KR-102962179-B1 - VOICE PROCESSING DEVICE AND OPERATING METHOD OF THE SAME

KR102962179B1KR 102962179 B1KR102962179 B1KR 102962179B1KR-102962179-B1

Abstract

A voice processing device is disclosed. The voice processing device includes a voice data receiving circuit configured to receive input voice data associated with a speaker's voice, a wireless signal receiving circuit configured to receive a wireless signal including a terminal ID from a speaker's terminal, a memory, and a processor configured to generate terminal location data indicating the location of a speaker's terminal based on the wireless signal, and to match the generated terminal location data with a terminal ID and store it in memory. The processor generates first speaker location data indicating a first location and first output voice data associated with a first voice uttered at the first location using the input voice data, reads a first terminal ID corresponding to the first speaker location data by referencing the memory, and matches the first terminal ID with the first output voice data and stores it.

Inventors

김정민

Assignees

주식회사 아모센스

Dates

Publication Date: 20260511
Application Date: 20200821

Claims (10)

A voice data receiving circuit configured to receive input voice data associated with the speaker's voice; A wireless signal receiving circuit configured to receive a wireless signal including a terminal ID from the speaker's terminal; Memory; and The processor includes a device configured to generate terminal location data indicating the location of the speaker terminal based on the wireless signal, and to match the generated terminal location data with the terminal ID and store it in the memory. The above processor is, Using the above input voice data, first speaker location data representing a first location and first output voice data associated with a first voice uttered at the first location are generated, and By referring to the memory above, first terminal location data representing a location adjacent to the first speaker location data among the terminal location data is determined, and Referring to the memory above, read the first terminal ID stored among the terminal IDs that is matched with the first terminal location data, and Storing the first terminal ID and the first output voice data by matching them, Voice processing device.
In paragraph 1, The above input voice data is generated from voice signals generated by a plurality of microphones, Voice processing device.
In paragraph 2, the processor is, Generating the first speaker location data based on the distance between the plurality of microphones and the time at which the voice signal is received by the plurality of microphones. Voice processing device.
In paragraph 1, the processor is, Generating terminal location data indicating the location of the speaker terminal based on the reception strength of the wireless signal, Voice processing device.
In paragraph 1, the processor is, Calculate the time of flight of the wireless signal using a time stamp included in the wireless signal, and generate terminal location data indicating the location of the speaker terminal based on the time of flight. Voice processing device.
delete
In paragraph 1, the processor is, Using the above input voice data, second speaker location data representing a second location and second output voice data associated with a second voice uttered at the second location are generated. Referring to the memory above, read the second terminal ID among the terminal IDs that corresponds to the second speaker location data, and Storing the second terminal ID and the second output voice data by matching them, Voice processing device.
In a method of operating a voice processing device, A step of receiving input voice data associated with the speaker's voice; A step of receiving a wireless signal including a terminal ID from the speaker's terminal; A step of generating terminal location data indicating the location of the speaker terminal based on the above wireless signal; A step of matching and storing the generated terminal location data with the terminal ID; A step of generating first speaker location data representing a first location and first output voice data associated with a first voice uttered at the first location using the above input voice data; A step of reading a first terminal ID corresponding to the first speaker location data among the stored terminal IDs; and The method includes the step of matching and storing the first terminal ID and the first output voice data, The step of reading a first terminal ID corresponding to the first speaker location data is: A step of determining first terminal location data representing a location adjacent to the first speaker location data among the stored terminal location data; and A step comprising reading a first terminal ID stored among the above-mentioned stored terminal IDs that is matched with the first terminal location data. Method of operation of a voice processing device.
In paragraph 8, the step of receiving the input voice data is, A step of receiving voice signals from a plurality of microphones; and A step comprising obtaining the input voice data by converting the received voice signals to analog-to-digital (ADC), Method of operation of a voice processing device.
In paragraph 8, the method of operating the voice processing device is, A step of generating second speaker location data representing a second location and second output voice data associated with a second voice uttered at the second location, using the above input voice data; A step of reading a second terminal ID corresponding to the second speaker location data among the terminal IDs; and A method further comprising the step of matching and storing the second terminal ID and the second output voice data. Method of operation of a voice processing device.

