JP2002344574A - Mobile communication equipment - Google Patents

Abstract

PROBLEM TO BE SOLVED: To facilitate inputting of mail text when transmitting an e-mail from mobile communication equipment. SOLUTION: The mobile communication equipment is provided with a conversation function and a function to enable the transmission and reception of an e-mail. By providing the mobile communication equipment with a speech recognition function, voice-text conversion is made possible and the text can be entered by voice and the entered text can be transmitted as an e-mail.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention
The present invention relates to a mobile communication device such as S.

[0002]

2. Description of the Related Art In recent years, the spread of mobile communication devices such as mobile phones and PHSs has been remarkable, and even if they are functions, they can transmit and receive e-mails and access the Internet, as well as simple call functions. There are things, and these things are becoming mainstream now.

The e-mail function can transmit and receive so-called e-mails that can be transmitted not only between mobile communication devices but also to a general personal computer or the like via the Internet. In any case, the text input of the e-mail is provided on the device itself, usually by operating a plurality of input keys such as numeric keys used for telephone number input etc. You are typing.

[0004] For example, Japanese alphabets mixed with kanji are input by a predetermined operation by assigning a hiragana, katakana alphabet, an alphabet and the like to the above-mentioned numeric keys, and having other input keys function as conversion keys. It was made possible.

[0005] The input text is displayed on a display unit such as a liquid crystal screen provided in the main body of the device.

[0006]

However, as described above, the key operation for transmitting an e-mail in the conventional mobile communication device is different from the JIS keyboard used in a word processor or a personal computer. Because of the special operation using the keys, it was very troublesome for those who are not used to it, and it was troublesome to even feel pain.

[0007] For this reason, many people do not use the convenient e-mail function that has been added at all, or use an input terminal such as a keyboard that can be connected to the device, so that anyone cannot easily write and send e-mail. There is the actual situation.

[0008] The problem of such character input is exactly the same when using a telephone directory function (address book function), a memo function, or the like, which is standardly provided in recent mobile communication devices.

An object of the present invention is to provide a mobile communication device that can solve the above-mentioned problems.

[0010]

Means for Solving the Problems To solve the above problems, the present invention employs the following means.

(1) According to the first aspect of the present invention, a mobile communication device having a telephone call function and a function of transmitting and receiving an electronic mail is provided. And sent the input text as e-mail.

Therefore, there is no need to input characters by a difficult key operation, and an electronic mail can be easily transmitted.

(2) In the present invention described in claim 2, claim 1 is
In the above, a display unit for displaying a sentence that has been converted to speech text is provided, and if there is an erroneous speech recognition and / or erroneous conversion part in the display content, this is corrected and re-input to improve the accuracy of the speech text conversion. The feature is that it has a learning function that enhances it.

By performing such learning, the accuracy of speech-to-text conversion is improved, and as the number of times of use increases, accurate text input can be performed by voice, and e-mail and the like can be written in a short time. Will be able to do it.

(3) According to the present invention described in claim 3, according to claim 1,
In step 2 or 2, at the time of a call, the contents of the call input from the microphone are converted to text so that the text can be displayed on the display unit. A learning function is provided to increase the accuracy of speech-to-text conversion by inputting.

Therefore, the learning can be performed at the time of a normal telephone call without reading out the text for learning at a special time, and by repeating the learning many times, the voice of the user can be obtained. The recognition rate and the accuracy of the conversion result are remarkably improved, so that text input by voice can be smoothly performed without feeling any stress.

(4) According to the present invention described in claim 4, claim 1 is
The feature of any one of the above-mentioned is that the general operation of the device can be performed by voice.

Therefore, for example, even if a telephone number is input, an operation command can be executed by voice without pressing a numeric key (dial button) or performing a key operation for calling a registered destination. , Mobile phone, PH
The usability of mobile communication devices such as S is significantly improved.

(5) The present invention described in claim 5 is characterized in that in any of the above-mentioned claims 1 to 4, a memory can be added.

That is, when voice is converted to text,
Although it is necessary to store the voice and a considerably large capacity memory is required, the voice text conversion can be performed smoothly by enabling additional memory as needed.

