KR20190086928A - Apparatus for recognizing call sign and method for the same - Google Patents

Abstract

The present application relates to an apparatus for recognizing ring back tone and a method thereof. According to one embodiment of the present invention, the apparatus may comprise: a voice reception unit receiving voice of a user and converting the voice into a voice signal; a first ring back tone sensing unit determining whether previously set ring back tone is included in the voice signal according to the first sensing characteristics; a second ring back tone sensing unit reexamining whether the ring back tone is included in the voice signal according to the second sensing characteristics if it is determined that the first ring back tone sensing unit includes the ring back tone; and a control unit generating a previously set wake-up signal if it is determined that the second ring back tone sensing unit includes the ring back tone.

Description

[0001] The present invention relates to a ring tone recognition apparatus and a ring tone recognition method,

The present invention relates to a ring tone recognition apparatus and a ring tone recognition method, and more particularly, to a ring tone recognition apparatus and a ring tone recognition method capable of recognizing a user's voice and activating a terminal apparatus and the like.

There are various ways of communication between people, such as writing, gesture, and voice. Especially, voice is one of the most convenient way of communicating people. On the other hand, a communication method between a person and a machine is very limited in terms of input through a keyboard and a mouse, and output through a speaker and a display device for input.

A communication method between a person and a device via voice is being attempted to improve communication between a person and a device. Speech recognition technology is a technique that is prioritized for communication between a person and a device through such voice. In order to communicate through a voice between a person and a device, the device should be able to recognize the voice uttered by the person. Various speech recognition technologies have been studied for this purpose, and they have been applied to various fields such as a mobile communication terminal such as a mobile phone, a control device for a machine, a computer, and a navigation device.

Generally, speech recognition methods such as Hidden Markov Model (HMM) and Dynamic Time Warping (DTW) and artificial neural networks are mainly used.

The present application is intended to provide a ring tone recognition device and a ring tone recognition method capable of recognizing a user's voice and activating a terminal device or the like.

The present application is to provide a ring tone recognition apparatus and a ring tone recognition method capable of discriminating whether or not a user utters a ring tone by using a plurality of ring tone detection units having different sensing characteristics.

In the present application, additional typing verification is performed by another recognizer when recognizing a keyword due to one attempt, and when the user makes two consecutive attempts, the additional verification process is omitted, thereby reducing the false rejection rate without increasing the false acceptance rate It is possible to provide a ring tone recognition device and a ring tone recognition method which can be used.

A ring tone recognizing apparatus according to an embodiment of the present invention includes a voice receiving unit for receiving a voice of a user and converting the voice into a voice signal; A first call sound sensing section for discriminating whether or not a preset ring tone is included in the voice signal according to the first sensing characteristic; A second ringing sound sensing unit for re-inspecting whether or not the ringing tone is included in the voice signal according to a second sensing characteristic when the first ringing tone sensing unit determines that the ringing tone is included; And a controller for generating a predetermined wake-up signal when the second ring tone detector determines that the ring tone is included.

A ring tone recognizing apparatus according to an embodiment of the present invention includes a voice receiving unit for receiving a voice of a user and converting the voice into a voice signal; A first call sound sensing section for discriminating whether or not a preset ring tone is included in the voice signal according to the first sensing characteristic; A second ringing sound sensing unit for determining whether the ringing tone is included in the voice signal according to the second sensing characteristic; And a controller for generating a predetermined wake-up signal based on the detection result of the first ring tone detector, the detection result of the second ring tone detector, and the set retention time. Here, the hold time may be set when the first ring tones detection unit determines that the ring tone is included and determines that the ring tone is not included in the second ring tone detection unit.

A method for recognizing a ring tone according to an embodiment of the present invention includes: receiving a voice of a user and converting the voice into a voice signal; Determining whether or not a predetermined ring tone is included in the voice signal using a first ring tone detector having a first sensing characteristic; Re-inspecting whether or not the ringing tone is included in the voice signal using a second ringing tone sensing part having a second sensing characteristic when the first ringing tone sensing part determines that the ringing tone is included; And a controller generating a predetermined wake-up signal when the second ring tone detector determines that the ring tone is included.

