JP2003509712A - Personal information system for wireless transmission and reception of speech information - Google Patents

Abstract

The invention relates to a personal information system, especially a personal guide system, for transmitting voice information of a speaker on wireless paths to a number of listeners. According to the invention, a voice recognition unit (SE) for identifying the source information of the speaker's source language, a translating unit (U) for translating source information into target information of the target language, and a voice generator unit (SG) for generating the target language from the target information are provided in the signal path between a microphone (M) of the speaker and the headphones (H) of the listeners.

Description

Detailed Description of the Invention

TECHNICAL FIELD The present invention transmits and receives the speech information from a speaker's microphone to a listener equipped with a receiver and a sound reproducing transducer for receiving a wireless transmission signal of the transmitter through the transmitter. Personal information system, especially a personal guide system.

(Background Art) A guide (speaker) wears on the body and transmits by a wireless microphone, and each individual of the guided group receives a high-frequency receiver, and explains to the guide, for example, city guide. A personal group guide system for listening to is known. In this way, multiple people can be simultaneously explained in one language. In the case of another language, for example, a city guide will speak in that language, or another person will speak in that language, in which case different languages will be transmitted and received at different transmission and reception frequencies at the same time. Become. Such a system is commercially available from Sennheiser, Inc. as consisting of a SKM1081 type wireless microphone and an EK1031 type receiver.

Infrared operated multi-channel interpreter systems are also known, such as the Sennheiser Infraport 1029 system. In this case, the speaker's voice is sent to multiple interpreters, which are translated at the same time. afterwards,
Each language is sent separately to the multi-channel infrared transceiver. Although the listener wears a multi-channel receiver, he or she listens to the explanation by selecting a favorite language from a plurality of languages simultaneously transmitted by frequency selection. Such a system can also be viewed as a multi-channel radio frequency system and the selection will be made according to time slots (DECT).

Data capable of evaluating a spoken word, for example, an automatic language recognition device for converting it into automatic typing is already on the market (for example, "ViaVoice" from IBM). Also, regarding an automatic translation system that automatically translates text or speech signals into other languages,
The research is being done.

In these conventional methods and systems called group individual guidance system and multi-channel interpreter system, a multilingualist who guides the group and a plurality of guides who can speak in different languages are required. Personnel costs are high. Moreover, a complicated transmission / reception system is required. The automatic language recognition systems developed to date require expensive computer systems and software,
Although it translates written text automatically, it has a limited finish and requires modification.

US Pat. No. 4,882,581, for example, when a participant in a conversation asks a wireless device a question, it is transmitted wirelessly to a translation computer, which is then translated by the computer and then wirelessly by the speaker's participant radio. A conversation interpreting method is disclosed in which, while being transmitted to a device, a description translated in another language is output from the wireless device. Another participant involved in the conversation hears the translated question and answers in the language he / she uses, but the answer is also wirelessly translated into a computer, and the participant who is the questioner on that computer. After being translated into the interrogator's language, it is wirelessly transmitted again to the interrogator's participant to obtain an answer in the interrogator's participant's language.

German Patent No. 19580018 discloses a communication device in which a radio telephone and an electronic translator for translating a starting language into two intermediate translation languages are incorporated. This intermediate translation language is adapted to be converted into a second language there after being transmitted to another communication device.

DISCLOSURE OF THE INVENTION (Technical problem to be solved by the invention) An object of the present invention is to construct a personal information system for transmitting and receiving speech information as described at the beginning of the specification of the present application, and Equipped to provide a personal information system that can automatically translate source language speech into one or more target languages, thereby eliminating the need for interpreters. In this sense
A device suitable for that purpose is one which is as compact as possible in structure and can be integrated in a speaker or listener device.

(Solution) [0009] A speaker equipped with a receiver and a sound reproduction transducer (for example, a headphone) that receives a wireless transmission signal from the transmitter transmits / receives the speech information from a microphone of a speaker via the transmitter. In the personal information system for doing so, the above-mentioned object can be achieved by configuring the personal information system according to the present invention as follows.

That is, in the signal path between the speaker's microphone and the listener's sound reproduction transducer, a speech recognition device for recognizing the source information in the source language emitted by the speaker and the source information in the target language. And a speech generator for generating a target language from target information. The automatic conversion from the source language emitted by the speaker to the target language of the listener uses the conventional speech recognition device and the speech generator, and the conversion into other languages converts the recognized source information into This is possible because it is done by translating it into the target information and not directly converting from the source language to the target language.

[0011] Preferably, not only is the translated speech information provided to a specific listener in parallel with the speech recognition device, the translation device, and the conversion path of the speech generator, but also not translated to a part of the listeners. In order to obtain the original speech information, a direct signal path for unchanged transmission and reception of speech information is provided. A simple listening device is provided for people who hear the original speech information.