(6) According to the present invention described in claim 6, according to claim 5,
It is characterized in that a voice recognition program can be stored in a memory.

That is, the speech recognition program may be mounted in a chip as a chip in the device, or may be stored in a memory so as to be detachable. For example, the speech recognition program When there are a plurality of, it is possible to select a favorite one and attach it to one's own mobile phone or the like.

(7) According to the present invention described in claim 7, according to claim 1,
In any one of the above-described embodiments, an input mode changeover switch capable of switching between a voice input mode for inputting characters by voice text conversion and a key input mode for inputting characters by key operation is provided.

(8) According to the present invention described in claim 8, according to claim 7,
Is characterized in that switching from one of the voice input mode and the key input mode to the other mode can be arbitrarily switched during character input.

[0025]

DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention relates to a mobile communication device having a telephone call function and a function of transmitting and receiving electronic mail.
By providing a voice recognition function, voice-to-text conversion is enabled, and a text is input by voice, and the input text can be transmitted as an electronic mail.

That is, as a mobile communication device, a mobile phone, a PHS or the like can be considered, and in recent years, a device having an e-mail function has been generally used.

In order to send an electronic mail, characters must be input as a matter of course. In this embodiment, such character input is performed by voice-to-text conversion.

Therefore, a sentence can be easily created and transmitted as an e-mail, which has a great effect that the trouble of inputting characters by a difficult key operation as in the related art is eliminated.

As the voice recognition function, a voice recognition program constructed to perform such a function can be built in a chip.

In this embodiment, an input mode changeover switch which can switch between a voice input mode for inputting characters by voice text conversion and a key input mode for inputting characters by key operation is provided.

Further, the timing for operating the input mode changeover switch is not restricted.

That is, switching from one of the voice input mode and the key input mode to the other mode can be arbitrarily performed during character input.

Therefore, in places where character input by voice is inappropriate, text input can be performed by conventional key input, and further, for example, a fixed phrase can be immediately input to a mobile communication device by key input. By using this function in combination with the voice input mode, more efficient text input becomes possible, and the time required for creating a mail text can be reduced.

As described above, according to the present embodiment, the mail text can be efficiently created, and the mail text can be easily created in any place where the user must be quiet or where the voice can be emitted. And can be sent.

The mobile phone and the PHS, which are the mobile communication devices in the present embodiment, have standard specifications except that the voice recognition chip and the input mode changeover switch are provided.

That is, a display unit composed of a liquid crystal screen or the like, an operation unit composed of input keys, command keys, and the like are provided on the surface of a handy-sized housing, and an antenna,
A receiving unit including a speaker and a transmitting unit including a microphone are provided.

The display unit displays an initial screen indicating the radio wave reception level, date, remaining battery level, etc., and a screen corresponding to the operation by the operation unit, such as a status display screen, a function guide screen, and a menu screen. Is done.

Further, the display unit is capable of displaying an input sentence when transmitting an electronic mail, that is, a mail sentence, and displaying a received sentence when receiving an electronic mail.

When text input by voice, that is, voice / text conversion is performed, if there is an erroneous voice recognition and / or erroneous conversion part in the display content of the display unit, the part is corrected and re-input. It is also characterized by having a learning function to increase the accuracy of speech-to-text conversion.

That is, by performing the learning related to the voice recognition function of the mobile communication device, the accuracy of voice-to-text conversion increases, and as the number of times of use increases, accurate text input can be performed. , E-mail, etc., in a short time.

As a learning function, instead of the above-mentioned one,
Alternatively, the following configuration can be adopted as a function to be further added.

That is, since the frequency of use as a telephone is high, at the time of a telephone call when used as a normal telephone, the contents of the telephone call of the user input from the microphone are converted to text and displayed on the display unit as text. After the end, if there is an erroneous speech recognition and / or erroneous conversion part in the display content, this is corrected and re-input, thereby providing a learning function for improving the accuracy of the speech-to-text conversion.

According to such a learning function, learning can be performed during a normal telephone call without reading a text for learning at a special time, and the mobile communication device can be used as a telephone. The learning process is overwhelming, so learning can be repeated many times. By learning the characteristics of the user's voice (sound quality, intonation, habits, etc.), the speech recognition rate and the accuracy of the conversion result can be improved. Can be significantly increased.

