WO2001018990A1 - 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

Personal information system, in particular personal guidance system, for the wireless transmission of voice information

The invention relates to a personal information system, in particular a personal guidance system, for transmitting voice information from a speaker's microphone by means of a transmitter to one or more listeners, which are each equipped with a receiver and playback sound transducer for receiving the wirelessly transmitted signals from the transmitter.

Group guidance systems are known in which a leading person (speaker) wears a wireless microphone close to the body and the individual persons in a guided group each receive a high-frequency receiver through which they hear the leading person, for example a city guide. In this way, several people can be addressed simultaneously in one language. For another language, for example, the city guide must speak this language himself or another person speaks this language, whereby different languages can also be transmitted simultaneously using different transmission frequencies. Such a system is sold, for example, by Sennheiser with the SKM 1081 wireless microphone and the EK 1031 receivers. In addition, multichannel interpreting systems are known, for example Sennheiser Infraport 1029 on an infrared basis. The voice of a speaker is transmitted to several interpreters, who translate the lecture simultaneously. Each language is then fed separately to a multi-channel infrared transmitter. The listeners have multi-channel receivers with which they can select their desired language from the simultaneously transmitted languages via frequency selection and listen to the lecture. These systems are also conceivable as multi-channel high-frequency systems, or a selection based on time slot (DECT) takes place.

There are already automatic speech recognizers on the market (e.g. Via Voice from IBM) that convert the spoken word into evaluable data, e.g. for automatic writing. Furthermore, work is being carried out on automatic translation systems in which a text or a speech signal is automatically translated into another language.

These known methods and systems, that is to say the group tour management systems described and the multichannel interpreting systems described, require multilingual people who lead the groups or several guides of different languages, which means a particularly high personnel expenditure. In addition, complicated transmission systems are required. The automatic speech recognition systems previously proposed require extensive computer systems and software and also only permit automatic translations of written texts that can be used to a limited extent and that still need to be revised.

A method for interpreting in a conversation is already known from US Pat. No. 4,882,681, in which a subscriber speaks a question to a radio, for example, this signal is transmitted wirelessly to a translation computer, translated there and then wirelessly to the subscriber's radio is transferred back and the translation is output in another language. A second participant then hears this translated question, she answers in his language, and this is wirelessly transmitted back to the translation computer, where it is translated into the language of the first participant and wirelessly transmitted back to the first participant, so that he answers the question asked in a first language in the same language received from the translation computer. In addition, DE-A-1 95 08 01 7 describes a communication device with a built-in radio telephone and electronic translator, which translates from a first source language into an intermediate translation language. This intermediate translation language is then transmitted to another communication device in order to be converted there into a second language.

The present invention has for its object to equip and design a personal information system for transmitting speech information of the type mentioned in such a way that an automatic conversion of a source speech signal into one or more target languages is made possible, so that the use of interpreters is unnecessary. The equipment required for this should be as compact as possible so that it can be integrated in a speaker unit or in receiver units.

This object is achieved in a personal information system for transmitting voice information from a microphone of a speaker by means of a transmitter to one or more listeners, which are each equipped with a receiver and playback sound transducer (for example headphones) for receiving the wirelessly transmitted signals from the transmitter, in accordance with the present invention solved in that in the signal path between the microphone of the speaker and the playback sound transducer of the listener a speech recognition unit for recognizing the source information of the source language of the speaker, a translator unit for translating the source information into the target information of the target language and a speech generator unit for generating the target language from the target information , The automatic conversion from the speaker's source language to the listener's target languages is made possible by the fact that already known Speech recognition units and speech generator units are used and the conversion into the other language takes place by translating the recognized source information into the respective target information and not the direct conversion of 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 connected in parallel with an additional direct signal path for the unchanged transmission of the speech information in order not only to supply the translated speech information to certain listeners, but also to make the original speech information available to some listeners untranslated. Simplified receiver units can then be provided for these listeners of the original language information.

The units used here, such as the speech recognition unit, translator unit and speech generator unit, can be implemented in a relatively space-saving manner by using microelectronics, so that in a first advantageous embodiment they are accommodated in a receiver unit for the listener, but in a second embodiment for the speaker in a speaker unit. This has the advantage that the three units only have to be present once. The receiver units can e.g. B. be equipped for only one target language, so that several different handset units must be distributed for transmission in several languages. However, it is also possible to equip the receiver units for several target languages and to switch them over accordingly by the receiver.

The speaker unit or the central unit are preferably equipped for a plurality of target languages, and the transmitter is set up to transmit a plurality of target languages, including the source language, in the multiplex.

The system according to the invention can preferably be designed as a tour guide system in order to convert the speech information given by a speaking guide into several languages at the same time and to address these to the individual listeners transfer. However, the principle according to the invention can also be implemented in any information system in which the language of a speaker or animator is automatically translated into several languages and transmitted to the listeners, who then select the desired language.

The transmission between the transmitter and the receiver is preferably carried out by means of radio frequency in order to enable seamless transmission even with obstacles in between. However, transmission by means of infrared signals is also possible if there are no obstacles between the speaker and the listener, or parallel transmission paths are provided in another way. In the event that the speech recognition unit, translator unit and speech generator unit are accommodated in the receiver unit and the transmission between transmitter and receiver takes place by means of radio frequency, it is also conceivable to use the system according to the invention in a radio transmission to a radio receiver, which is also a receiver unit. It will then be a matter of specially equipped radio receivers in which the speech information is derived from the received signal, as far as speech is concerned, by a speech recognition unit, converted into target information of a selectable language by a translator unit and then into the target language by a speech generator unit is changed. In this way it is possible with such a specially equipped radio receiver to convert the received speech signals abroad into the desired own language, e.g. to Being able to understand announcements and messages in the foreign language.

