EP1214800B1 - Personal information system, especially a personal guide system, for wirelessly transmitting voice 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

The invention relates to a personal information system, in particular passenger guidance system, for transmitting voice information from a microphone of a Speaker by means of a transmitter to one or more listeners, each with a Receiver and playback sound converter for receiving the wirelessly transmitted Signals of the transmitter are equipped.

There are known person-group management systems in which a leading person (Speaker) wears a wireless microphone close to the body and the individual persons a guided group each receive a radio frequency receiver over which they the leader, e.g. a city guide, listen. It can be so many people be addressed simultaneously in one language. For another language must e.g. the city guide speaks that language himself or speaks another person this language, whereby one also over different transmission frequencies can transmit different languages at the same time. Such a facility will e.g. from the company Sennheiser with the wireless microphone SKM 1081 and the Receivers EK 1031 distributed.

Moreover, multi-channel interpreting facilities are known, e.g. Sennheiser Infraport 1029 infrared. Here, the voice of a lecturer becomes transfer several interpreters, and these translate the lecture simultaneously. each Speech is then fed separately to a multi-channel infrared transmitter. The listeners have multi-channel receivers, with which they are transferred from the same time Select your desired language via frequency selection and the Listen to a lecture. These systems are also conceivable as multi-channel high-frequency systems, or a time slot-based selection (DECT) is performed.

There are also automatic speech recognizers on the market (e.g., Via Voice from the company IBM), which convert the spoken word into evaluable data, e.g. for automatic writing. Furthermore, on automatic translator systems worked, in which a text or also a speech signal automatically into a other language is translated.

These known methods and systems, ie the described Personengruppenführungsanlagen and the multichannel interpreter applications described multilingual people who lead the groups or several leaders of different Languages, which means a particularly high personnel expenditure. Furthermore complicated transmission systems are required. The previously proposed Automatic speech recognition systems require extensive computer systems and software and also allow only limited scope useful automatic translations of text texts that are still being revised Need to become.

From US-A-4,882,681 is already a method for interpreting in a Conversation in which a subscriber e.g. a question in a radio speaks, this signal is transmitted wirelessly to a translation computer, translated there and then wirelessly to the radio of the Participant is transferred back and there the translation in another Language is output. A second participant then hears this translated question answers them in his language, and this will be wireless again transfer the translation computer, there is in the language of the first Translated and transferred to this wireless back, so he on his in a first language question in the same language the answer from Translation computer receives. In addition, in DE-A-195 08 017 already a communication device with built-in radiotelephone and electronic Translator, which translates from a first source language into a translation intermediate language translated. This translation intermediate language then becomes transferred to another communication device to there in a second language to be implemented.

The present invention is based on the object, a personal information system for transmitting voice information of the type mentioned in the beginning equip and train that an automatic conversion of a source voice signal in one or more target languages is possible, so that the use is dispensable by interpreters. This should be the necessary equipment for it be as compact as possible to be in a speaker unit or in earphone units to be integrated.

This task is used in a personal information system for transmitting Voice information from a microphone of a speaker by means of a transmitter one or more listeners, each with a receiver and playback sound converter (e.g., headphones) for receiving the wirelessly transmitted signals of the Transmitter are equipped, according to the present invention solved in that in the signal path between the microphone of the speaker and the playback sound converter the listener, a speech recognition unit for recognizing the source information the source language of the speaker, a translator unit for Translate the source information into the destination information of the target language and a Voice generator unit for generating the target language from the destination information is switched. The automatic translation from the source language of the speaker in the target languages of the listener is thereby made possible that already known Speech recognition units and speech generator units are used and the translation into the other language by translating the recognized source information into the respective destination information and not the direct implementation the source language into the target language.

This implementation path with a speech recognition unit, a translation unit and a speech generator unit is preferably an additional direct one Signal path parallel to the unchanged transmission of the speech information, so as not only to supply the listener with the translated speech information, but some listeners and the original language information untranslated To make available. For these listeners of the original language information can then be provided simplified hearing units.