In particular, given that speech recognition is often poor at recognizing spoken language, and that email texts are often spoken,
It is extremely effective to use the contents of telephone calls as learning material, and the process of creating e-mails by speech-to-text becomes much smoother and faster, so users will feel no stress. Sentence input by voice can be performed smoothly without any problem.

Accordingly, anyone can enjoy and use the e-mail, and the value of use as a communication tool can be enhanced.

As described above, according to the present embodiment, a learning function unique to a mobile communication device mainly having a telephone function can be exhibited, and key input is not required.
The usability of the e-mail function by the mobile communication device is remarkably improved, and the convenience of the user is dramatically improved.

Since the mobile communication device according to the present embodiment can perform voice recognition, it has a so-called voice navigation function that enables not only writing of mail but also general operation of the device by voice. It is preferable to have it.

Therefore, even if a telephone number is input, an operation command can be executed by voice without pressing a numeric key (dial button) or performing a key operation for calling a registered destination. , Mobile phone, PH
The usability of mobile communication devices such as S is significantly improved.

Further, as a hardware feature, the mobile communication device can be provided with an additional memory.

That is, when voice is converted to text,
Although it is necessary to store the voice and a considerably large capacity memory is required, the voice text conversion can be performed smoothly by enabling additional memory as needed.

As the memory accommodating portion, a so-called flip-type structure which can be folded and connected to the housing, for example, can be considered in order to avoid an increase in the size of the housing. Such a flip-type memory storage unit can be provided on the rear surface of the housing and can be used in a folded state during normal use other than when the memory is attached and detached, so that it does not become an obstacle.

Alternatively, it is conceivable that a dedicated slot is provided in the housing to be a plug-in type used in digital cameras and the like.

Further, a speech recognition program can be stored in an expandable memory.

That is, the voice recognition program may be chipped in the device as described above and mounted in advance, but if it can be stored in a memory and can be detached as described above, For example, when there are a plurality of voice recognition programs, it is possible to select a desired one and attach it to one's own mobile phone or the like.

Further, a large number of music pieces can be stored in the memory as desired, and these can be selectively used as ringtones (ringtone melodies).

When selecting and setting, if the navigation function by voice is provided as described above, the user directs a predetermined command including a desired music title in a predetermined order to the microphone (mouthpiece). The operability is significantly improved because only utterance is required.

[0057]

Embodiments of the present invention will be described below with reference to the drawings.

FIG. 1 is a perspective view showing a mobile phone as a mobile communication device, FIG. 2 is an explanatory view of a memory storage section provided in the mobile phone, and FIG. 3 is a function showing an electrical configuration of the mobile phone. FIG. 4 is a block diagram, FIG. 4 is a conceptual diagram of the voice-to-text conversion process, FIG. 5 is an explanatory diagram showing a modification of the mobile phone, and FIG. 6 is a flowchart of the voice-to-text conversion process.

As shown in FIGS. 1 to 3, the mobile phone 1 according to the present embodiment has a display unit 2 including a liquid crystal screen 20 on the surface of a housing 10 and a plurality of input devices below the display unit 2. Keys 3a, 3b,
An operation unit 3 is provided.

A memory storage unit 11 which can be freely folded via a pivot 11a provided at the lower end is provided on the back surface of the housing 10.
Is arranged. The memory storage unit 11 will be described later in detail.

Further, a control circuit 4 as a control means is provided in the housing 10, and the control circuit 4 includes a transmission / reception section 5 as a transmission / reception means and a voice input / output as a voice input / output means. Unit 6, a display control unit 7 as display control means for the display unit 2, an input operation identification circuit 8 for controlling input means such as input keys 3a, 3b,.
A chip 9 in which a speech recognition program is written, a memory M in which various programs, text data, image data, a dictionary function and the like are stored, and a timer T as timer means are connected.

An antenna 5a is connected to the transmission / reception unit 5, and wireless communication is performed with a base station of a portable telephone (not shown) through the antenna 5a, and a signal transmitted or received by the wireless communication is transmitted to the transmission / reception unit 5. A transmission / reception circuit executes an electric signal / wireless signal conversion process by a wireless process.

