KR20200003529A - Digital device for recognizing voice and method for controlling the same - Google Patents

Abstract

The present invention relates to a digital device capable of recognizing a voice. According to one embodiment of the present invention, the digital device comprises: a memory; a microphone receiving an audio signal of a first language; and a controller controlling the memory and microphone. More especially, the controller translates the received audio signal of the first language into a text of a predetermined second language by referring the memory, retranslates the translated text of the second language with the first language by referring the memory, compares the retranslated text of the first language with the received audio signal of the first language, and modifying some or all of the translated text of the second language and then converting the modified text of the second language into a format, which may be outputted in an audio signal, according to the comparison result.

Description

Digital device capable of speech recognition and its control method {DIGITAL DEVICE FOR RECOGNIZING VOICE AND METHOD FOR CONTROLLING THE SAME}

The present invention relates to a digital device capable of speech recognition, and is applicable to, for example, a portable audio device such as a headset, a neckband, or a mobile device such as a mobile phone.

Recently, mobile devices, TVs, and wearable devices capable of speech recognition have emerged. Technological evolution of servers and speech recognition engines has resulted in significantly higher speech recognition rates than long ago.

However, in the case of providing translation services in different languages, there are still many errors in the speech recognition based translation services due to special differences in various languages.

Accordingly, an embodiment of the present invention is to propose a technique for fundamentally eliminating errors in speech recognition and translation when translating audio of a first language into a second language and outputting the same through a speaker.

Furthermore, another embodiment of the present invention is to propose a technique for detecting not only the text of a language but also the state information of a user who speaks through a speech recognition engine.

The objects of the present invention are not limited to the above-mentioned objects, and other objects that are not mentioned will be clearly understood by those skilled in the art from the following description.

In order to solve the above problems, the control method of the digital device capable of speech recognition according to an embodiment of the present invention, the step of receiving an audio signal of a first language, with reference to a memory, the received first Translating an audio signal of a language into text of a second predetermined language; retranslating the translated second language text into the first language with reference to the memory; and Comparing text with an audio signal of the received first language, and converting a part or all of the text of the translated second language into a format that can be output as an audio signal according to the comparison result It includes.

The comparing may include displaying different portions of the same and different portions when the text of the retranslated first language and the audio signal of the received first language are different, and user selection or data stored in a memory of the digital device. The method further includes providing an option for automatically modifying the other portion accordingly.

The receiving may further include extracting feature points of the audio signal of the first language, wherein the feature points include at least one of stress, intonation, voice, and volume.

The converting may further include outputting the translated second language text in different accent, intonation, voice, or volume according to a feature point extracted from the audio signal of the first language.

The first language and the second language are different from each other, and the digital device includes at least one of a wearable device and a mobile device.

A digital device capable of speech recognition according to an embodiment of the present invention includes a memory, a microphone for receiving an audio signal of a first language, and a controller for controlling the memory and the microphone.

The controller may be configured to translate the received audio signal of the first language into text of a second predetermined language by referring to the memory, and to translate the text of the translated second language into the first language by referring to the memory. Retranslate into a second language, compare the text of the retranslated first language with the audio signal of the received first language, and modify some or all of the text of the translated second language according to the comparison result. And converting it into a format that can be output as a signal.

When the text of the retranslated first language and the audio signal of the received first language are different, the digital device displays the same part and a different part differently, and displays the user part or data stored in the memory of the digital device. The display module may further include a display module configured to automatically display an option for automatically modifying the other part.

The controller extracts a feature point of the audio signal of the first language, and the feature point includes at least one of stress, intonation, voice, and volume.

The controller may be configured to control the speaker to output the translated text of the second language in another accent, intonation, voice, or volume according to a feature point extracted from the audio signal of the first language.

Specific details of other embodiments are included in the detailed description and the drawings.

According to an embodiment of the present invention, there are one or more of the following effects.

First, according to one embodiment of the present invention, when the audio of the first language is translated into a second language and output through a speaker, there is a technical effect of fundamentally eliminating errors in speech recognition and translation.

