherein
the voice is input from a microphone array attached to a fixed part of a voice input device,
the fixed part is configured to be disposed at a determined position, and
a movable part is movable with respect to the fixed part;
estimating a horizontal angle corresponding to the determined first signal having the peak that exceeds the threshold value as a first horizontal angle in an utterance direction;
calculating a second signal at a horizontal angle and an elevation angle within a range of the first horizontal angle;
detecting a peak value of the second signal for the horizontal angle and the elevation angle within the range of the first horizontal angle;
estimating a direction corresponding to the peak value of the second signal as the utterance direction the voice from the utterer; and
driving the movable part based on the estimated utterance direction.