The voice input / output unit 6 includes a microphone (microphone) 6a as a mouthpiece for inputting a transmission voice, and a speaker as a earpiece for outputting a voice signal received wirelessly as a reception voice. 6b and connected to.

The input operation identifying circuit 8 includes, for example, a call start key 3a and a call end key 3 serving as a power key.
b, a plurality of input keys 3a, 3b, 3c, 3d, such as a function key 3c capable of selecting and executing other various functions, a telephone number input key 3d of "0" to "9", and an e-mail key 30 Is connected. The e-mail key 30 can be selected by the function key 3c without making it independent.

When the e-mail key 30 is operated, the sub-keys are a voice input mode in which the voice recognition program is executed to input characters by voice-to-text conversion, and a key input mode in which characters are input by key operation as in a conventional mobile phone. Input mode changeover switch (not shown)
Are provided on the liquid crystal screen 20 which is the display unit 2. Either one can be selected by an arrow key 31 provided near the function key 3c.

In the voice input mode, as shown in FIG.
The voice is analog-input from the microphone 6a and converted from an analog signal to a digital signal via an analog-digital converter AD, and the digital signal is text-converted by the control circuit 4.

As described above, the speech recognition program chip 9 is connected to the control circuit 4, and the digitized speech data is collated with the stored speech data by the program stored in the chip 9. Then, the sound is determined, and this sound is converted into kana-kanji characters for each segment in accordance with the context and output to the display unit 2 via the display control circuit 7. When performing the kana-kanji conversion, a dictionary stored in the memory M is referred to.

In order to store the user's voice data for collating the digitized voice data, the user's voice is stored before the mail function is activated on the mobile phone 1. Preparatory work should be performed.

Further, in preparation for a case where an e-mail text is created by key input, the mobile phone 1 according to the present embodiment is provided with a function for immediately inputting a plurality of fixed texts and the like. Therefore, it is possible to immediately input a fixed long sentence with a simple key operation.

In addition, there is no restriction on the timing of operating the input mode changeover switch, so that switching from one of the voice input mode and the key input mode to the other mode is performed by character input. It is possible to switch arbitrarily at any time during the process.

Therefore, it is possible to use the key input mode and the voice input mode in combination when creating one e-mail text, and it is possible to more efficiently input a sentence by inputting in combination. This makes it possible to reduce the time required for creating a mail sentence.

By switching the mode with the input mode changeover switch, in places where character input by voice is inappropriate, text input can be performed by conventional key input. In any place where a voice may be emitted, a mail message can be easily created and transmitted.

Since a large memory area is used when speech-to-text conversion is performed by the above-described speech recognition function, the memory M can be added to the cellular phone 1 according to the present embodiment.

That is, as shown in FIGS. 1 and 2, the memory accommodating section 11 is formed to have a sufficient size of about 2/3 of the casing 10, and the pivot support section 11a provided at the lower end of the casing 10 is provided. It is foldable via. The mobile phone 1 is usually stored on the back of the housing 10 so that the mobile phone 1 can be used. When the memory M is replaced, the memory M is opened downward so that the memory M can be attached and detached.

Reference numeral 11b denotes an opening for attaching and detaching the memory M.
A slot (not shown) for mounting the memory M is provided at the back of 1b. Reference numeral 11c denotes a cover for the attachment / detachment opening 11b, which is formed of a flexible material such as rubber.

As described above, since the large-capacity memory M can be mounted, the voice-to-text conversion can be performed smoothly.

Further, since the memory storage section 11 is of a so-called flip type as described above, it is possible to avoid an increase in the size of the housing 10 and, furthermore, because the memory housing 11 is provided on the back of the housing 10, It doesn't get in the way when using it normally or while carrying it.

As the memory storage section 11, FIG.
As shown in (1), a configuration in which a dedicated slot 11d in which a dedicated memory M 'is detachably provided is provided in the housing 10, that is, a plug-in type used in a digital camera or the like. Here, a dedicated slot 11d is provided on the side surface of the housing 10. In the figure, reference numeral 11e denotes a cover for closing the dedicated slot 11d, which is also formed of a flexible material such as rubber. As for the other reference numerals, the same components as those of the embodiment shown in FIG. 4 are denoted by the same reference numerals.