Furthermore, according to another embodiment of the present invention, there is a technical effect that can detect not only a text of a language but also state information of a user who speaks through a speech recognition engine.

The effects of the present invention are not limited to the above-mentioned effects, and other effects not mentioned will be clearly understood by those skilled in the art from the description of the claims.

1 is a block diagram illustrating a portable audio device as an example of a digital device according to an embodiment of the present invention.
2 is a perspective view of a portable audio device as an example of a digital device according to an embodiment of the present invention.
3 is an exploded perspective view of a portable audio device as an example of a digital device according to an embodiment of the present invention.
4 illustrates a process in which a digital device corrects an error through a first translation / second translation or the like according to an embodiment of the present invention.
Fig. 5 shows a detailed flowchart of the digital device performing post-interpretation correction according to an embodiment of the present invention.
6 illustrates a process in which a digital device executes N to N interpretation according to an embodiment of the present invention.
7 illustrates a scenario in which a digital device according to another embodiment of the present invention masks a voice / emotion of a talker.
FIG. 8 shows a flow chart embodying the scenario shown in FIG. 7 in more detail.
FIG. 9 is a block diagram showing the main configuration of the digital device shown in FIGS. 1 to 8.

Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings, and the same or similar components are denoted by the same reference numerals regardless of the reference numerals, and redundant description thereof will be omitted. The suffixes "module" and "unit" for components used in the following description are given or used in consideration of ease of specification, and do not have distinct meanings or roles from each other. In addition, in describing the embodiments disclosed herein, when it is determined that the detailed description of the related known technology may obscure the gist of the embodiments disclosed herein, the detailed description thereof will be omitted. In addition, the accompanying drawings are intended to facilitate understanding of the embodiments disclosed herein, but are not limited to the technical spirit disclosed in the present specification by the accompanying drawings, all changes included in the spirit and scope of the present invention. It should be understood to include equivalents and substitutes.

Terms including ordinal numbers such as first and second may be used to describe various components, but the components are not limited by the terms. The terms are used only for the purpose of distinguishing one component from another.

When a component is referred to as being "connected" or "connected" to another component, it may be directly connected to or connected to that other component, but it may be understood that other components may be present in between. Should be. On the other hand, when a component is said to be "directly connected" or "directly connected" to another component, it should be understood that there is no other component in between.

Singular expressions include plural expressions unless the context clearly indicates otherwise.

In this application, the terms "comprises" or "having" are intended to indicate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, and one or more other features. It is to be understood that the present invention does not exclude the possibility of the presence or the addition of numbers, steps, operations, components, components, or a combination thereof.

1 is a block diagram illustrating a portable audio device as an example of a digital device according to an embodiment of the present invention. The portable audio device 100 includes a wireless communication unit 110, an input unit 120, a sensing unit 130, an output unit 140, an interface unit 150, a controller 160, a power supply unit 170, and the like. can do.

The portable acoustic apparatus refers to a device that receives a sound signal from a terminal (for example, a mobile phone) and transmits sound information collected through a microphone to the terminal. Conventionally, a portable audio device is connected to a terminal jack of a terminal using a wired method for receiving an acoustic signal, but recently, a portable communication device of a wireless communication method has also been commercialized.

More specifically, various portable audio devices have been developed in consideration of portability, such as a headphone type that fits in a band shape on the head, a type that hangs on the ear, and a type that fits in the ear so as to be carried on a user's body. In particular, there is a recent trend of increasing the number of neck-back portable sound devices that can be worn on the user's neck. 1 illustrates this.

The components shown in FIG. 1 are not essential to implementing a portable audio device, so the portable audio device described herein may have more or fewer components than those listed above.

More specifically, the wireless communication unit 110 of the components between the portable sound device 100 and the wireless communication system, between the portable sound device 100 and another mobile terminal, or between the portable sound device 100 and an external server It may include one or more modules to enable wireless communication of. In addition, the wireless communication unit 110 may include one or more modules for connecting the portable audio device 100 to one or more networks.

The wireless communication unit 110 may include at least one of the short range communication module 111 and the location information module 112. Or it may include a mobile communication module or a wireless Internet module, if necessary.

