JP4232453B2 - Call voice text conversion system - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a text conversion system for call voice that can improve the accuracy of information transmission when a telephone call is made.
[0002]
[Problems to be solved by the invention]
When making a call using a mobile phone etc., it may be difficult to hear the other party's voice depending on the usage environment and location, and it may be difficult to communicate, such as listening back and forth to grasp the contents of the call. There is. Although it can be expected that such problems can be solved by improving communication technology, there are cases in which it cannot be solved immediately.
[0003]
In addition, it may be difficult for elderly people and people with hearing impairments to communicate not only with communication technology but also with normal transmission of voice information. In addition, there are cases where the speaker is careless, forgets to talk on the phone, and there is a case where the exact memory is lost, etc. was there.
[0004]
The present invention has been made in view of the above circumstances, and its purpose is to make it easier to understand what the other party is saying when making a telephone call and to facilitate communication. An object is to provide a text conversion system for call voice.
[0005]
[Means for Solving the Problems]
According to the first aspect of the present invention, when a speaker inputs a call voice during a conversation using a telephone, the call voice is transmitted to the other party, and the call voice is subjected to a voice recognition process by the text conversion means. Since it is converted into text data and the volume information adding means adds information for specifying the character size according to the volume of the call voice, the speaker can display the call volume of the other party by displaying the information on the display means. You can see text expressed in character size proportional to. As a result, even when it is difficult to hear or when it is missed, information for recognizing the other party's call status increases from the text information, and communication is facilitated.
In addition, the text data transmission means can send the text data when the call is made after the call as an e-mail upon request, so that the contents of the call can be recorded as a record, and the state of the call You will be able to understand it with supplementary information.
[0006]
According to the second aspect of the invention, in the first aspect of the invention, the emotion estimation means obtains the speaker's emotion that can be analyzed by calling voice, and the emotion information addition means adds the emotion information to the text data. By displaying the information, the speaker can understand and respond to emotions appearing in the other party's call voice, and recognize the other party's call status from the text information even when it is difficult to hear or missed. This will increase the amount of information needed to communicate, making it easier to communicate.
[0007]
According to the invention of claim 3, in each of the above inventions, the speaker information adding means adds speaker display information for displaying the converted text data corresponding to each speaker to the text data. Even in the case of being missed, information for recognizing the other party's call status increases from the text information, making it easier to communicate.
[0009]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, an embodiment in which the present invention is applied to a system using a mobile phone will be described with reference to the drawings.
FIG. 1 schematically shows the overall configuration of a system. Cellular phones 1a and 1b can be connected to a telephone network 3 via base stations 2a and 2b, etc. It is configured to make a call with a wired telephone.
[0010]
The exchange 4 is connected to a server 5 as a text data converter, which is a volume information adding means, an emotion information adding means, a speaker information adding means, and a text data transmitting means in the present invention. It has a function. The functions of these means are realized by executing software to be described later on the server 5.
[0011]
The server 5 can access mail servers 7a, 7b and the like operated by various providers via a network such as the Internet 6. The mail servers 7a and 7b can be accessed from personal computers 8a and 8b possessed by a user such as the mobile phones 1a and 1b via the Internet 6.
[0012]
Next, the operation of the present embodiment will be described with reference to FIGS.
FIG. 2 shows a basic operation when voice information is converted into text data and displayed. An example will be described in which a speaker A who uses the mobile phone 1a calls a speaker B who uses the mobile phone 1b.
[0013]
When user A calls mobile phone 1b of user B using mobile phone 1a, he / she can talk to mobile phone 1b from base station 1a, communication network 3, and exchange 4 via base station 1b. become. Server in this state, first, when the speaker A speaks a "hello" in the voice input (step A1), the voice information is outputted as sound transmitted to the mobile phone 1b (step A2), from the exchange 4 5 is converted into text data in the server 5.
[0014]
The server 5 first performs voice recognition processing on the received voice input signal (step A3), and converts it into text data (step A4). At this time, the server 5 performs input voice analysis processing as will be described later on the received voice input signal, and adds data relating to volume, emotion, and the like (see FIG. 3). Then, the text data and additional information obtained through this analysis process are transmitted to the mobile phone 1b of the speaker B who is the listener and the mobile phone 1a of the speaker A who has inputted the voice (step A4).