The dedicated memory M 'is thin and small, and is desirably as large as possible. Note that the dedicated memory M 'may be selected from various existing memories so as to be compatible.

Further, a speech recognition program can be stored in the above-mentioned expandable memories M and M '.

That is, the speech recognition program may be chipped in the device as described above and mounted in advance, but if it can be stored in the memories M and M 'and can be detachably attached. For example, when there are a plurality of programs for voice recognition, it becomes possible to select a desired one and attach it to one's own mobile phone 1.

Further, it is also possible to store a large number of music pieces according to preference in the memories M and M 'and selectively use them as ringtones (ringtone melody).

The mobile phone 1 according to the present embodiment has a program for voice recognition as described above, and can perform voice recognition. , Which is a so-called voice navigation function.

Therefore, for example, when an e-mail is sent after a mail text has been written, a telephone operation of pressing the telephone number input key 3d or a key operation for calling a registered telephone destination is performed even when the telephone number of the destination is input. Even without the operation, the operation command can be executed by voice. in this way,
The mobile phone 1 according to the present embodiment has extremely good usability.

Also, even when the above-mentioned incoming melody is selected and set, the user can issue a predetermined command including a desired music title in a predetermined order by using the navigation function.
All you have to do is speak to 6a.

In the mobile phone 1 according to the present embodiment,
When a sentence is input by voice, that is, when a voice-to-text conversion is performed, if there is an erroneous recognition and / or erroneous conversion of voice in the content displayed on the liquid crystal screen 20 of the display unit 2, correct and reinput. Thus, a learning function for improving the accuracy of speech-to-text conversion is provided.

That is, by performing the learning related to the voice recognition function, the accuracy of voice-to-text conversion is improved, and as the number of times of use increases, accurate text input can be performed by voice. You can write in less time.

Further, in the present embodiment, taking advantage of the characteristic of being a mobile phone 1, in addition to the learning function described above, a learning function is executed in addition to the above-described learning function. The text of the user's call is converted to text and displayed on the LCD screen 20. After the end of the call, if there is an erroneous recognition and / or erroneous conversion of the voice in the displayed content, it is corrected and re-input. , To improve the accuracy of the voice-to-text conversion.

By providing such a learning function, learning can be performed at the time of a normal telephone call without reading a text for learning at a special time.
Moreover, since the mobile phone 1 is used overwhelmingly as a telephone, learning is inevitably repeated many times, and the user's voice (sound quality, intonation, ) Can be remarkably learned by further learning the features obtained by performing the preparatory work for storing the information, and the accuracy of the speech recognition rate and the conversion result can be significantly increased.

In particular, when creating a mail sentence with a lot of colloquial descriptions, which are spoken words that are difficult to recognize in voice recognition, it is extremely effective to use the contents of a normal telephone call as learning material.

In the present embodiment, the setting is made so that the content of the call is not converted entirely, but only within a predetermined time.

Also, the learning is not performed for each call, but in conjunction with the timer T, a limit on the number of times, such as performing only the first call or twice a day, is set. It is also possible.

As described above, by providing a learning function for speech recognition, the task of creating an e-mail by speech-to-text conversion becomes much smoother and speedier. Sentence input by voice can be performed without feeling any stress.

Therefore, anyone can use and enjoy the e-mail while enjoying it, and the value of use as a communication tool can be enhanced.

Here, a speech-to-text conversion process is performed based on a speech recognition program, and the portable telephone 1 according to the present embodiment is processed.
Fig. 6 shows the operation flow up to the actual transmission of the e-mail
It will be described based on. The power of the mobile phone 1 is already on.

First, when the e-mail key 30 of the mobile phone 1 is operated (S1), the display control section 7 performs a mail screen activation process, and a mail screen is displayed on the display section 2 (S1).
2).