The short range communication module 111 is for short range communication, and includes Bluetooth ™, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wideband (UWB), ZigBee, NFC (Near Field Communication), at least one of Wi-Fi (Wireless-Fidelity), Wi-Fi Direct, Wireless USB (Wireless Universal Serial Bus) technology can be used to support short-range communication.

The short-range communication module 111 may be provided between the portable sound device 100 and the wireless communication system, between the portable sound device 100 and another mobile terminal, or the portable sound device 100 through local area network (Wireless Area Networks). ) And a wireless communication between the network where the other mobile terminal (or external server) is located. The short range wireless communication network may be short range wireless personal area networks.

The short range communication module 111 may detect (or recognize) a terminal or the like that can communicate around the portable sound device 100. Further, when the detected terminal is a device authorized to communicate with the portable acoustic apparatus 100 according to the present invention, the controller 160 transmits at least a part of the data processed by the mobile terminal through the short range communication module 111. Can be sent. Accordingly, the user of the portable acoustic apparatus 100 may use the data processed by the terminal through the wearable device.

For example, according to this, when a telephone is received in a terminal or the like, the user can perform a telephone call through the portable acoustic apparatus 100.

The location information module 112 is a module for acquiring the location (or current location) of the portable audio device 100. Examples of the location information module 112 include a GPS (Global Positioning System) module or a WiFi (Wireless Fidelity) module. For example, when the mobile terminal utilizes the GPS module, the mobile terminal may acquire the location of the portable acoustic apparatus 100 using a signal transmitted from a GPS satellite. As another example, when the portable audio device 100 utilizes the Wi-Fi module, the portable audio device 100 is based on information of the wireless access point (AP) that transmits or receives a Wi-Fi module and a wireless signal. To obtain the position of. If necessary, the location information module 112 may perform any function of other modules of the wireless communication unit 110 to substitute or additionally obtain data regarding the location of the portable sound device 100. The location information module 115 is a module used to acquire the location (or current location) of the portable audio device 100, and is not limited to a module that directly calculates or acquires the location of the portable audio device 100. .

The input unit 120 may be a microphone (MIC) 121 for inputting an audio signal, or an audio input unit, a user input unit 122 (eg, a touch key or a push key) for receiving information from a user. key), etc.). The voice data or the image data collected by the input unit 120 may be analyzed and processed as a control command of the user.

The user input unit 122 is a configuration for the user to control the portable audio device 100, for example, a call button, a button for adjusting the volume, a power button and a storage button for accommodating the sound cable into the main body as an example. Can be.

The user input unit 122 may include only a call button, a pair of volume control buttons, and may further include a play / stop button and a song order change button.

The size of the portable audio device 100 is limited, and the user input unit 122 is often inputted by the user without directly viewing the number of buttons, so that it is difficult to distinguish the functions of each button. Time and number of times of pressing and combinations of a plurality of buttons can be expanded to expand the control commands that can be input.

The microphone 121 processes an external sound signal as electrical voice data. The processed voice data may be utilized according to a function (or an application program being executed) performed by the portable sound device 100 or transmitted to an external terminal or an external server through the wireless communication unit 110. Meanwhile, various microphones for removing noise may be implemented in the microphone 122 to remove noise generated in the process of receiving an external sound signal.

The sensing unit 130 may include one or more sensors for sensing at least one of information in the portable sound device, surrounding environment information surrounding the portable sound device, and user information. For example, the sensing unit 130 may include a proximity sensor 131, an illumination sensor 132, an illumination sensor, a touch sensor, an acceleration sensor, a magnetic sensor, and gravity. G-sensor, Gyroscope Sensor, Motion Sensor, RGB Sensor, Infrared Sensor, Infrared Sensor, Fingerprint Sensor, Ultrasonic Sensor , Optical sensors, microphones (see 121), battery gauges, environmental sensors (e.g. barometers, hygrometers, thermometers, radiation sensors, heat sensors, gas sensors, etc.), It may include at least one of a chemical sensor (eg, electronic nose, healthcare sensor, biometric sensor, etc.). On the other hand, the portable audio device disclosed herein may utilize a combination of information sensed by at least two or more of these sensors.