The devices used in this respect as a speech recognition device, a translation device, and a speech generator are relatively space-saving due to the use of microelectronic technology, and therefore preferred embodiments of the present invention As a result, the devices are incorporated in the listening device, and in another preferred embodiment, they are incorporated in the speaker side, that is, the utterance device. This has the advantage that the three types of devices can be prepared as a single unit. Since the listening device is configured for one target language, for example, when it is necessary to translate into a plurality of languages, the listening device is provided to each of a plurality of listeners. However, by enabling the listening device to handle multiple target languages,
It is also possible to allow the listener to switch by a switch operation.

The speaking device and the central unit preferably allow for multiple target languages, in which case the transmitter allows multiple object languages, including the source language, to be multiplexed.

The system according to the invention is preferably constructed as a personal guide system for simultaneously translating the speech information given by the guiding guide into a plurality of languages and transmitting it to individual listeners. . However, according to the principle of the present invention, the language of the speaker or the creator is automatically translated into a plurality of languages and transmitted to the listener, and at the same time, the listener selects a desired language to be written by himself. Any information system can be constructed as long as it can be constructed.

It is desirable to perform transmission and reception between the transmitter and the receiver by using high frequency so that transmission and reception can be performed without a gap even if an obstacle is present in the middle. However, if there is no obstacle between the speaker and the listener, it is possible to transmit and receive with an infrared signal, and it is also possible to provide a parallel transmission / reception path by some method. In the case where the speech recognition device, the translation device, and the speech generator are provided in the listening device, and the transmission and reception between the transmitter and the receiver are performed at high frequency, the system according to the present invention operates as the listening device. It can be considered to be used for transmitting / receiving broadcast to / from a broadcast receiver. In this case, as far as speech is concerned, the speech recognition device receives the speech information from the received signal, this speech information is converted into target information in a language selectable by the translator and thus converted into the target language by the speech generator. It is necessary to configure the broadcast receiver in. In the case of the broadcast receiver of this configuration, in a foreign country, the received speech signal can be converted into a desired language as described above in order to understand news or news in a foreign language, for example.

In the personal information system according to the present invention, the source information is obtained at the output of the speech recognition device, and the translated target information is obtained at the output of the translation device. Therefore, in another embodiment of the present invention, An output device for outputting encrypted source information or target information can be connected in order to output the recognized information or the translated information, respectively. The output device may be, for example, a display device or a printer.

(Best Mode for Carrying Out the Invention) Other advantages and detailed configurations of the present invention will be apparent from the following description given with reference to the accompanying drawings. In the first embodiment shown in FIG. 1, the utterance device SPE is provided with a microphone M and a transmitter S equipped with an antenna A. Each of the plurality of listening devices HE1 and HE2 is provided with a receiver E connected to an antenna A, a speech recognition device SE, a translation device U, and a speech generator SG, to which headphones or earphones A are connected. . Instead of the headphones or the earphone A, it is possible to use an appropriate sound reproducing transducer such as a loudspeaker or a speaker.
In each of the listening devices HE1 and HE2, the receiver E receives the source language from the utterance device SPE and the speech recognizer SE delivers the source information. This source information is translated into target information in the target language by the translator U, then converted into the target language in the speech generator SG, and then reproduced by the headphones or earphones H.

Since each of the listening devices HE1 and HE2 is configured to correspond to only one target language, each listener is provided with a listening device HE corresponding to a different language. However, since the translation device U is configured to convert the target information in different languages, the listener operates the selection switch W to select each target language. The number of hearing devices HE1 and HE2 is practically unlimited.

The embodiment shown in FIG. 2 is different from the above-described first embodiment in that a speech recognition device SE, a translation device U, a speech generator SE and the like are provided in a speech device SPE. . The transmitter S is configured to transmit a plurality of target languages and is configured to transmit information in a multiplex transmission mode such as a frequency multiplex transmission mode or a time multiplex transmission mode. Since this listening device HE has a simpler configuration than the listening device in the first embodiment, the translation of the speech information is not performed by this listening device HE, and the information received by the receiver E is sent to the headphones or earphones. It just needs to be sent. In this case, each device and the ideal value HE may be configured so as to correspond to the target language so that different listening devices HE can be distributed. More preferably, each listening device HE selectively receives a different language so that the listener can select a desired language by operating the selection switch W.

In the two embodiments shown in FIGS. 1 and 2 respectively, a short circuit O is introduced into the system as indicated by the broken line in order to additionally transmit the original language from the speech device to the listening device. It is provided so that the original language can be provided to each listener. Such variations are particularly desirable in the case of guided tourists and other events, as there are circles in which one language, especially the native language, is predominantly used. The listener's information may be directly transmitted to such a listener so that the listener can carry a simple listening device, for example, the listening device as shown in FIG. In this case, it is preferable to use the system of FIG. 1 in which the transmission / reception electronic circuits are provided in the listening devices HE1 and HE2, and on the other hand, the listener who does not need translation uses the simple listening device HE as shown in FIG. It shall be used.

