Wireless communication device using voice recognition and voice synthesis

Abstract

The wireless communication device according to the present invention is characterized by including: a voice recognition unit that converts a voice signal input through a microphone into a stream of syllable information using voice recognition; an encoding unit that encodes the stream of syllable information to generate digital transmission data; a transmitting unit that modulates the digital transmission data and transmits the transmission signal through an antenna; a receiving unit that demodulates a reception signal received through the antenna and outputs digital reception data; a decoding unit that decodes the digital reception data and converts it into a stream of syllable information; and a voice synthesis unit that converts the stream of syllable information into a voice signal using voice synthesis and outputs it through a speaker.

Description

[Technical field]

[0001] The present invention relates to wireless communication devices, and more particularly to wireless communication devices utilizing voice recognition and voice synthesis. [Background technology]

[0002] A wireless communication device for voice communication converts a voice signal, which is generally an analog signal, into a digital signal through processes such as sampling, quantization, and encoding, and transmits the converted signal through a wireless communication network, and converts the received digital signal into a voice signal through a reverse conversion process and outputs the converted signal. In such a voice communication method, there is a limit to the bit rate reduction, such as 128 kbps, 192 kbps, and 320 kbps required for high-quality audio transmission for music, and 2.4 kbps, 3.2 kbps, etc. required for audio transmission with maximum voice compression in voice communication. Summary of the Invention [Problem to be solved by the invention]

[0003] The technical problem to be solved by the present invention is to provide a wireless communication device capable of dramatically reducing the bit rate as compared with the existing voice communication method. [Means for solving the problem]

[0004] In order to solve the above technical problem, a wireless communication device according to the present invention includes a voice recognition unit that converts a voice signal input through a microphone into a stream of syllable information using voice recognition; an encoding unit that encodes the stream of syllable information to generate digital transmission data; a transmitting unit that modulates the digital transmission data and transmits a transmission signal through an antenna; a receiving unit that demodulates a reception signal received through the antenna and outputs digital reception data; a decoding unit that decodes the digital reception data and converts it into a stream of syllable information; and a voice synthesis unit that converts the stream of syllable information into a voice signal using voice synthesis and outputs it through a speaker.

[0005] The syllable information may include a combination of initial, medial, and final sounds.

[0006] The syllabic information may further include prosodic information.

[0007] The prosodic information may include normal sounds, rising sounds, falling sounds, long sounds, and stressed sounds.

[0008] The syllable information may further include timbre information.

[0009] The tone information may include a predetermined number of levels for men, women, the elderly, and children.

[0010] The initial, medial, and final sounds that make up the syllable information correspond to the three axes of a three-dimensional coordinate system, and the syllable information is mapped to digital data using the coordinate values ​​of the initial, medial, and final sounds in the three-dimensional coordinate system.

[0011] The syllable information further includes prosodic information, and the syllable information is mapped to the digital data based on the coordinate values ​​of the initial, medial and final sounds in the three-dimensional coordinate system and the prosodic information.

[0012] The wireless communication device is a wireless communication device for voice communication through an artificial satellite, and the transmitter and the receiver can modulate and demodulate the transmission signal and the reception signal so as to transmit and receive the transmission signal to and from the artificial satellite.

[0013] The wireless communication device may further include a gyro sensor; a three-axis gear connected to the antenna; and an antenna attitude control unit that controls the three-axis gear so that the antenna faces upward according to a sensing value of the gyro sensor.

[0014] The wireless communication device may further include a recording unit for storing the digital transmission data output from the encoding unit and the digital reception data output from the receiving unit. Effect of the Invention

[0015] According to the present invention, it is possible to provide a wireless communication device that can dramatically reduce the bit rate compared to existing voice communication methods by using voice recognition and voice synthesis.

[0016] The present invention is also applicable to any language, such as English or Latin, whose syllable structure is composed of a single middle sound, an initial sound and a middle sound, a middle sound and a final sound, or an initial sound, a middle sound and a final sound.