In particular, it may include a sensor for detecting whether the earphone to be described later is located in the holder, such a sensor may be representatively applied.

The output unit 140 is used to generate an output related to visual, auditory, or tactile, and may include at least one of an audio output unit 141, a haptic module 142, and an optical output unit 143.

The sound output unit 141 is a device for outputting sound according to an audio signal, and representative examples thereof may include earphones that are inserted into a user's ear and deliver sound, and a speaker that outputs sound without the earphones being inserted.

The interface unit 150 serves as a path to various types of external devices connected to the portable sound device 100. The interface unit 150 may include at least one of an external charger port and a wired / wireless data port. In the portable audio device 100, in response to an external device being connected to the interface unit 150, appropriate control associated with the connected external device may be performed.

In addition to the operation related to the application program, the controller 160 generally controls the overall operation of the portable acoustic apparatus 100. The controller 160 may process signals, data, information, or the like, which are input or output through the above-described components.

The power supply unit 170 receives power from an external power source and an internal power source under the control of the controller 160 to supply power to each component included in the portable sound device 100. The power supply unit 170 includes a battery, which may be a built-in battery or a replaceable battery.

At least some of the components may operate in cooperation with each other in order to implement an operation, control, or control method of the portable acoustic apparatus according to various embodiments described below.

2 is a perspective view of a portable audio device as an example of a digital device according to an embodiment of the present invention. 3 is an exploded perspective view of the portable audio device 100 as an example of a digital device according to an embodiment of the present invention.

The portable sound device 100 may largely include a configuration of the neckband wire 310 and the main body 200. The neckband wire 310 may surround the neck area of the user and serve to mount the portable audio device 100 on the neck of the user.

The main body 200 and the neckband wire 310 may be combined to form a 'U' shape, or both ends may be detached and optionally formed to form an 'O' shape as needed.

The main body 200 may be coupled to both ends of the necked wire, respectively.

The main body 200 may be divided into a first body coupled to one end of the neckband wire 310 and a second body coupled to the other end of the neckband wire 310.

In order to prevent duplication of description, only the main body 200 of one side of the first body or the second body will be described.

The main body 200 may be provided integrally, but may be provided in the form of a combination of the upper case 210 and the lower case 220 for the purpose of component mounting. One side of the upper case 210 or the lower case 220 may include a side region of the main body 200. Alternatively, the side case may be provided as a separate member to be combined with the upper case 210 and the lower case 220. In the present invention, it will be described on the premise that the upper case 210 forms a side region of the main body 200.

Since the portable acoustic device 100 is easily exposed to moisture such as sweat, it may add a waterproof function. A rib covering a gap between the upper case 210 and the lower case 220 may be formed or water may be prevented from penetrating through the waterproof member.

The main body 200 may be manufactured by injection molding a polymer material. For example, a plastic product having a strength such as polystyrene (PS) may be used. However, it may be partially composed of a release material including metal, glass, leather, and the like.

The main body 200 may protect the internal parts and at the same time may be a polyurethane coating on the surface of the main body 200 to be in close contact with the user's body. Applying a polyurethane coating on the surface of the main body 200 can form a unitary appearance of the portable audio device 100. The main body 200 is in close contact with the user's skin and does not shake in accordance with the user's movement. There is an advantage.

The main body 200 may mount most components capable of performing the functions of the portable acoustic apparatus 100 of the present invention. For example, various components such as the main board, the wireless communication unit, the battery 260, and the recovery module may be inserted into the main body 200.

The main board is mounted with a wireless communication unit, a microphone 201, etc., and is connected to a battery 260, a user input unit, a sound output unit, and the like. Components mounted on the main body 200 may be provided symmetrically on both sides of the body, that is, the first body and the second body, or may be provided on only one side.

The neckband wire 310 may be elastically deformed within a predetermined range when a force is applied to the neckband wire 310 and then restored to its original shape when the force is removed. The shape memory alloy may be a representative form having elastic properties. Further, the first substrate 240, the fixing bracket 250, the battery 260, and the like are additionally provided.