[0015]
Thus, the cellular phone 1a, in 1b, so to display the words of a text data respectively received "Hello" display unit 9a, the 9b (see Figure 2 step A5, A6 and the display example). At this time, since the display on the mobile phone 1a side is the text data of the words spoken by itself, the character “self” indicating itself is displayed at the beginning of the text data, and the display on the mobile phone 1b side is: Since it is text data of the words spoken by the other party, characters of “phase” indicating the other party are displayed at the top of the text data.
[0016]
Next, when the speaker B answers this and, for example, makes a voice input to the mobile phone 1b saying “Here is” (step A7), the voice information is transferred from the mobile phone 1b to the mobile phone 1a in the same manner as described above. Is output as a voice (step A8), and is converted into text data in the server 5.
[0017]
The server 5 performs voice recognition processing and text data conversion processing (steps A9 and A10), and the obtained text data and additional information of the speaker B who is the listener and the speaker B who has input the voice are input. Both are transmitted to the mobile phone 1b (step A10).
[0018]
In the cellular phones 1a and 1b, the word “here is”, which is text data, is displayed on each display unit (see steps A11 and A12 in FIG. 2 and the display example thereof). Further, in the respective displays on the cellular phones 1a and 1b, the characters “phase” and “self” are displayed at the head of the text data.
[0019]
Next, in the text conversion processing executed by the server 5 in steps A4 and A10 described above, processing for performing input speech analysis processing and adding data relating to volume, emotions, etc. will be described with reference to FIG. In this analysis process, the server 5 first performs a volume analysis process on the input voice data (step B1).
[0020]
Here, the volume level of the input voice is calculated and discriminated by a predetermined threshold value to discriminate the volume from three levels of small, medium and large. According to the determined result, the character size of the corresponding text is set as additional information to the text data so as to be small, medium and large (steps B2 to B5).
[0021]
When this additional information is set in the text data, when displaying on the display unit described above, if the display unit can be displayed with the character size set, this corresponds to the additional information. Can be displayed in character size. Here, “medium” of the character size corresponds to a normal conversation level.
[0022]
Next, the server 5 performs emotion analysis processing (step B6). This is to analyze the tone of the input speech and estimate the emotion of the speaker. Specifically, the emotion analysis processing itself is, for example, analyzing words that represent emotions such as emotions, emotional inflection patterns, voice waveform patterns, and differences in voice levels relative to normal times. Can be estimated.
[0023]
Here, the server 5 has five estimated emotion classifications of “joy”, “anger”, “sorrow”, “easy”, and “normal” (step B7). Corresponding to these, information is added so as to set the character color to "yellow", "red", "blue", "green" or "black" (steps B8 to B12).
[0024]
The result of such an analysis is added as additional information to the text data. The display unit 9a capable of displaying this additional information performs a display operation as shown in FIG. 4, for example. In addition, in a display portion where additional information cannot be displayed, characters of a normal size are used for display.
[0025]
In the figure (a), when the other party is speaking in a troubled tone (corresponding to “sorrow”), this (yourself) is answering in an angry tone (corresponding to “angry”). ing. After the "phase:" display S1 indicating the opponent, the surprised state is displayed with a large black character size indicating "normal", and the "Uh" display S2 is displayed, followed by a blue color indicating the "sad" state The display S3 is displayed with the character size of “It is not a problem”.
[0026]
Correspondingly, after “Self:” display S4 indicating oneself, “Do n’t say that” with red character indicating angry tone, display S5, “Red” with large character size in red character is displayed. "S6", a red letter and a "Dayo" display S7 with the middle character size. In this way, the color changes according to the emotion and the character size changes according to the loudness of the voice, so that it is easy to understand the tone of the other party visually.
[0027]
On the other hand, FIG. 5B shows a case in which the content of conversation spoken with a pleasant tone is shown. After “Self:” display S8, a “passed” display S9 is displayed with a large yellow character size indicating a “joy” state. In response to this, after “phase:” display S10, “joy” is displayed. A “good” display S11 is displayed with the character size in yellow indicating the state.