A method for recognizing a ring tone according to an embodiment of the present invention includes: receiving a voice of a user and converting the voice into a voice signal; Determining whether or not a predetermined ring tone is included in the voice signal using a first ring tone detector having a first sensing characteristic; Determining whether the ringing tone is included in the voice signal using a second ringing tone detector having a second sensing characteristic; And generating a predetermined wake-up signal based on the detection result of the first call sound detection unit, the detection result of the second call sound detection unit, and the set pause time. Here, the hold time may be set when the first call sound sensing section determines that the ring tone is included in the voice signal and the second call sound sensing section determines that the ring tone is not included in the voice signal have.

In addition, the means for solving the above-mentioned problems are not all enumerating the features of the present invention. The various features of the present invention and the advantages and effects thereof will be more fully understood by reference to the following specific embodiments.

According to the ring tone recognition apparatus and the ring tone recognition method according to an embodiment of the present invention, a ring tone included in a user's voice is detected using a plurality of ring tone detection units having different sensing characteristics, The recognition rate can be increased.

According to the ring tone recognition apparatus and the ring tone recognition method according to an embodiment of the present invention, when a user utters a continuous ring tone, the terminal apparatus and the like can be activated without further verification as to whether or not the ring tone is detected. That is, it is possible to improve the recognition rate of the user's continuous call attempt even in an environment where it is difficult to recognize a ringing tone that the user has uttered, such as when ambient noise or noise is severe.

According to the ring tone recognition apparatus and the ring tone recognition method according to an embodiment of the present invention, the false rejection rate can be lowered while maintaining the performance of the recognizer having a low false acceptance rate.

However, the effects that can be achieved by the ringing tone recognition apparatus and the ringing tone recognition method according to the embodiments of the present invention are not limited to those described above, and other effects not mentioned can be obtained from the following description It will be understood by those of ordinary skill in the art.

1 is a schematic diagram showing a ring tone recognition apparatus according to an embodiment of the present invention.
2 is a schematic diagram showing the relationship between a false acceptance rate and a false rejection rate in a call sound acceptance section according to an embodiment of the present invention.
3 is a flowchart illustrating a ring tone recognition method according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, wherein like reference numerals are used to designate identical or similar elements, and redundant description thereof will be omitted. The suffix "module" and " part "for the components used in the following description are given or mixed in consideration of ease of specification, and do not have their own meaning or role. That is, the term 'part' used in the present invention means a hardware component such as software, FPGA or ASIC, and 'part' performs certain roles. However, 'minus' is not limited to software or hardware. The " part " may be configured to be in an addressable storage medium and configured to play back one or more processors. Thus, by way of example, and by no means, the terms " component " or " component " means any combination of components, such as software components, object- oriented software components, class components and task components, Subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays and variables. The functions provided in the components and parts may be combined into a smaller number of components and parts or further separated into additional components and parts.

In the following description of the embodiments of the present invention, a detailed description of related arts will be omitted when it is determined that the gist of the embodiments disclosed herein may be blurred. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory and are intended to provide further explanation of the invention as claimed. , ≪ / RTI > equivalents, and alternatives.

1 is a schematic diagram showing a ring tone recognition system according to an embodiment of the present invention.

Referring to FIG. 1, a ring tone recognition system according to an embodiment of the present invention may include a terminal device 1 and a ring tone recognition device 100.

Hereinafter, a ring tone recognition system according to an embodiment of the present invention will be described with reference to FIG.

The terminal device 1 may be various kinds of devices such as a speaker, a display device, a computer, a server, and the like, and may perform an operation corresponding to a command of the user A. Here, the terminal device 1 may be in a standby mode in a power saving mode or a sleep mode, and may be in a sleep mode or a sleep mode according to a wake-up signal transmitted by the ring back tone recognition device 100 It is possible to switch to the active mode.

The ring tone recognizing apparatus 100 can recognize a voice uttered by the user A and can determine whether or not a predetermined ring tone is included in the recognized voice. The ring tone recognizing apparatus 100 can transmit a wake-up signal to the terminal device 1 when it is determined that the ring tone is included in the voice uttered by the user. That is, it is possible to control the terminal device 1 to switch to the operation mode in response to the voice command of the recognized user. Here, the ringing tone may be a preset keyword for converting the terminal device 1 in the sleep mode into the operation mode.