1 to 3 exemplify the portable audio device, the present invention is not limited thereto and may be applied to any other type of digital device capable of speech recognition.

4 illustrates a process in which a digital device corrects an error through a first translation / second translation or the like according to an embodiment of the present invention. It is possible to initially receive a user's voice through the microphone described above with reference to FIGS. 1 to 3, and to analyze and translate the voice received through a controller, a memory, a network interface, and the like.

The main technical idea of the present invention is a technology of translating a speech recognized language into a preset language (for example, Korean-English) and interpreting (English-Korean) again to correct the difference. Learning the difference (Diff) of the corrected content by the feature (feature), and then designed to enable automatic correction through the AI (Artificial Intelligence) also belongs to another scope of the present invention.

For example, assume that a device according to an embodiment of the present invention is a device A shown in FIG. 4. Through the microphone of the A device, a voice of “see at 6 o'clock tomorrow” is input (S401).

When the device A translates the communication with the translation program or the server stored in the internal memory, “Look at the clock tower at 6 o'clock tomorrow” is first translated (S402).

Based on the original translation of "Look at the clock tower at 6 o'clock tomorrow" (S403), when translated back into Korean, it is usually translated "Look at the clock tower tomorrow at 6" (S404).

At this time, the A device according to an embodiment of the present invention detects the difference between the Korean text (S401) and the retranslated Korean sentence (S404) received in step S401. Then, it provides a list for correcting the "look" corresponding to the difference (S405).

If the user selects "Meet" (S406), the English translation is modified again to "See you at the clock tower at 6 o'clock tomorrow" (S407).

In addition, a GUI (S409) for re-checking the modified “See you at the clock tower at 6 o'clock tomorrow” (S408) is displayed, and when a user confirmation (transmission) is received, the final English “See you at” is displayed. The clock tower at 6 o'clock tomorrow ”is transmitted to the B device (S411), and the corresponding Korean language (S410) is stored together in memory, so that the same error is prevented in the future.

Fig. 5 shows a detailed flowchart of the digital device performing post-interpretation correction according to an embodiment of the present invention.

In FIG. 4, it is assumed that any language is received in an audio format through speech recognition, but original text may be transmitted through voice or keyboard input (S501).

At this time, the digital device according to an embodiment of the present invention performs translation in a predetermined language (S502). The preset language may be English, Korean, Japanese, Chinese, etc., but is not limited thereto.

The digital device retranslates the original language back to the original language based on the text translated in step S502 (S503).

Further, it is determined whether the original text input in step S501 and the text retranslated in step S503 are the same (S504).

In the case where the determination result is the same (S504), since a special correction process is not necessary, the translated content is output through the speaker or transmitted to another device (S514).

On the other hand, if it is not the same as the determination result (S504), it provides feedback informing the user of the difference (S505). In FIG. 4, outputting a graphic image in the form of a list is illustrated, but feeding back a difference through audio is within the scope of the present invention.

It is determined whether the AI function is applied according to the performance of the digital device of the present invention or according to the user's selection (S506).

As a result of the determination (S506), if AI is applied, it is proposed to change the word with the difference based on the AI technology (S507).

As a result of the determination (S506), if the AI is not applied, the user selects a word to correct the job (S508).

Further, the digital device determines whether there is a user input (S509).

As a result of the determination (S509), if there is no user input, the translated content is output as it is without error correction or transmitted to another device (S514). For example, the difference may be that the other party has no difficulty in understanding even if the translation error is not corrected.

On the other hand, if there is a user selection as a result of the determination (S509), a sentence to which correction is applied is newly generated (S510), and a message for requesting reconfirmation to the user is displayed (S511). If reconfirmation is returned to step S502, and if reconfirmation is not performed, it is determined again whether AI is applied (S512).

If the determination result (S512) AI is not applied, the process returns to step S514. If the determination result (S512) AI is applied, the correction word is learned and stored in the memory (S513), and the process moves to step S514.