Then, an input mode changeover switch is displayed on the mail screen, and when the voice input mode is selected (S
3) The analog voice can be converted to a digital signal. If a mail sentence is input from the microphone 6a, the analog-to-digital converter AD converts the analog signal to a digital signal (S4). At the same time (S5), the converted contents are displayed on the liquid crystal screen 20 (S6). If there is an error in the conversion contents, the LCD screen 20
Of the mobile phone 1 according to the present embodiment has a learning function as described above. Therefore, the conversion accuracy is considerably high, and the correction processing is minimized.

In step S3, when the key input is selected (S7), or when the input mode changeover switch is selected during the text input in the voice input mode (S8), the key input is performed. You can easily input fixed phrases. Then, these mode switching operations are repeated as appropriate, and a desired mail text can be input in a short time by appropriately combining the input modes.

When the mail text is determined, mail transmission is performed by a predetermined key operation or voice navigation (S9), and in response thereto, the control circuit 4 transmits the determined mail text to the mail destination (S10).

When an end signal is input by operating the e-mail key 30, the control circuit 4 performs an end process (S11).

Note that the speech recognition program is stored in the memory M
In this case, it is preferable that the memory M can be appropriately downloaded and updated from a voice recognition program download server connectable to the base station of the mobile phone 1.

Further, the present invention is not limited to the portable telephone 1, but is equivalent to such a portable telephone in view of the object effect of the present invention, for example, PHS (Personal HandyPh).
On System) can also be applied to other mobile communication devices. Further, the configuration of the mobile phone 1, particularly the shape and arrangement of the input keys 3a, 3b,.
The shape and the like of the memory storage section 11 are not limited to the embodiments described above.

[0103]

According to the present invention described above, when an electronic mail is transmitted from a mobile communication device such as a cellular phone, the electronic mail can be easily converted by voice-to-text conversion without inputting a text by a troublesome key operation. Anyone can easily send an e-mail.

[Brief description of the drawings]

FIG. 1 is a perspective view showing a mobile phone as a mobile communication device.

FIG. 2 is an explanatory diagram of a memory storage unit provided in the mobile phone.

FIG. 3 is a functional block diagram showing an electrical configuration of the mobile phone.

FIG. 4 is a conceptual diagram of a speech-to-text conversion process.

FIG. 5 is an explanatory diagram showing a modification example of a mobile phone.

FIG. 6 is a flowchart of a voice / text conversion process.

[Explanation of symbols]

 M, M 'memory 1 Mobile phone 2 Display unit 3 Operation unit 4 Control circuit 5 Transmission / reception unit 11 Memory storage unit

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat ゛ (Reference) G10L 15/28 G10L 3/00 521S H04M 11/00 302 571K 521A

Claims (8)

[Claims] 1. A mobile communication device having a telephone call function and a function of transmitting and receiving an electronic mail. The mobile communication device is provided with a voice recognition function to enable voice-to-text conversion, input text by voice, and input text. A mobile communication device characterized in that the mobile communication device can transmit an electronic mail as an electronic mail. 2. A display unit for displaying a text-to-speech-converted sentence. If there is an erroneous speech recognition and / or erroneous conversion part in the displayed content, the part is corrected and re-input, thereby providing
2. The mobile communication device according to claim 1, further comprising a learning function for improving the accuracy of the voice-to-text conversion. 3. During a call, the contents of a call input from a microphone are converted to text so that text can be displayed on a display unit, and if there is an erroneous speech recognition and / or erroneous conversion part in the displayed contents,
The mobile communication device according to claim 1 or 2, further comprising a learning function for improving the accuracy of speech-to-text conversion by correcting and re-inputting the text. 4. The mobile communication device according to claim 1, wherein the whole operation of the device can be performed by voice. 5. The mobile communication device according to claim 1, wherein a memory can be added. 6. The mobile communication device according to claim 5, wherein a voice recognition program can be stored in a memory. 7. An input mode changeover switch capable of switching between a voice input mode for inputting characters by voice text conversion and a key input mode for inputting characters by key operation. The mobile communication device according to claim 1. 8. A voice input mode and a key input mode.
8. The mobile communication device according to claim 7, wherein switching from one mode to the other mode can be arbitrarily switched during character input.