[0028]
The server 5 is configured to perform a mail delivery service in addition to the above-described real-time processing. This is because a request for a mail service is received from speakers A and B who are users of the mobile phones 1a and 1b in advance, or a request for a mail delivery service that can be set for each call is received. It is to be implemented when there is.
[0029]
In this method, the call voice as described above is voice-recognized and converted into text data, and then the speaker information is added to send it as a normal mail. At this time, volume information and emotion information can be added to the text data and transmitted as it is. For example, the mail is distributed via the Internet 6 to the mail servers 7a and 7b of the providers contracted by the speakers A and B, and can be viewed by downloading from the PCs 8a and 8b.
[0030]
This makes it possible to read the content of the call while confirming the loudness and emotions of the actual call, making it easier to understand the atmosphere and situation of the place, or taking notes of the call record. Even if it is not, it can be confirmed later by the received mail, and the communication information can be made accurate.
[0031]
The mail delivery destination is not limited to the PCs 8a and 8b, but may be set to, for example, a PDA that is a mobile device or a car navigation device that can access the Internet. Furthermore, it may be delivered by e-mail to the mobile phones 1a and 1b themselves.
[0032]
According to the present embodiment as described above, the content of the conversation with the other party can be obtained as character information by performing the voice recognition process and the text data conversion process by the server 5 connected to the exchange 4. Even if it is difficult to hear, it becomes possible to reliably grasp the contents of the call by referring to the text information. In addition, since the size and color of the characters can be changed according to the volume and emotion of the call voice, it becomes easier to grasp the situation at the time of the other party's call and to facilitate communication.
[0033]
In addition, since the call contents can be confirmed later as text information by e-mail, it is more reliable when leaving a call record, and it is not necessary to take notes, so that you can concentrate on the conversation. Become.
[0034]
The present invention is not limited to the embodiment described above and shown in the drawings, and can be modified as follows.
In addition to color, emotion information can also be expressed by a character pattern, character thickness or character line type, and character shading pattern.
[0035]
The color indicating emotion information can be displayed as the background color of the character or the color of the marker in addition to the color of the character itself.
Emotion information can be transmitted directly to the other party by operating a button indicating the mood when speaking by operating a setting switch or the like on the speaker side.
[0036]
For additional information that expresses emotion or volume, a function for setting a non-display function may be provided.
You can also hide your own conversations. This may be set by a switch.
[0037]
The medium for receiving text data by e-mail is not limited to a PC, and an appropriate medium such as a PDA or another mobile phone can be designated and received.
[Brief description of the drawings]
FIG. 1 is a schematic diagram of an overall configuration showing an embodiment of the present invention. FIG. 2 is a chart showing exchanges between mobile phones and servers. FIG. 3 is a schematic flowchart of volume analysis processing and emotion analysis processing. FIG. 4 is a diagram showing an example of a display screen.
1a and 1b are mobile phones (telephones), 2a and 2b are base stations, 3 is a telephone network, 4 is an exchange, 5 is a server (text conversion means, volume information addition means, emotion estimation means, emotion information addition means, talk Person information adding means), 6 is the Internet (network), 7a and 7b are mail servers, 8a and 8b are PCs, and 9a and 9b are display units.

Claims (3)

A text conversion means for inputting a call voice of a speaker who talks through a telephone, converting the voice into speech data by performing voice recognition processing;
Volume information adding means for analyzing the volume of the call voice and adding character size information specifying the character size according to the volume to the text data ;
Display means for displaying the text data on the telephone during a call;
A text conversion system for call voice, comprising: text data transmission means for transmitting the text data as an e-mail upon completion of the call in response to a request . The text conversion system according to claim 1,
Emotion estimation means for estimating a speaker's emotion that can be analyzed from the call voice;
A text conversion system for call speech, comprising: emotion information adding means for adding emotion information specifying a color or pattern according to the emotion of the speaker estimated by the emotion estimation means to the text data . In the call voice text conversion system according to claim 1 or 2,
A text conversion system for call voice, comprising: speaker information adding means for adding speaker display information for displaying the converted text data corresponding to each speaker to the text data.

Images