JP2664679B2 - Communications system - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION [Object of the Invention] (Industrial application field) The present invention relates to a communication system capable of effectively performing a so-called videophone or videoconference by transmitting an image signal and an audio signal. (Prior Art) Videophone systems and videoconferencing systems use a telephone conversation or a conference call between parties located at a distance from each other, and use the image communication technology to image the face of the party and the surrounding scene. It is realized while displaying, and its usefulness is attracting attention. FIG. 4 is a diagram showing a schematic configuration of a video telephone system of this type, and FIG. 5 is a diagram showing a schematic configuration of a video conference system. In each of these figures, a video telephone 1 and a video conference device 2 are input devices including a TV camera for capturing and inputting the face of the party (user) and the surrounding scene, and a microphone for inputting a conversation voice spoken by the party. Unit, a communication unit for transmitting the input signal to the other party and receiving the signal transmitted from the other party, an output comprising a TV monitor for displaying the received image signal as an image and a speaker for outputting the audio signal as sound. And a unit. The difference between the video telephone 1 and the video conference device 2 is as follows.
This is the difference between performing so-called one-to-one communication for one party or communicating with multiple parties and communicating with each of them, and there is no essential difference. The videophone 1 or the video conference device 2
Is connected to the exchange 4 via a predetermined transmission line 3 such as a subscriber line. Information communication between the video telephones 1 and between the video conference devices 2 is performed under communication control by an information center 6 that connects these exchanges 4 via a predetermined transmission path 5. The information center 6 is composed of a central control device having various data files. For example, the information center 6 performs accumulation control of communication image signals, accumulation control of communication audio signals, and the like, and controls exchange of the image signals and audio signals. And so on. According to the system thus configured, the TV
An image of the face of the party or the surrounding scene is input using a camera or the like, and the image is communicated and displayed on a TV monitor or the like at the communication destination. At the same time, the conversation voice uttered by the party is input via a microphone. This is transmitted together with the image signal, and is output as sound from a speaker at the communication destination. The transmission of the image signal and the audio signal is mutually communicated between the parties. As a result, it is possible to have a conversation while confirming the facial expression of the communication partner and the surrounding circumstances, and for example, by communicating information between the parties by means of information expression including gestures and hand gestures, it is possible to communicate effectively. It is possible to hold telephone calls and conferences. (Problems to be Solved by the Invention) However, if there is a difference in the language used between the communication parties, communication between the parties is attempted even though the videophone system or the video conference system has the above-mentioned advantages. This is extremely difficult, and is an obstacle to facilitating communication. The present invention has been made in view of such circumstances,
Its purpose is to make full use of the advantages of the videophone system and videoconferencing system, and to effectively communicate with each other without having to worry about differences in the language used between the parties. An object of the present invention is to provide a communication system capable of making a call. [Configuration of the Invention] (Means for Solving the Problems) The present invention relates to an image communication system for transmitting an image signal captured and input by an imaging device and displaying the image signal on an image display device, and imaging of the image signal. A voice communication system for inputting voice at the time of input, transmitting the voice signal, and outputting voice.