According to the embodiment, it is also possible for the ring tone recognizing apparatus 100 to recognize various commands inputted by the user in addition to the ring tone. That is, the ring tone recognizing apparatus 100 may recognize a command input by the user as a voice, generate a control signal corresponding to each command, and transmit the control signal to the terminal apparatus 1. For example, the ring tone recognizing apparatus 100 can recognize a command for a channel change, a volume control, or the like of a TV which is uttered by a user, and can generate a control signal corresponding to the recognized command and transmit the control signal to the TV. In this case, the TV can perform a channel change, a volume control, and the like in accordance with the received control signal.

Although the terminal device 1 and the ring tone recognition device 100 are separately shown in FIG. 1, the ring tone recognition device 100 may be included in the terminal device 1 according to an embodiment.

1, the ring tone recognizing apparatus 100 may include a voice receiving unit 110, a first call sound sensing unit 110, a second call sound sensing unit 120, and a controller 140.

The voice receiving unit 110 can receive the voice of the user A and convert it into a voice signal. The voice receiving unit 110 may be a microphone or the like and may convert a voice uttered by a user into a voice signal that is an electrical signal. The user's voice corresponds to an analog type signal having a specific frequency and amplitude, and the voice receiving unit 110 can convert the inputted voice into a voice signal, which is a digital signal, through an analog-digital converter (not shown). Here, the voice receiving unit 110 may provide the converted voice signal to the first call sensing unit 120. 1, although the voice receiving unit 110 provides voice signals only to the first call detecting unit 120, the voice receiving unit 110 may also transmit the voice signals to the second call sound detecting unit 130 .

The first call sound sensing unit 120 may determine whether or not a predetermined ringing tone is included in the voice signal according to the first sensing characteristic. Also, if the first call sound sensing unit 120 determines that the ringing tone is included, the second ringing tone sensing unit 130 may re-check whether or not the ringing tone is included in the speech signal according to the second sensing characteristic. That is, the recognition performance of the ringing tones can be improved by determining whether or not the ringing tone is included by using the first ringing tone detector 120 and the second ringing tone detector 130 having different sensing characteristics

Specifically, the first call sound sensing unit 120 may have a first sensing characteristic with a high false acceptance rate (FAR) and a low false rejection rate (FRR), and the second calling sound sensing unit 130 may have a second sensing characteristic with a high false reject rate and a low false accept rate. Here, the false acceptance rate is a rate at which the voice signal does not contain the actual voice but is mistakenly determined to be included, and the false reject rate corresponds to a rate at which the voice signal contains the actual voice but is mistakenly determined to be not included. If the false acceptance rate is high, the terminal device 1 may react to the user regardless of the intention of the user, thereby inconveniencing the user. If the false rejection rate is high, the user does not respond even when the terminal device 1 is called It can cause discomfort.

Here, since the false acceptance rate and the false rejection rate are in trade-off with each other as shown in FIG. 2, it is difficult to satisfy both of the two performances. Accordingly, in this case, it is possible to determine whether or not the ring tone is included in the voice signal by using two ring tone detectors having different detection characteristics. Preferably, the false acceptance rate of the first call sound sensing unit 120 is relatively higher than that of the second call sound sensing unit 130 or the false rejection rate of the first call sound sensing unit 120 is greater than the false acceptance rate of the second call sound sensing unit 130).

Since the first call sound detection unit 120 has a first detection characteristic with a high false acceptance rate, even when the actual ring tone is not included, there is a high probability of discriminating that the ring tone is included. However, since the false rejection rate is low, the first call sound sensing unit 120 can be used to primarily determine a voice signal that may include a ringing tone. Thereafter, using the second ringing tone detector 130 having the second detection characteristic with a high false rejection rate, the first ringing tone detector 120 can re-examine the voice signal that is determined to include the ringing tone. That is, even if the first ringing tone detector 120 determines that a ringing tone is included, the second ringing tone detector 130 may re-examine the ringing tone to determine that the ringing tone is not included. This makes it possible to compensate for the disadvantage of the first call sound sensing unit 120 having a high erroneous acceptance rate.

2, the first call sound sensing unit 120 may have a false acceptance rate FA1 and a false rejection rate FR1, and the second call sound acceptance unit 130 may have a false acceptance rate FA2, and the false rejection rate may be FR2. Here, the false acceptance rate and the false reject rate of each call sound recognizing section can be set according to the graph of FIG. 2. In order to maintain each of the first and second sensing characteristics, at least the false acceptance rate FA1 is FA2 And the false rejection rate FR2 can be selected to be higher than FR1. Although FIG. 2 illustrates only one curve, depending on the implementation method, each ringing tone detector section may have different error curves and select one of them.