In the embodiment of FIG. 1, the utterance device SPE, the microphone, the transmitter S, etc. can be housed in a common housing, from which the antenna A can be pulled out. Wireless microphones are also well known. The listening device HE in this embodiment includes not only the receiver E and headphones or earphones H, but also an electronic device such as a speech recognition device SE, a translation device U having a selection switch W, and a speech generator SG. May be. These devices are preferably housed in a common housing, particularly the housing of the headphones or corresponding earpiece.

In the case of the second embodiment shown in FIG. 2, the electronic devices of the utterance device SPE include a common housing, that is, a microphone M, a transmitter S and an antenna A, as well as a speech recognition device SE, It is desirable to provide them in the translation devices U1 and U2 and the speech refiners SG1 and SG2. The hearing device in the second embodiment shown in FIG.
In addition, it may include a receiver A and an earphone or headphone H that can be switched by the selection switch W. These devices are preferably housed in a housing, especially in the housing of the corresponding earpiece of the headphones H.

Since the source information is obtained from the output of the speech recognizer SE in an appropriately encrypted form, and the target information is obtained from the output of the translator U in an appropriately encrypted form, the source information It is also possible that the topic in the target language or the target language is output together with these data. For that purpose, an output device D as shown by a broken line in FIG. 1 may be connected to the place. The output device may be, for example, a display device that displays information on a display screen or an output printer that prints out information.

[Brief description of drawings]

FIG. 1 is a block circuit diagram of a first embodiment of the present invention.

FIG. 2 is a block circuit diagram of a second embodiment of the present invention.

[Explanation of symbols]

          E ... Receiver H ... Sound reproduction transducer           M: Microphone O: Direct signal path           S ... Transmitter SE ... Speech recognition device         SG ... Speech generator U ... Translation device

[Procedure for Amendment] Submission for translation of Article 34 Amendment of Patent Cooperation Treaty

[Submission date] March 31, 2001 (2001.3.31)

[Procedure Amendment 1]

[Document name to be amended] Statement

[Name of item to be amended] Claims

[Correction method] Change

[Contents of correction]

[Claims]

─────────────────────────────────────────────────── ─── Continuation of front page (51) Int.Cl. ⁷ Identification code FI theme code (reference) H04B 7/26 QF term (reference) 5B091 AA07 CB12 CB32 CD03 CD15 5D015 KK02 5D045 AB21 AB26 5K067 AA21 BB02 DD51 DD54 FF25 FF26 KK13

Claims (11)

[Claims] 1. A transmitter equipped with a receiver (E) and a sound reproducing transducer (H) for receiving a radio transmission signal of the transmitter (S) from a microphone (M) of a speaker to the transmitter (
In a personal information system for transmitting and receiving the speech information via S), particularly in a personal guide system, in the signal path between the microphone (M) of the speaker and the sound reproduction transducer (H) of the listener,
A speech recognizer (SE) for recognizing source information in the source language emitted by the speaker,
A personal information system comprising: a translation device (U) for translating source information into target information in a target language; and a speech generator (SG) for generating a target language from the target information. 2. An additional direct signal for transmitting and receiving speech information directly in parallel with a speech recognizer (SE), a translator (U) and a speech generator (SG) according to claim 1. A personal information system characterized by having a road (O). 3. The receiver according to claim 1, wherein the receiver is a receiver.
(E), a speech recognition device (SE), a translation device (U), and a speech generator (SG) are provided in the listening device (HE1, HE2).
(Figure 1). 4. The speech recognition device (SE), the translation device (U), the speech generator (SG) and the transmitter (S) on the speaker side according to claim 1 or 2. A personal information system characterized in that it is provided in a utterance device (SPE). 5. The utterance device (SP) according to any one of claims 1 to 4.
Corresponding electronic devices (S, E, SE, U, SG, W) in E) are housed together with the microphone (M) in a common housing, or in a listening device (HE) a sound reproduction transducer. Personal information system characterized by being housed in a common housing together with (H). 6. A personal information system according to any one of claims 1 to 5, characterized in that the listening device (HE) corresponds to one target language. 7. The device according to any one of claims 1 to 5, wherein the listening device (HE) is compatible with a plurality of languages and can be switched (W). Personal information system characterized by. 8. The apparatus according to claim 4, wherein the utterance device (SE) can handle a plurality of target languages, and the transmitter (S) does not direct the source language to multiple target languages. A personal information system characterized in that it is designed to be sent by. 9. The personal information system according to any one of claims 1 to 8, wherein transmission and reception are performed wirelessly by using a high frequency. 10. The method according to claim 1, wherein:
A personal information system characterized in that transmission and reception are performed by infrared rays using high frequencies. 11. A speech recognition device (SE) or translation device (SE) or translation device (SE) as claimed in any one of claims 1 to 10, in order to force the recognized source information or translated target information. A personal information system in which an output device (display device or printer D) is connected to the output of U).