Description

Voice Processing Device and Method of Operating the Voice Processing Device Embodiments of the present invention relate to a voice processing device and a method of operating the voice processing device. A microphone is a device that recognizes speech and converts the recognized speech into an electrical signal called a voice signal. When a microphone is placed in a space where multiple speakers are present, such as a conference room or classroom, the microphone receives speech from all of them and generates voice signals associated with their voices. Therefore, when multiple speakers speak simultaneously, it is necessary to separate their voice signals. Furthermore, it is necessary to identify which speaker each separated voice signal is from. FIG. 1 shows a voice processing system according to embodiments of the present invention. FIG. 2 shows a voice processing device according to embodiments of the present invention. FIG. 3 is a flowchart illustrating the operation method of a voice processing device according to embodiments of the present invention. FIGS. 4 to 6 are drawings for explaining the operation of a voice processing device according to embodiments of the present invention. FIG. 7 is a flowchart illustrating the operation of a voice processing device according to embodiments of the present invention. FIGS. 8 to 10 are drawings for explaining the operation of a voice processing device according to embodiments of the present invention. FIG. 11 is a drawing for explaining the operation of a voice processing device according to embodiments of the present invention. Hereinafter, embodiments of the present invention will be described with reference to the attached drawings. FIG. 1 illustrates a voice processing system according to embodiments of the present invention. Referring to FIG. 1, a voice processing system (10) according to embodiments of the present invention receives the voice of speakers (SPK1 to SPK4) and can separate voice data corresponding to the voice of speakers (SPK1 to SPK4) by speaker. According to embodiments, the voice processing system (10) can determine the location of speakers (SPK1 to SPK4) based on the voice of speakers (SPK1 to SPK4) and separate voice data by speakers (SPK1 to SPK4) based on the determined location. The voice processing system (10) may include speaker terminals (ST1~ST4) of speakers (SPK1~SPK4), a plurality of microphones (100-1~100-n (n is a natural number); collectively 100) configured to receive the voice of speakers (SPK1~SPK4), and a voice processing device (200). Speakers (SPK1~SPK4) may be located at each position (P1~P4). According to embodiments, speakers (SPK1~SPK4) located at each position (P1~P4) may pronounce a sound. For example, a first speaker (SPK1) located at the first position (P1) may pronounce a first sound, a second speaker (SPK2) located at the second position (P2) may pronounce a second sound, a third speaker (SPK3) located at the third position (P3) may pronounce a third sound, and a fourth speaker (SPK4) located at the fourth position (P4) may pronounce a fourth sound. Meanwhile, the embodiments of the present invention are not limited to the number of speakers. Speaker terminals (ST1~ST4) corresponding to each speaker (SPK1~SPK4) can transmit a wireless signal. According to embodiments, speaker terminals (ST1~ST4) can transmit a wireless signal including a terminal ID for identifying each speaker terminal (ST1~ST4). For example, speaker terminals (ST1~ST4) can transmit a wireless signal according to a wireless communication method such as ZigBee, Wi-Fi, BLE (Bluetooth Low Energy), or UWB (Ultra-Wideband). As described below, wireless signals transmitted from speaker terminals (ST1~ST4) can be used to calculate the location of speaker terminals (ST1~ST4). The voices of speakers (SPK1~SPK4) can be received by multiple microphones (100). The multiple microphones (100) can be placed in a space where the voices of speakers (SPK1~SPK4) can be received. A plurality of microphones (100) can generate voice signals (VS1 to VSn) associated with voice. According to embodiments, each of the plurality of microphones (100) can measure a pressure change of a medium (e.g., air) caused by voice, generate voice signals (VS1 to VSn) which are electrical signals based on the measured pressure change of the medium, and output the generated voice signals (VS1 to VSn). A plurality of microphones (100) can receive the voice of speakers (SPK1~SPK4) located at each position (P1~P4) and convert the voice of the speakers (SPK1~SPK4) into voice signals (VS1~VSn) which are electrical signals. For example, a first microphone (100-1) can receive the voice of speakers (SPK1~SPK4) and generate a first voice signal (VS1) associated with the voice of speakers (SPK1~SPK4). The first voice signal (VS1) generated by the first microphone (100-1) can correspond to the voice of at least one speaker (SPK1~SPK4). A plurality of microphones (100) can output voice signals (V