[0017] In addition, the present invention has the advantage that the memory required for recording can be minimized compared to existing voice communication methods and methods of storing voice compression files by converting the syllable information stream into digital data using a three-dimensional coordinate system, converting it into digital transmission data in an encoding unit, and then storing it in a recording unit (not shown).Similarly, the present invention has the advantage that the memory required for recording can be minimized compared to existing voice communication methods and methods of storing voice compression files by storing digital reception data output from the receiving unit in the recording unit.

[0018] In addition, when searching for recorded content in the recording unit, the wireless communication device of the present invention can directly match consecutive syllables to the state of digital data in the recording unit and search for them, which has the advantage of being able to search for recorded content such as specific words much more quickly than the existing method of saving a voice compression file and searching for recorded data.

[0019] The existing speech recognition method of STT (Speech to Text) type, which converts voice input through a microphone into text, has many errors such as converting input voice into text with a completely different meaning, and has limitations in accurately converting into the desired text. Therefore, in order to solve this problem, a huge amount of speech recognition DB and an advanced learning program that processes speech recognition data are required.

[0020] On the other hand, the existing voice synthesis method using the Text to Speech (TTS) method, which converts input text into voice, is still unnatural and difficult to hear, and in order to overcome such limitations, a huge system and program are required.

[0021] In the present invention, the voice of a speaker inputted through a microphone is converted into a syllable information stream consisting of syllables and prosody in a voice recognition unit, and digital transmission data, which is a numeric code, is immediately generated in an encoding unit, so that accurate voice can be transmitted, and the digital reception data outputted from the receiving unit is converted into an accurate syllable information stream in a decoding unit, and the voice is immediately played through a voice synthesis unit and a speaker. Therefore, the present invention has an advantage that it can be configured with a revolutionary simple system and program compared to the existing STT type voice recognition and TTS type voice synthesis. [Brief description of the drawings]

[0022] [Figure 1] 1 is a diagram showing a configuration of a wireless communication device according to an embodiment of the present invention.

[0023] [Diagram 2] 1 is a diagram showing a code structure of syllable information.

[0024] [Diagram 3] This is a diagram showing the concept that the initial, medial, and final sounds that make up a syllable correspond to the three axes of a three-dimensional coordinate system.

[0025] [Figure 4] 1 is a diagram showing a specific example of a three-dimensional coordinate system corresponding to the initial, medial, and final sounds that constitute a syllable.

[0026] [Diagram 5] 13 is a diagram illustrating an additional configuration of a wireless communication device according to an embodiment of the present invention.

[0027] [Figure 6]4 is a diagram showing a shape in which an antenna of a wireless communication device is controlled to point upward according to an embodiment of the present invention; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0028] Hereinafter, a preferred embodiment of the present invention will be described in detail with reference to the drawings. In the following description and the accompanying drawings, substantially the same components are denoted by the same reference numerals, and duplicated description will be omitted. In addition, in describing the present invention, if it is determined that a detailed description of related known functions or configurations may obscure the gist of the present invention, the detailed description thereof will be omitted.

[0029] FIG. 1 shows the configuration of a wireless communication device according to an embodiment of the present invention.

[0030] The wireless communication device 100 according to this embodiment includes a microphone 111, a voice recognition unit 112, an encoding unit 113, a transmitting unit 114, a receiving unit 121, a decoding unit 122, a voice synthesis unit 123, a speaker 124, and an antenna 130.

[0031] The wireless communication device 100 can perform voice communication with another wireless communication device 200. Like the wireless communication device 100, the other wireless communication device 200 also includes a microphone 211, a voice recognition unit 212, an encoding unit 213, a transmitting unit 214, a receiving unit 221, a decoding unit 222, a voice synthesis unit 223, a speaker 224, and an antenna 230.