The units used here, such as the speech recognition unit, translator unit and speech generator unit are relatively space-saving realized by the use of microelectronics, so that they are housed in a first advantageous embodiment of the listener in a handset, in a second embodiment, however, the speaker in a speaker unit. This has the advantage that the three units only need to be present once.
The earphones can z. B. be equipped for only one target language, so that several different listener units must be distributed for transmission in several languages. However, it is also possible to equip the earphone units for multiple target languages and to switch accordingly by the listener.

The speaker unit or the central unit are preferably for several Target languages equipped, and the transmitter is to transmit several Target languages, including the source language, are multiplexed.

The system according to the invention can preferably be used as a personal guidance system be expanded to the language information given by a speaking leader to translate into several languages simultaneously and to the individual listeners transfer. However, the principle of the invention may also be in any Information system be implemented at the language of a speaker or Animateurs automatically translated into several languages and transmitted to the listener who will then select the desired language.

The transmission between transmitter and receiver is preferably carried out by means of High frequency, for a seamless transmission even in between To enable obstacles. However, it is also a transmission using Infrared signals possible if no obstacles between the speaker and the Listeners are lying, or there are other parallel transmission paths provided. In the event that the speech recognition unit, translator unit and Voice generator unit are housed in the receiver unit and the transmission between transmitter and receiver by means of high frequency, it is also conceivable the system according to the invention in a broadcast transmission to a radio receiver apply, which also represents a listener unit. It will be here then act to specially equipped radio receivers, where from the Receive signal, as far as it is speech, by a speech recognition unit the language information is derived by a translator unit into a Target information of a selectable language and then implemented by a Voice generator unit is converted into the target language. That's the way it is possible with such a specially equipped radio receiver, abroad to convert the received speech signals into the desired own language in order to e.g. Understand announcements and messages in the foreign language.

As in the personal information system according to the invention at the output of the Speech recognition unit, the source information and at the output of the translation unit the translated destination information is available, it is according to a Another embodiment of the invention possible, here an output unit for Output of encoded source information or destination information to connect to output the recognized or translated information. This output unit can e.g. a display unit or a printer.

Further advantageous embodiments of the invention are the dependent claims remove.

The invention will now be described with reference to the accompanying drawings explained in more detail with reference to several embodiments.

Figur 1

das Blockschaltbild einer ersten Ausführungsform und

Figur 2

das Blockschaltbild einer zweiten Ausführungsform.

Show it:

FIG. 1

the block diagram of a first embodiment and

FIG. 2

the block diagram of a second embodiment.

In the first embodiment of Figure 1 are in a speaker unit SPE Microphone M and provided with an antenna A transmitter S provided. In a plurality of receiver units HE1, HE2, etc. are each one connected to an antenna A. Receiver E, a speech recognition unit SE, a translator unit U and a voice generator SG provided to the a headphone or earphone A is connected. Of course, instead of the headphone or earphone A as well any other suitable reproduction sound transducer should be provided, e.g. also a Speaker. In each of the hearing units HE1, HE2, etc., the receiver receives E is the source language of the speaker unit SPE, and the voice recognition unit SE derives the source information from this. This source information is provided by the Translator unit U translated into a target information of the target language and in the Voice generator unit SG converted into the target language, the head or Earphone H is played.

Each of the hearing units HE1, HE2, etc. is either only for one target language set up so that if necessary to the individual listeners HE units HE different languages, or the translator unit U is for conversion to target information of different languages set up so that the listener then by pressing a Wahlschaiters W the can select the respective target language. The number of listener units HE1, HE2 is practically unlimited.

The embodiment shown in Figure 2 differs from the first described Figure 1 in that the speech recognition unit SE, the translator unit U and the speech generator units SG are accommodated in the speaker unit SPE. The transmitter S is set up to transmit several target languages and transmits this information in multiplex, z. B. in frequency division or time division multiplex. The earphones HE are simpler than in the first embodiment, because there is no translation of the language information, only the Information received via the receiver E on the headphone or earphone must be transferred. Again, each earphone unit HE for each one Target language be equipped so that different HE units output HE Need to become. Conveniently, but each of the hearing aid HE is for Optionally, reception of different languages is established, and the listener dials the desired language via a selector W off.