The false acceptance rate and false rejection rate of the first call sound sensing unit 120 and the second call sound sensing unit 130 are determined by algorithms applied to the first call sound sensing unit 120 and the second call sound sensing unit 130, Can be determined accordingly.

Hereinafter, some embodiments for making a ringing tone sensing part with different sensing characteristics will be described.

According to one embodiment, the recognition error threshold and the false rejection rate can be adjusted by changing the recognition threshold of the ringing tone detector. Depending on the implementation of the ring tone detection section, a probability value for whether a ring tone other than 0 (false) or 1 (true) is included can be determined as a recognition result. At this time, it is possible to adjust the ratio of the false acceptance rate and the false rejection rate by changing the recognition threshold value for determining whether or not to recognize the probability value.

As a concrete implementation method, the first call sound sensing unit 120 and the second call sound sensing unit 130 can check whether or not a voice tone corresponding to a ringing tone is included from a voice signal to determine whether or not a ringing tone is included , Whether or not the voice waveform corresponding to the ringing tone is included in the voice signal can be calculated as a probability value. If the probability value is greater than or equal to a predetermined threshold probability value, it can be determined that the ringing tone is included. Depending on the setting of the threshold probability value, the detection characteristics of each of the first ringing sound sensing portion 120 and the second ringing sound sensing portion 130 are selected For example, when the threshold probability value is lowered, the false acceptance rate becomes higher, so that it approaches the first sensing characteristic. When the threshold probability value is increased, the false rejection rate becomes higher.

Alternatively, by changing the language model of the ring tone detection section, a ring tone detection section having different sensing characteristics can be created. For example, the respective sensing characteristics may be determined according to the range of the pronunciation variation permitted to be set in the first ringing sound sensing portion 120 and the second ringing sound sensing portion 130, respectively. For example, when "Clover" is a ringing tone, it can be determined that a ringing tone is input when "Clover", "Grove", "Crover" The more the recognition range is widened, the higher the false acceptance rate becomes. However, the more the false recognition rate is narrowed, the higher the false rejection rate. .

Another method is to apply a similarity filter. The pronunciation is similar to the ringing tone to be detected, but the other words are learned in advance to reduce the false acceptance rate by the analogy. That is, when a similar word is included in the voice signal, it can be determined that the voice is not an input of a ringing tone. For example, when "Clover" is a ringing tone, similar words such as "Listen" and "Play" have some similarities but actually have different meanings, so that the user can determine that the ringing tone is not intended to be input have. Therefore, when the similarities are extended and set, the false acceptance rate can be lowered, but the false rejection rate can be increased. If the similarity is narrowed or the similarity filter is not set, the false rejection rate can be lowered, but the false acceptance rate can be increased.

It is also possible to apply an algorithm for detecting the silence included before or after the ringing tone. In general, when a user utters a ringing tone, silence is included. Therefore, it is possible to recognize whether a silence is included in the input voice signal, and to recognize the silence as a ringing tone only when silence is included. In this case, although the false acceptance rate can be greatly reduced, it is difficult to determine whether or not silence is included when a lot of noise, etc. are mixed in the environment in which the user A is uttering. Therefore, have.

On the other hand, according to the embodiment, machine learning or the like can be applied to the first call sound sensing unit 120 and the second call sound sensing unit 130. [ For example, after the voice signal including the ringing tone and the voice signal not including the ringing tone are repeatedly output in various environments, the first ringing tone sensing section 120 and the second ringing tone sensing section 130 can continuously determine have. At this time, the first call sound sensing unit 120 and the second call sound sensing unit 130 can be learned by feeding back the determination result. In this case, it is possible to reduce the erroneous rejection rate in the noisy environment by adding the learning result in the noisy environment to the ringing sound sensing unit 120 or the second ringing sound sensing unit 130.

Therefore, the first ringing sound sensing unit 120 and the second ringing sound sensing unit 130 are applied to the first ringing sound sensing unit 120 and the second ringing sound sensing unit 130, respectively, Characteristic and a second sensing characteristic. The embodiments described above may be used independently, or one or more methods may be used in combination.

