# US 2017/0365257 A1 · Voice control system and method thereof

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

- Number: US 2017/0365257 A1
- Document ID: US20170365257A1
- Status: Published application
- Kind: A1
- Application number: 15/622,455
- Filed: 2017-06-14
- Published: 2017-12-21
- Earliest claimed: 2016-06-15
- Assignees: Realtek Semiconductor Corp.
- Applicants: Realtek Semiconductor Corp.
- Inventors: CHIA-CHIANG LIN; YI-HUAN WANG
- Web page: https://patentgrep.com/patent/US20170365257A1

## CPC

- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 15/08: Speech classification or search
- G10L 19/00: Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis (in musical instruments G10H)
- G10L 25/78: 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)
- G10L 2015/088: {Word spotting}
- G10L 2015/223: {Execution procedure of a spoken command}
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

Disclosed is a voice control system and method thereof. The voice control system is used in an electronic device and works in a sleep mode and a working mode. The voice control system comprises an audio detection module, an audio codec and a control module. Under the sleep mode, the audio detection module continually detects whether there is a wake-up speech in a received first audio data. If yes, the audio detection module generates a first indication signal and temporarily stores the following first audio data. When the control module is woken up by the first indication signal, the voice control system enters the working mode. Under the working mode, the control module drives the audio codec to read and process the temporarily stored first audio data to recognize control speech in the first audio data and to accordingly control the electronic device.

## Claims

### Claim 1

A voice control system, used in an electronic device, operating in a sleep mode and a working mode, comprising:
an audio detection module, in the sleep mode, continually detecting whether there is a wake-up speech in a first audio data received by a microphone, wherein the audio detection module generates a first indication signal when the wake-up speech is detected, and temporarily stores the first audio data detected after the wake-up speech;
an audio codec, connected to the audio detection module; and
a control module, connected to the audio detection module and the audio codec;
wherein the voice control system operates in the working mode after the control module is woken up by the first indication signal, and in the working mode, the control module drives the audio codec to read and process the first audio data temporarily stored in the audio detection module to recognize a control speech and to accordingly control the electronic device.

### Claim 2 (depends on 1)

The voice control system according to claim 1, wherein the audio detection module comprises:
a recognition unit, in the sleep mode, receiving the first audio data and detecting whether there is the wake-up speech in the first audio data;
an indication unit, connected to the recognition unit and the control module; and
a buffer unit, connected to the microphone and the audio codec;
wherein the recognition unit controls the indication unit to generate and transmit the first indication signal to the control module when the wake-up speech is detected, and at the same time the buffer unit temporarily stores the first audio data detected after the wake-up speech.

### Claim 3 (depends on 2)

The voice control system according to claim 2, wherein the control module comprises:
a wake-up unit, connected to the indication unit of the audio detection module; and
a control unit, connected to the wake-up unit;
wherein in the sleep mode, the wake-up unit continually detects whether there is the first indication signal, and the wake-up unit wakes up the control unit when the wake-up unit receives the first indication signal, such that the voice control system starts to operate in the working mode.

### Claim 4 (depends on 3)

The voice control system according to claim 3, wherein the recognition unit comprises a timer, in the working mode, after the timer counts for a predetermined time, the recognition unit controls the indication unit to transmit a second indication signal to the wake-up unit if there is no first audio data detected after the wake-up speech is detected, and the wake-up unit stops the control unit from working according to the second indication signal, such that the voice control system returns to the sleep mode.

### Claim 5 (depends on 3)

The voice control system according to claim 3, wherein the audio codec comprises:
a first audio input unit, connected to the buffer unit of the audio detection module to read the first audio data temporarily stored in the buffer unit; and
a codec unit, connected to the first audio input unit and the control unit of the control module, wherein in the working mode, the control unit drives the codec unit to process the first audio data read by the first audio input unit to recognize the control speech in the first audio data and to accordingly control the electronic device.

### Claim 6 (depends on 5)

The voice control system according to claim 5, wherein the audio codec further comprises an audio output unit and the audio output unit is connected to the audio output unit, and wherein the control module transmits a second audio data to the codec unit and drives the codec unit to process the second audio data, and the audio output unit outputs the processed second audio data to a speaker for playing.