[0032] Wireless communication device 100 and wireless communication device 200 may be devices that communicate directly with each other (e.g., similar to a radio), devices that communicate with each other through a base station (e.g., similar to a cellular phone), or devices that communicate with each other through a satellite.

[0033] The voice recognition unit 112, 212 converts the voice signal input through the microphone 111, 211 into a stream of syllable information using voice recognition. The encoding unit 113, 213 encodes the stream of syllable information to generate digital transmission data. The transmitting unit 114, 214 modulates the digital transmission data and transmits the transmission signal through the antenna 130, 230.

[0034] The receivers 121 and 221 demodulate signals received through the antennas 130 and 230 to output digital received data. The decoders 122 and 222 decode the digital received data and convert it into a stream of syllable information. The voice synthesizers 123 and 223 convert the stream of syllable information into a voice signal using voice synthesis and output it through the speakers 124 and 224.

[0035] When the wireless communication device 100 and the wireless communication device 200 are devices that communicate with each other via an artificial satellite, the transmitters 114 and 214 and the receivers 121 and 221 modulate and demodulate the transmission signal and the reception signal so that they can be transmitted to and received from the artificial satellite.

[0036] In an embodiment of the present invention, the syllable information includes a combination of an initial sound, a middle sound, and a final sound, and the initial sound, the middle sound, and the final sound are expressed by Roman alphabet phonetic symbols.

[0037] For example, the initial tone can be composed of 26 types, including silent, voiced, unvoiced, and semiconsonants, as follows:

[0038] JPEG0007612032000001.jpg24152

[0039] For example, the middle voice can be composed of ten vowels as follows:

[0040] JPEG0007612032000002.jpg7152

[0041] For example, the final voice can be composed of 12 types including silent, voiced and unvoiced consonants as follows:

[0042] JPEG0007612032000003.jpg7152

[0043] The syllable information may also include a pause indicating a pause of a certain length.

[0044] Of course, other syllable components may be added to the initial, medial and final syllables in addition to the above syllable components, depending on the syllable to be expressed.

[0045] JPEG0007612032000004.jpg11152

[0046] Also, the syllable information may further include timbre information. For example, the timbre information may be set in a predetermined number (e.g., 100 levels) for male, female, elderly, and child to express a total of 400 timbres. As the timbre information, a specific timbre may be set as a default, a specific timbre may be set by analyzing the frequency or waveform of the user's voice, or a specific timbre selected by the user may be set. The timbre information may be changeable by the user during a call. The types and levels of timbre may also be expanded or added. The voice synthesis unit 223 of the receiving side may generate a voice signal by reflecting the timbre information included in the syllable information during voice synthesis.

[0047] The number of chords required to express one syllable is as follows. First, there are 26 initial sounds, 10 medial sounds, and 12 final sounds, so there are 26 x 10 x 12 = 3,120 combinations. Since there are five types of rhythm for each combination, the total number becomes 3,120 x 5 = 15,600. If a rest is added to this, the total number becomes 15,601. If 400 timbre information is added, the total number becomes 15,601 + 400 = 16,001. In other words, one valid syllable can be expressed with 16,001 chords.

[0048] For example, if one syllable is expressed by 2 bytes, 2 bytes is 16 bits, so it can be expressed as 0000 to FFFF, that is, 2 16=65,536 kinds of codes can be expressed. And since 0000 is used as a rest, 0001~FFFF, i.e. 65,535-16,001=49,534, remains, and this part can be used as a spare code to convey other additional information. That is, 0000H can represent a rest, 0001H(1)~3CF1H(15,601) can represent syllables and prosody, ~3E81H(16,001) can represent tone, and ~FFFFH(65,535) can be used as a spare code. Figure 2 shows the code structure of syllable information based on this.