The control unit 140 may generate a predetermined wake-up signal when the second ringing tone sensing unit 130 determines that the ringing tone is included. The control unit 140 can transmit the generated wake-up signal to the terminal device 1, and can cause the terminal device 1 to operate in the operation mode in response to the user's ringing tone. That is, the control unit 140 can generate a wake-up signal only when it is determined that the ringing tone is included in both the first ringing sound sensing unit 120 and the second ringing sound sensing unit 130. Thus, it is possible to prevent problems such as the terminal device 1 being operated too frequently in response to user's utterance.

However, if the second ringing tone detector 130 determines that the ringing tone is not included in the voice signal, the controller 140 may set a hold time of a predetermined time interval. That is, since the second call sound detection unit 130 has a high erroneous rejection rate, it is possible to set a hold time and confirm whether or not the user further utters a voice including a ringing tone within the hold time. If the voice receiving unit 110 re-receives the voice of the user within the hold time and the first call sound sensing unit 120 determines that the voice is included in the voice signal corresponding to the voice re-received, the control unit 140 A wake-up signal can be generated. This is because the user repeatedly inputs a ringing tone for the operation of the terminal device 1, so that the second ringing tone detector 130 having a high erroneous rejection rate is skipped and the first ringing tone detector 120, It is possible to generate the wake-up signal only by the discrimination in Fig. Thus, it is possible to improve the recognition rate according to the user's continuous attempt even in an environment where recognition of the ringing tones is difficult. Herein, the retention time may be set to 5 seconds, but the present invention is not limited thereto and can be variously set according to the embodiment.

The control unit 140 may cause the first call sound sensing unit 120 to operate at all times to promptly respond to the input voice signal. That is, the first call sound sensing unit 120 may be operated at all times so that the user can always hear a ringing tone to be uttered. On the other hand, the second call sound sensing unit 130 performs a function of re-examining the discrimination result in the first call sound sensing unit 120, so that even in the first call sound recognizing unit 120 having a low erroneous reject rate, It can be controlled so as not to perform the retest for the voice signal that has been determined to be non-existent. Also, the second ringing tone sensing part 130 can be controlled not to operate even during the hold time.

According to another embodiment of the present invention, the first call sound sensing unit 120 and the second call sound sensing unit 130 may be operated at all times. When the second call sound sensing unit 130 operates after the operation of the first call sound sensing unit 120, an additional time is required for the calculation. Therefore, each call sound sensing unit performs an operation on the input voice signal, It is possible to finally decide whether to include a ringing tone.

The final result can be set to determine the final result in consideration of the sensing characteristics and performance of the first ringing sound sensing portion 120 and the second ringing sound sensing portion 130. For example, the final result may be determined according to whether or not the first call sound sensing unit 120 and the second call sound sensing unit 130 are sensed and within the above-described retention time, as shown in Table 1 below.

First ring tone
The sensing unit Second ringing tone
The sensing unit Is it within hold time Final result Detection Detection irrelevant Include Ringtone Detection Can not detect Yes Include Ringtone NO Do not include ringtone Can not detect Detection irrelevant Include Ringtone Can not detect Can not detect irrelevant Do not include ringtone

3 is a flowchart illustrating a ring tone recognition method according to an embodiment of the present invention.

Referring to FIG. 3, a voice processing unit may receive a voice of a user and convert the voice into a voice signal (S10). Thereafter, it is possible to determine whether or not the voice signal includes a predetermined ringing tone by using the first ringing tone detector having the first sensing characteristic (S20). Here, the first call sound sensing section may have a first sensing characteristic with a high false acceptance rate and a low false rejection rate.

If it is determined that the ringing tone is included in the first ringing tone detector (S30), the second ringing tone detector having the second sensing characteristic may check whether the ringing tone is included in the speech signal (S50). Here, the second call sound sensing section may have a second sensing characteristic with a high false rejection rate and a low false acceptance rate.

If the second ringing tone detector determines that the ringing tone is included in the voice signal (S60), the control unit may generate a predetermined wake-up signal (S70). The wake-up signal generated by the controller can be transmitted to a terminal device or the like, and the sleep mode or the power saving mode terminal device can be switched to an active mode by a wake-up signal.