### Claim 7 (depends on 6)

The voice control system according to claim 6, wherein the audio detection module further comprises a sampling and frequency converting unit, the sampling and frequency converting unit is connected between the buffer unit and the audio codec, the sampling and frequency converting unit converts the data format of the second audio data outputted by audio output unit from a second sample rate to a first sample rate, and temporarily stores the second audio data in the buffer as a reference audio data, wherein the data format of the first audio data is the first sample rate and the second sample rate is higher than the first sample rate.

### Claim 8 (depends on 7)

The voice control system according to claim 7, wherein the control module drives the codec unit to read and process the first audio data and the reference audio data temporarily stored in the buffer unit, and the control module processes the processed first audio data according to the processed reference audio data to recognize the control speech in the first audio data and to accordingly control the electronic device.

### Claim 9 (depends on 7)

The voice control system according to claim 7, wherein the recognition unit processes the processed first audio data according to the processed reference audio data and temporarily stores the processed first audio data in the buffer unit, and the processed first audio data is transmitted to the control module through the audio codec to recognize the control speech in the first audio data and to accordingly control the electronic device.

### Claim 10 (depends on 1)

The voice control system according to claim 1, wherein the audio codec comprises a second audio input unit, the second audio input unit is connected to the microphone and the codec unit, after the control module controls the electronic device to enter a calling mode or an audio recording mode, the control module drives the second audio input unit to directly receive the first audio data from the microphone, and the control module processes the processed first audio data after the codec unit processes the first audio data.

### Claim 11

A voice control method, applied to a voice control system, wherein the voice control system operates in a sleep mode and a working mode, and comprises an audio detection module, an audio codec and a control module, the audio codec is connected to the audio detection module, and the control module is connected to the audio codec and the audio detection module, the voice control method comprising:
in the sleep mode, continually detecting whether there is a wake-up speech in a first audio data received by a microphone;
generating a first indication signal when the wake-up speech is detected, and temporarily storing the first audio data detected after the wake-up speech;
waking up the control module by the first indication signal to make the voice control system operate in the working mode; and
in the working mode, driving the audio codec to read and process the first audio data temporarily stored in the audio detection module to recognize a control speech in the first audio data and to accordingly control the electronic device.

### Claim 12 (depends on 11)

The voice control method according to claim 11, after the step of waking up the control module by the first indication signal to make the voice control system operate in the working mode, further comprising:
in the working mode, counting for a predetermined time to determine whether there is the first audio data detected during the predetermined time after the wake-up speech is detected;
storing the first audio data detected after the wake-up speech if there is the first audio data detected during the predetermined time after the wake-up speech is detected; and
transmitting a second indication signal to stop the control unit from working if there is no first audio data detected during the predetermined time after the wake-up speech is detected, such that the voice control system returns to the sleep mode.

### Claim 13 (depends on 11)

The voice control method according to claim 11, further comprising:
transmitting a second audio data to the codec unit for processing and outputting the processed second audio data to a speaker for playing.

### Claim 14 (depends on 13)

The voice control method according to claim 13, further comprising:
converting the data format of the second audio data from a second sample rate to a first sample rate, and temporarily storing the second audio data in the buffer as a reference audio data, wherein the data format of the first audio data is the first sample rate and the second sample rate is higher than the first sample rate.

### Claim 15 (depends on 14)

The voice control method according to claim 14, further comprising:
driving the codec unit to read and process the first audio data and the reference audio data temporarily stored in the buffer unit, and processing the processed first audio data by the control module according to the processed reference audio data to recognize the control speech in the first audio data and to accordingly control the electronic device.

### Claim 16 (depends on 14)

The voice control method according to claim 14, further comprising:
processing the processed first audio data by the audio detection module according to the processed reference audio data and temporarily storing the processed first audio data; and
transmitting the processed first audio data to the control module through the audio codec to recognize the control speech in the first audio data and to accordingly control the electronic device.

### Claim 17 (depends on 11)

The voice control method according to claim 11, after the step of recognizing the control speech in the first audio data and accordingly controlling the electronic device, further comprising:
driving the second audio input unit to directly receive the first audio data from the microphone, and processing the processed first audio data after processing the first audio data, when the electronic device is controlled to enter a calling mode or an audio recording mode.