[0049] In an embodiment of the present invention, the initial, medial and final sounds constituting a syllable can be made to correspond to the three axes of a three-dimensional coordinate system, as shown in Fig. 3. For example, the initial sound can be made to correspond to the x-axis, the medial sound to the y-axis and the final sound to the z-axis. The syllable is then mapped to digital data based on the respective coordinate values ​​of the initial, medial and final sounds in the three-dimensional coordinate system. At this time, syllable information including prosody is mapped to digital data based on the prosody information together with the respective coordinate values ​​of the initial, medial and final sounds in the three-dimensional coordinate system.

[0050] FIG. 4 shows a concrete example of a three-dimensional coordinate system corresponding to the initial, medial, and final sounds that make up a syllable.

[0051] JPEG0007612032000005.jpg25152

[0052] If the prosodic value is n, then, for example, n=1 for normal sounds, n=2 for rising sounds, n=3 for falling sounds, n=4 for long sounds, and n=5 for stressed sounds.

[0053] The code corresponding to a syllable (x, y, z) and a prosody n is calculated by the following formula:

[0054] f(x,y,z,n)=(Xm * Ym * Zm) * (n-1)+(Xm * Ym) *(z-1)+Xm * (y-1)+x

[0055] Here, Xm, Ym, and Zm are the maximum values ​​of x, y, and z, respectively, that is, Xm=26, Ym=10, and Zm=12, and x, y, and z≠0.

[0056] For example, the normal sound [a] can be expressed as a digital value f(1,1,1,1) = 0001H.

[0057] JPEG0007612032000006.jpg11152

[0058] JPEG0007612032000007.jpg45152

[0059] JPEG0007612032000008.jpg91152

[0060] JPEG0007612032000009.jpg66152

[0061] 64bps is only about 1 / 5000 of the bit rate of 320kbps for high quality audio transmission. Therefore, according to the present invention, it is possible to secure about 5000 times as many transmission channels as the existing transmission method, and has a transmission efficiency about 37.5 times higher than the bit rate of 2.4kbps for voice communication at maximum compression.

[0062] In the embodiment of the present invention, the initial, medial and final consonants of a syllable are expressed by Roman alphabet phonetic symbols. However, the present invention is not limited to Roman alphabet phonetic symbols, and any phonetic symbols that can express the initial, medial and final consonants, such as Hangul (Korean Alphabet) phonetic symbols, Japanese (Hiragana) phonetic symbols, and International Standard Phonetic Symbols, may be used.

[0063] Also, the wireless communication device 100 may further include a recording unit (not shown) for storing the digital received data output from the digital transmission data receiving units 121 and 221 output from the encoding units 113 and 213 .

[0064] The digital transmission data output from the encoding units 113 and 213 and the digital reception data output from the receiving units 121 and 221 are created by digitizing the syllable information stream using a three-dimensional coordinate system, and therefore the memory constituting the recording unit (not shown) can minimize the memory capacity compared to existing voice communication methods or methods for storing voice compression files.

[0065] In addition, when searching for a specific word or syllable in the recording unit (not shown), the corresponding word or syllable can be directly matched to the state of the digital data in the recording unit and searched for, so that the recorded contents such as a specific word can be searched for more quickly than in the case of storing an existing voice compression file and searching for recorded data.

[0066] There are various methods for matching digital data to search for syllables or words, and those skilled in the art can easily understand the methods, so detailed description will be omitted.

[0067] When the wireless communication device 100 is a wireless communication device for communication via a satellite, it is preferable that the antenna 130 is controlled to point in a direction toward the satellite, i.e., upward. Fig. 5 shows an additional configuration of the wireless communication device according to an embodiment of the present invention for this purpose.

[0068] 5, the wireless communication device 100 may further include a three-axis gear 131 connected to the antenna 130, an attitude controller 132, and a gyro sensor 133. The attitude controller 132 controls the three-axis gear 131 according to a sensing value of the gyro sensor 133 so that the antenna 130 faces upward even if the wireless communication device 100 is tilted.