On the other hand, if the second call sound sensing unit determines that the ring tone is not included in the voice signal (S60), the control unit can set a predetermined hold time (S80). That is, it is possible to check whether the user repeatedly outputs the ringing tone within the hold time. To this end, after setting the retention time (S80), the user can re-receive the voice to generate a voice signal (S10), and the first call sound sensing section determines whether or not the ring back tone is included in the re- (S20). Here, if the first call sound sensing unit determines that the ring tone is included (S30), it can be checked whether the voice signal is received within the hold time (S40). If the received voice signal is within the hold time, the control unit can generate a wake-up signal (S70). That is, when the first call sound sensing section determines that the ring tone is included in the voice re-uttered by the user within the hold time, it is possible to generate the wake-up signal without performing the additional recheck by the second ring tone detector . Through this, the recognition rate according to the user's continuous attempts can be improved.

The present invention is not limited to the above-described embodiments and the accompanying drawings. It will be apparent to those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

1: Terminal device 100: Call tone recognition device
110: voice receiving unit 120: first call sound sensing unit
130: second call sound sensing section 140:

Claims (9)

A voice receiving unit for receiving a voice of a user and converting the voice into a voice signal;
A first call sound sensing section for discriminating whether or not a preset ring tone is included in the voice signal according to the first sensing characteristic;
A second ringing sound sensing unit for re-inspecting whether or not the ringing tone is included in the voice signal according to a second sensing characteristic when the first ringing tone sensing unit determines that the ringing tone is included; And
And a controller for generating a predetermined wake-up signal when the second ringing tone detector determines that the ringing tone is included.
A voice receiving unit for receiving a voice of a user and converting the voice into a voice signal;
A first call sound sensing section for discriminating whether or not a preset ring tone is included in the voice signal according to the first sensing characteristic;
A second ringing sound sensing unit for determining whether the ringing tone is included in the voice signal according to the second sensing characteristic; And
And a controller for generating a predetermined wake-up signal based on the detection result of the first ring tone detector, the detection result of the second ring tone detector, and the set retention time,
Wherein the hold time is set when it is determined that the ring tone is included in the first ring tone detection unit and that the ring tone is not included in the second ring tone detection unit.
3. The method according to claim 1 or 2,
Wherein the first call sound sensing unit has a first sensing characteristic with a high false acceptance rate (FAR) and a low false rejection rate (FRR)
Wherein the second call sound recognizing section has a second sensing characteristic with a high false rejection rate and a low false acceptance rate.
The method of claim 3,
Wherein the first call sound detection section has a first false acceptance rate and a first false rejection rate and the second call sound acceptance section has a second false acceptance rate and a second false rejection rate,
The first erroneous acceptance rate is equal to or greater than the second erroneous acceptance rate, and the second erroneous rejection rate is equal to or greater than the first erroneous rejection rate.
The apparatus of claim 1, wherein the control unit
And sets a hold time when the second call sound sensing unit determines that the ring tone is not included.
6. The apparatus of claim 5, wherein the control unit
Up signal when the first ring sensor section re-receives the user's voice in the retention time and determines that the ring tone is included in the re-received voice.
The method according to claim 6,
Wherein the first call sound sensing section operates at all times,
Wherein the second ringing tone sensing portion does not operate when it corresponds to the retention time or when the first ringing tone sensing portion determines that the ringing tone is not included in the voice signal.
Receiving a voice of a user and converting the voice into a voice signal;
Determining whether or not a predetermined ring tone is included in the voice signal using a first ring tone detector having a first sensing characteristic;
Re-inspecting whether or not the ringing tone is included in the voice signal using a second ringing tone sensing part having a second sensing characteristic when the first ringing tone sensing part determines that the ringing tone is included; And
Wherein the control unit generates a predetermined wake-up signal when the second ringing tone detector determines that the ringing tone is included.
Receiving a voice of a user and converting the voice into a voice signal;
Determining whether or not a predetermined ring tone is included in the voice signal using a first ring tone detector having a first sensing characteristic;
Determining whether the ringing tone is included in the voice signal using a second ringing tone detector having a second sensing characteristic; And
Generating a predetermined wake-up signal based on the detection result of the first ring tone detection section, the detection result of the second ring tone detection section, and the set retention time,
The hold time is set when the first call sound sensing section determines that the call sound is included in the voice signal and the second call sound sensing section determines that the call sound is not included in the voice signal / RTI >

Images