6 illustrates a process in which a digital device executes N to N interpretation according to an embodiment of the present invention. On the other hand, in order to translate more quickly in the many-to-many translation model, one feature of the present invention is to use only N translation engines by using official language translation instead of using N × N translation engines. That is, the official language translation can be "Korean" or "English" here.

If the previous embodiments assume a one-to-one interpretation through a digital device (eg, portable audio device, headset, etc.), FIG. 6 proposes a one-to-n or many-to-many (N to N) interpretation service. .

Connect multiple headsets to one terminal and set the language to use an interpreter. The translation network is configured by connecting all connected headsets, including communication between terminals (mobile phones).

For example, if the talker speaks the language, everyone who is connected to the other terminal including the same terminal can receive the interpreter service in the language set by each person.

More specifically, for example, it is assumed that two headsets are connected to the first mobile phone and two headsets are also connected to the second mobile phone.

The language of the first headset connected to the first mobile phone is set to “English”, the language of the first headset connected to the first mobile phone is set to “Chinese”, and the language of the third headset connected to the second mobile phone Is also set to “Japanese” and the language of the fourth headset connected to the second mobile phone is also set to “Korean”.

At this time, if “Do you have dinner?” Is input through the first headset (S601), the corresponding Chinese is output through the second headset (S602), and the corresponding Japanese is output through the third headset. (S603), and the corresponding Korean language is output through the fourth headset (S604). Of course, it is also within the scope of other rights of the present invention to combine the above-described embodiments of FIGS.

7 illustrates a scenario in which a digital device according to another embodiment of the present invention masks a voice / emotion of a talker.

If the previous embodiments mainly focused on errors in the text itself, FIG. 7 proposes a technique for more precisely detecting the intent of the talker.

For example, by interpreting the content through the talker's voice, the listener can identify who the talker is. In addition, the language before translation is given so that the guide can be used to identify which country is speaking.

Furthermore, the stressed voices are mapped to words in the speaker's voice, and the translated sentences are conveyed for feelings through stressed stresses. In addition, expressing and displaying the stress or emotion in text will be said to belong to another scope of the present invention.

More specifically, for example, as shown in FIG. 7, when the female A utters "see at the clock tower tomorrow at 6 o'clock" without any change in tone (S701), first, when the preset language is English, “See you at the clock tower at 6 o'clock tomorrow ”(S702), indicating that it was Korean or Korean, and in the voice of the same woman A,“ See you at the clock tower at 6 o'clock tomorrow ” Is transmitted to the other device (S703).

On the other hand, let's assume that the same woman A, but emphasized a certain part and said "I was angry because of you!" For example, "you" and "he said" two parts are emphasized.

Through the analysis of words and vocabulary with an accented emphasis, the additional information is transmitted to the audio data so that the words “told you” and “you” are highlighted and output as “I told you I'am upset because of you”. (S705).

FIG. 8 shows a flow chart embodying the scenario shown in FIG. 7 in more detail.

The digital device according to an embodiment of the present invention capable of speech recognition receives a user voice input (S801). At this time, unlike the prior art, feature points of the input voice are extracted (S802). The feature point corresponds to, for example, stress, intonation, voice, etc., and other additional information may be extracted.

The recognized voice is converted into text (S803) and translated into another preset language (S804).

Furthermore, the extracted feature points as well as the translated content are mapped to each other and transmitted to another device or an internal controller (S805).

First, it is determined whether a feature point exists in the data received in step S805 (S806).

If there is no feature point (S806), the translated text is output as it is (S809).

On the other hand, if there is a feature point in the determination result (S806), the feature point is masked in the text with reference to the data received in step S805 (S807).

Then, after the feature point masked text is applied to the text to speech (TTS), the process moves to step S809. Therefore, there is a technical effect that the emphasis portion of the first spoken first language can be reflected almost the same or similarly in the interpreted second language.

FIG. 9 is a block diagram showing a main configuration of the digital device shown in FIGS. 1 to 8. Accordingly, FIG. 9 may be interpreted independently, and supplementary interpretation with reference to the previous drawings is also within the scope of the present invention. However, in particular, the multilateral interpretation service illustrated in FIG. 6 is specifically illustrated in FIG.