In a communication system such as a videophone system or a video conference system in which the image signal and the audio signal are transmitted by communication between terminals connected to each other via a transmission line, input audio is input to the audio communication system. Translation means for translating
A voice memory for temporarily storing the translated voice signal translated by the translation means; and a means for sequentially reading and transmitting the translated voice signal stored in the voice memory. An image memory in which a signal is converted into a still image of a predetermined cycle and temporarily stored, and a translated voice signal stored in the voice memory are sequentially read out and transmitted, and are stored in the video memory in synchronization with the transmission. Means for sequentially reading out and transmitting the still images which are present. (Operation) According to the present invention, an audio signal input together with an image signal is translated into a predetermined foreign language, a translation audio signal as a translation result is temporarily stored in an audio memory, and the image signal is transmitted at a predetermined period. When converted to a still image and temporarily stored in an image memory, and sequentially reading and transmitting the translated voice signal stored in the voice memory, the translated voice signal is stored in the image memory in synchronization with the read output of the translated voice signal. By performing the synchronous control for sequentially reading and transmitting the still images, the time lag between the translated audio signal and the corresponding image signal caused by the time required for the translation processing on the input audio signal is corrected. As a result, the obstacle of the conversation caused by the difference in the language used is eliminated. In addition, since the image-communicated information is displayed in synchronization with the translated and outputted voice, the expression, the gesture and the hand gesture of the communicating party displayed as the image can be correlated with the translated and outputted speech. For this reason, it is possible to perform effective conversation communication and conference call by achieving communication between the communication parties and facilitating communication. Hereinafter, an embodiment of the present invention will be described with reference to the drawings. FIG. 1 is a schematic configuration diagram of an embodiment system. The same parts as those of the conventional system shown in FIGS. 4 and 5 are denoted by the same reference numerals and described. The video telephone 1 or the video conference device 2 basically includes a TV camera 11 for capturing and inputting the face of the party (user) and the surrounding scene, a microphone 12 for inputting a conversation voice uttered by the party, and an image signal for the image. TV monitor to display 13,
Each of them is provided with a speaker 14 for outputting an audio signal. The image signal captured and input by the TV camera 11 and the audio signal collected by the microphone 12 are respectively converted into electric signals of a predetermined format, transmitted and output to the transmission path 3, and used for signal transmission. An image signal received via the transmission path 3 is provided to the TV monitor 13 and output as an image, and a received audio signal is applied to a speaker 14 and output as audio. Here, this system is characterized in that the video signal and the audio signal are communicated between the video telephone 1 and the video conference device 2 via the exchange 4 from the transmission line 3 and further via the transmission line 5. The information center 6 that performs communication control is configured as follows. That is, as shown in FIG. 1, the information center 6 in the present system temporarily stores an image signal to be used for communication, and stores an image memory 21 for controlling the timing of reading the image signal, and an audio signal to be used for communication. An audio memory 22 for temporarily storing and controlling the readout timing, and a translator for inputting the audio signal stored in the audio memory 22 and translating it into another language
23, and a control unit 24 that controls the operation of these units. The translation processing of the input voice by the translator 23 is performed under the instruction of the control unit 24, and translates Japanese into English and English into Japanese, for example. This translator 23
As shown in FIG. 2, for example, a speech recognition unit 31 for recognizing input speech, a translation processing unit 33 for machine-translating linguistic information indicated by the recognition result into another language using a translation dictionary 32,
The voice synthesizer 34 obtains the voice signal based on the translated language information. Note that the speech recognition unit 31, the translation processing unit 33, and the speech synthesis unit 34 are realized by appropriately adopting various information processing techniques conventionally proposed. Specifically, for example, a voice recognition unit
31 is realized using a continuous utterance / unspecified speaker speech recognition device. The speech synthesis unit 34 is realized as a speech synthesis device that performs regular synthesis of speech according to phoneme parameters and prosody parameters obtained from an input character string. Further, the translation processing unit 32 analyzes the input sentence indicated by the character string for each word, and
This is realized by a machine translation apparatus that generates a translated sentence corresponding to an input original sentence by performing a syntactic analysis, a semantic analysis, a dependency test, and the like using 32. Thus, when a difference in the language used is instructed by the communicating parties, the control unit 24 activates the translator 23 to translate the voice signal communicated between the languages into the above-mentioned language and output the translated signal. As a result, for example, when a voice signal "I am ..." is input as Japanese voice, the translator 23 reads this voice signal from the voice memory 22 and executes a translation process. Then, the translated voice signal "I am ..." of the English sentence obtained by this translation process is rewritten in the voice memory 22. As a result, the translated voice signal is read out from the voice memory 22 and communicated, and is output from the speaker 14 as voice. The translation output from the English voice to the Japanese voice is performed in the same manner. By the way, when the audio signal is translated and communicated in this way, a time lag occurs between the audio signal and the image signal due to the translation processing time. Therefore, in this system, an image signal to be communicated is, for example, 30 still images per second, and this still image is transmitted and output in order. Then, this still image signal is sequentially stored in the image memory 21,
The audio signal is output in synchronization with the reading of the audio signal from the audio memory 22. That is, when communication control is performed without translating a voice signal to be communicated, the still images are sequentially read in synchronization with the reading of the voice signal to the communication destination. When the audio signal is translated and communicated, the above-described translation processing is completed, and when the translated audio signal is read from the audio memory 22, a still image is output in synchronization with the translation. As a result, as shown schematically in FIG. 3, the image signal and the audio signal are always communicated in association with each other.