[0069] 6 shows a shape in which the antenna 130 of the wireless communication device 100 is controlled to face upward according to an embodiment of the present invention. As shown, even if the wireless communication device 100 is tilted, the antenna 130 faces upward, so communication with the artificial satellite is smooth.

[0070] The embodiments of the present invention are illustrated in terms of functional blocks and various processing steps. Such functional blocks may be embodied as any number of hardware and / or software components that perform a particular function. For example, the embodiments may employ integrated circuit components such as memory, processing, logic, look-up tables, etc. that may perform various functions under the control of one or more microprocessors or other control devices. Similar to components of the present invention being implemented in software programming or software elements, the embodiments may be embodied in programming or scripting languages ​​such as C, C++, Java, assembler, etc., including various algorithms embodied in a combination of data structures, processes, routines, or other programming components. Functional aspects may be embodied as algorithms executed by one or more processors. Additionally, the embodiments may employ conventional techniques for electronic configuration, signal processing, and / or data processing, etc. Terms such as "mechanism," "element," "means," and "component" are used broadly and are not limited to mechanical and physical components. The terms may include a series of software routines in conjunction with a processor or the like.

[0071] The specific implementation described in the embodiment is one embodiment and does not limit the scope of the embodiment in any way. For the sake of brevity of the specification, descriptions of conventional electronic configurations, control systems, software, and other functional aspects of the system are omitted. In addition, the line connections or connecting members between components shown in the drawings are illustrative of functional connections and / or physical or circuit connections, and may be replaced or appear as various additional functional connections, physical connections, or circuit connections in an actual device. In addition, unless specifically mentioned as "essential" or "important," a component is not necessarily required for application of the present invention.

[0072] The present invention has been described above with reference to its preferred embodiment. Those skilled in the art will understand that the present invention can be embodied in modified forms without departing from the essential characteristics of the present invention. Therefore, the disclosed embodiments should be considered in an illustrative rather than a restrictive sense. The scope of the present invention is defined in the claims, not in the above description, and all differences within the scope of the claims should be interpreted as being included in the present invention.

Claims

1. a voice recognition unit that converts a voice signal input through a microphone into a stream of syllable information using voice recognition; an encoding unit that encodes the stream of syllable information to generate digital transmission data; a transmitter for modulating the digital transmission data and transmitting the transmission signal through an antenna; a receiver unit that demodulates a signal received through the antenna and outputs digital received data; a decoder for decoding the digital received data and converting it into a stream of syllabic information; a voice synthesis unit that converts the stream of syllable information into a voice signal using voice synthesis and outputs the voice signal through a speaker; A wireless communication device comprising: The syllable information includes a combination of initial, middle, and final sounds and prosodic information; The prosodic information includes normal sounds, rising sounds, falling sounds, long sounds, and stressed sounds; the initial sound, the middle sound, and the final sound constituting the syllable information correspond to three axes of a three-dimensional coordinate system, respectively; A wireless communication device, characterized in that the syllable information is mapped to digital data based on the coordinate values ​​of the initial, medial and final syllables in the three-dimensional coordinate system and the prosodic information.

2. The wireless communication device according to claim 1 , wherein the syllable information further includes tone information.

3. The wireless communication device of claim 2, wherein the tone information includes a predetermined number of levels for male, female, elderly, and child.

4. The wireless communication device is a wireless communication device for voice communication via an artificial satellite, 2. The wireless communication device according to claim 1, wherein the transmitting section and the receiving section modulate and demodulate the transmission signal and the reception signal so that they can be transmitted to and received from an artificial satellite.

5. A gyro sensor and A three-axis gear connected to the antenna; an antenna attitude control unit that controls the three-axis gear so that the antenna is directed upward according to a sensing value of the gyro sensor; The wireless communication device of claim 4, further comprising:

6. The wireless communication device according to claim 1 , further comprising a recording unit for storing the digital transmission data output from the encoding unit and the digital reception data output from the receiving unit.

Images