In FIG. 9, the A device 900, the server 910, and the B device group 920 to which the present invention is applied are shown separately, but some or all of the functions of the server 910 are A device 900 or B device. Designing to perform in group 920 is also within the scope of the present invention.

The voice message of the first language received through the A device 900 is transmitted to the message receiving unit 911 of the server 910.

The message receiving unit 911 receives a voice message from the A device 900 (S902), and translates the message into an official language (for example, English) (S903).

On the other hand, the language that you want to receive from the B device group 920 through an interpreter is transmitted to the server 910 (S900), the translation engine 912 is translated into English as a public language with reference to the translation manager 913 (S904). Retranslation is performed in a specific language received in step S900 (S905).

The message transmitter 914 transmits the translated message to respective receiving devices in the B device group 920 (S906).

The present invention described above can be embodied as computer readable codes on a medium on which a program is recorded. The computer-readable medium includes all kinds of recording devices in which data that can be read by a computer system is stored.

Examples of computer-readable media include hard disk drives (HDDs), solid state disks (SSDs), silicon disk drives (SDDs), ROMs, RAMs, CD-ROMs, magnetic tapes, floppy disks, optical data storage devices, and the like. This also includes implementations in the form of carrier waves (eg, transmission over the Internet). In addition, the computer may include a control unit of the terminal. The above detailed description, therefore, is not to be construed as limiting in all respects, but should be considered as illustrative.

The scope of the invention should be determined by reasonable interpretation of the appended claims, and all changes within the equivalent scope of the invention are included in the scope of the invention.

100: portable audio equipment
110: wireless communication unit
120: input unit
130: sensing unit
140: output unit
150: interface unit
160: control unit

Claims (10)

In the control method of a digital device capable of speech recognition,
Receiving an audio signal of a first language;
Translating the received audio signal of the first language into text of a second predetermined language by referring to a memory;
Retranslating the translated text of the second language into the first language with reference to the memory;
Comparing the text of the retranslated first language with an audio signal of the received first language; And
According to the comparison result, modifying a part or all of the translated second language text and converting it into a format that can be output as an audio signal
Control method of a digital device capable of speech recognition, comprising a. The method of claim 1,
The comparing step,
If the text of the retranslated first language and the audio signal of the received first language are different, displaying the same part and a different part differently; And
Providing an option to automatically modify the other portion according to user selection or data stored in the memory of the digital device
The control method of the digital device capable of speech recognition further comprising. The method of claim 2,
The receiving step,
And extracting feature points of the audio signal of the first language, wherein the feature points include at least one of stress, intonation, voice, and volume. The method of claim 3,
The converting step,
And outputting the translated second language text in different accents, intonations, voices, or volumes according to feature points extracted from the audio signal of the first language. Control method. The method of claim 4, wherein
The first language and the second language are different from each other,
The digital device is a control method of a digital device capable of speech recognition, characterized in that at least one of a wearable device or a mobile device. In a digital device capable of speech recognition,
Memory;
A microphone for receiving an audio signal of a first language; And
A controller for controlling the memory and the microphone,
The controller,
The audio signal of the first language is translated into a text of a second predetermined language by referring to the memory.
Retranslating the translated text of the second language into the first language with reference to the memory,
Compare the text of the retranslated first language with an audio signal of the received first language, and
And a part or all of the translated second language text is converted into a format that can be output as an audio signal according to the comparison result. The method of claim 6,
If the text of the retranslated first language and the audio signal of the received first language are different, display the same part and a different part differently, and
And a display module for displaying an option for automatically modifying the other part according to a user selection or data stored in a memory of the digital device. The method of claim 7, wherein
The controller,
Extracting a feature point of the audio signal of the first language, wherein the feature point includes at least one of stress, intonation, voice, and volume. The method of claim 8,
The controller,
And a speaker for outputting the translated second language text in different accents, intonations, voices, or volumes according to feature points extracted from the audio signal of the first language. The method of claim 9,
The first language and the second language are different from each other,
The digital device is a digital device capable of speech recognition, characterized in that at least one of a wearable device or a mobile device.

Images