In the two embodiments of Figures 1 and 2 is for additional Transferring the original language from the speaker to the listeners a bridging path O (dashed lines) provided to the individual listener also in the To supply the original language. This variant is particularly useful because at Guides or other events usually a listener with a Language, e.g. the native language of the country, dominates. For these listeners, the Speaker information is transmitted unchanged, so that these listeners with simple hearing aid units can be equipped, e.g. as shown in Fig. 2. In this case, it is expedient to use the system of FIG. 1, in which the Translation electronics is thus provided in the earphones HE1, HE2, while for the listeners who do not need translation, the simplified Earphone HE according to FIG. 2 can be used.

In the embodiment of Fig. 1, it goes without saying that in the Speaker unit SPE the microphone M and the transmitter S in a common Housing are housed, from which also the antenna A is led out. Such Wireless microphones are well known. The listening units HE this Embodiment included in addition to the receiver E and the headphones or Earphones H also other electronic units such as the speech recognition unit SE, the translator unit U with selection switch W and the speech generator unit SG. All of these units are preferably in a common housing accommodated, in particular in a housing of the headphone H or at one corresponding mounting bracket. In the case of the second embodiment of FIG. 2 the electronic units of the speaker unit SPE are preferably in one housed common housing, so next to the microphone M and the transmitter S and the antenna A and the electronic units such as the speech recognition unit SE, the translator units U1 and U2 and the speech generator units SG1 and SG2. The earphone unit of the second embodiment of FIG. 2 contains fewer electronic units such as the selector switch W, switchable receiver E with antenna A and the headphone or earphone H. Also these units can be easily accommodated in a housing, in particular in the housing or on the mounting bracket of a headphone H.

Since the output of the speech recognition unit SE, the source information and on Output of the translation unit U the destination information in appropriately coded Form is present, with this data also an output of the lecture of the Speaker in the original language or in the target language. To this Purposes, an output unit D is connected at this point, as in FIG. 1 indicated by dashed lines. This output unit can e.g. a display unit for Presentation of the information on a screen or an output printer with which the information can be printed on paper.

Claims (10)

1. Personal information system, in particular personal guide system, for transmitting language information from a microphone (M) of a speaker by means of a transmitter (S) to one or more listeners who are equipped with receivers (E) and reproduction sound converters (H) for receiving the wirelessly transmitted signals of the transmitter (S), characterised in that an additional signal path comprising a language recognition unit (SE) for recognising the source information of the source language of the speaker, a translation unit (U) for translating the source information into the target information of the target language and a language generator unit (SG) to generate the target language from the target information, are connected parallel to the direct signal path (O) between the microphone (M) of the speaker and the reproduction sound converter (H) of the listener(s).
2. Personal information system according to claim 1, characterised in that the receiver (E), the language recognition unit (SE), the translation unit (U) and the language generator unit (SG) are housed with the listener in a listener unit (HE, HE1, HE2) (Fig. 1).
3. Personal information system according to claim 1, characterised in that the language recognition unit (SE), the translation unit (U), the language generator unit (SG) and the transmitter (S) are housed with the speaker in a speaker unit (SPE).
4. Personal information system according to claims 1 to 3, characterised in that the corresponding electronic units (S, E, SE, U, SG, W) are housed in the speaker unit (SPE) in a common housing with the microphone (O) or in the listener unit (HE) in a common housing with the reproduction sound converter (H).
5. Personal information system according to any one of claims 1 to 4, characterised in that the listener units (HE) are equipped in each case only for one target language.
6. Personal information system according to any one of claims 1 to 5, characterised in that the listener units (HE) are equipped for a plurality of target languages and can be switched over (W) correspondingly.
7. Personal information system according to claim 3, characterised in that the speaker unit (SE) is equipped for a plurality of target languages and the transmitter (S) is set up in multiplex to transmit a plurality of target languages, including the source language.
8. Personal information system according to any one of claims 1 to 7, characterised in that the transmission takes place wirelessly by means of high frequency.
9. Personal information system according to any one of claims 1 to 7, characterised in that the transmission takes place wirelessly by means of infrared signals.
10. Personal information system according to any one of the preceding claims, characterised by an output unit connected to the output of the language recognition unit (SE) or the translation unit (U), a display unit or printer, for outputting the recognised source information or translated target information.

Images