Therefore, it is possible to have a conversation between parties using different languages without causing the linguistic obstacle, and to effectively read the expression of the communication partner from the image corresponding to the voice. Becomes possible. Therefore, it is possible to perform a telephone conversation and a conference call with good communication characteristics in which communication is achieved. Note that the present invention is not limited to the above-described embodiment. For example, a translation processing function and a function of synchronizing an audio signal and an image signal may be provided in the videophone 1 or the video conference device 2. Also, the translation processing method, the synchronization control method, and the like can be variously modified. In short, the present invention can be variously modified and implemented without departing from the gist thereof. [Effects of the Invention] As described above, according to the present invention, when a voice signal is communicated, the voice is translated and output, and the voice is input in correspondence with the input voice in synchronization with the translation output of the voice. The displayed image is displayed. Therefore, it is possible to have a conversation without causing a linguistic obstacle even between communication parties having different languages. Also, since the image is displayed in association with the translated audio output,
It is possible to obtain an effect such that it is possible to communicate with good communication while accurately grasping the current situation from the facial expressions, gestures, and hand gestures.

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a schematic configuration diagram of a system according to an embodiment of the present invention, FIG.
The figure shows a configuration example of a translator in the embodiment system,
FIG. 3 is a diagram showing a relationship between an image signal and an audio signal, FIG. 4 is a configuration diagram of a conventional video telephone system, and FIG. 5 is a configuration diagram of a conventional video conference system. DESCRIPTION OF SYMBOLS 1 ... Video telephone, 2 ... Video conference equipment, 3 ... Transmission path, 4 ... Switching equipment, 5 ... Transmission path, 6 ... Information center, 11 ... TV camera, 12 ... Microphone, 13 ... TV
Monitor, 14 speaker, 21 image memory, 22 voice memory, 23 translator, 24 control unit, 31 voice recognition unit, 32 translation dictionary, 33 translation processing unit , 34 ... Voice synthesis unit.

Claims (1)

(57) [Claims] An image communication system that transmits an image signal captured and input by an imaging device and displays the image signal on an image display device, and an audio communication that inputs audio when the image signal is input and transmits the audio signal and outputs the audio. A communication system in which the image signal and the audio signal are transmitted by communication between terminals connected to each other via a transmission line, wherein the audio communication system translates the input audio. And a means for sequentially reading and transmitting the translated voice signal stored in the voice memory, and a voice memory for temporarily storing the translated voice signal translated by the translation means. Is synchronized with the image memory in which the image signal is converted into a still image of a predetermined cycle and temporarily stored, and the translated voice signal stored in the voice memory is sequentially read and transmitted. Communication system, comprising the means for sequentially transmitting reads the still image stored in the image memory. 2. The translation means includes a speech recognition means for recognizing the input speech, a translation processing means for machine-translating the recognition result of the speech recognition means into a predetermined foreign language, and a speech synthesis of the translation result of the translation processing means. 2. A speech synthesizing means for outputting a translated speech signal.
A communication system according to claim 1.