Since in the personal information system according to the invention the source information is available at the output of the speech recognition unit and the translated target information is available at the output of the translation unit, it is possible according to a further embodiment of the invention to connect an output unit here for outputting the coded source information or target information in order to provide the output recognized or translated information. This output unit can be a display unit or a printer, for example. Further advantageous embodiments of the invention can be found in the subclaims.

The invention is explained in more detail below with reference to the accompanying drawings using several exemplary embodiments.

Show it:

1 shows the block diagram of a first embodiment and

Figure 2 shows the block diagram of a second embodiment.

In the first embodiment according to FIG. 1, a microphone M and a transmitter S provided with an antenna A are provided in a speaker unit SPE. A plurality of receiver units HE1, HE2 etc. each have a receiver E connected to an antenna A, a speech recognition unit SE, a translator unit U and a speech generator SG to which a headphone or earphone A is connected. Instead of the headphone or earphone A, any other suitable reproduction sound transducer can of course also be provided, e.g. also a speaker. In each of the receiver units HE1, HE2, etc., the receiver E receives the source language of the speaker unit SPE, and the speech recognition unit SE derives the source information from this. This source information is translated into target information of the target language by the translator unit U and converted into the target language in the language generator unit SG, which is reproduced by the headphones or earphones H.

Each of the receiver units HE1, HE2 etc. is either set up for only one target language, so that receiver units HE of different languages may have to be output to the individual listeners, or the translator unit U is set up for conversion into target information of different languages, so that the listener can then select the respective target language by pressing a selector switch W. The number of receiver units HE1, HE2 is practically unlimited. The embodiment shown in FIG. 2 differs from the first described according to FIG. 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 for the transmission of several target languages and sends this information in the multiplex, for. B. in frequency division multiplexing or time division multiplexing. The receiver units HE are of a simpler design than in the first embodiment, since there is no translation of the speech information, but only the information received via the receiver E has to be transmitted to the headphones or earphones. Here, too, each receiver unit HE can be equipped for a target language, so that different receiver units HE must be output. Conveniently, however, each of the receiver units HE is set up to selectively receive different languages, and the receiver selects the desired language via a selector switch W.

In the two exemplary embodiments according to FIGS. 1 and 2, a bridging path 0 (shown in dashed lines) is provided for the additional transmission of the original language from the speaker to the listeners, in order to also supply the individual listeners in the original language. This variant is particularly expedient, since a group of listeners with one language, e.g. the mother tongue of the country. The speaker information can be transmitted unchanged for these listeners, so that these listeners can also be equipped with simpler receiver units, e.g. as shown in Fig. 2. In this case, it is expedient to use the system according to FIG. 1, in which the translation electronics are therefore provided in the receiver units HE1, HE2, while the simplified receiver unit HE according to FIG. 2 is used for the listeners who do not need a translation can.

In the embodiment according to FIG. 1, it goes without saying that the microphone M and the transmitter S are accommodated in a common housing in the speaker unit SPE, from which the antenna A is also led out. Such wireless microphones are generally known. The receiver units HE this In addition to the receiver E and the headphones or earphones H, the exemplary embodiment also contains further electronic units such as the speech recognition unit SE, the translation unit U with selector switch W and the speech generator unit SG. All of these units are preferably housed in a common housing, in particular in a housing of the headphones H or on a corresponding bracket. In the case of the second exemplary embodiment according to FIG. 2, the electronic units of the speaker unit SPE are preferably accommodated in a common housing, that is to say in addition to the microphone M and the transmitter S and the antenna A, 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 receiver unit of the second exemplary embodiment according to FIG. 2 here contains fewer electronic units, such as the receiver E with antenna A and the headphone or earphone H, which can be switched over by the selector switch W, and these units can also be accommodated in a simple manner, in particular in the housing Housing or on the bracket of a headphone H.

Since the source information is available at the output of the speech recognition unit SE and the target information is present in appropriately coded form at the output of the translation unit U, the data can also be used to output the speaker's speech in the original language or in the target language. For this purpose, an output unit D is connected at this point, as indicated by dashed lines in FIG. 1. This output unit can e.g. a display unit for displaying the information on a screen or an output printer with which the information can be output on paper.

Claims

Expectations 1 . Personal information system, in particular personal guidance system, for transmitting voice information from a microphone (M) of a speaker by means of a transmitter (S) to one or more listeners, the receiver (E) and playback sound transducer (H) for receiving the wirelessly transmitted signals of the transmitter (S ) are equipped, characterized in that in the signal path between the microphone (M) of the speaker and the playback sound transducer (H) of the listener, a speech recognition unit (SE) for recognizing 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) for generating the target language from the target information is switched. 2. Personal information system according to claim 1, characterized in that an additional direct signal path (0) for direct transmission of the speech information is provided in parallel with the speech recognition unit (SE), the translation unit (U) and the speech generator unit (SG). 3. Personal information system according to claim 1 or 2, characterized in that the receiver (E), the speech recognition unit (SE), the translator unit (U) and the speech generator unit (SG) at the listener are housed in a handset unit (HE, HE1, HE2) (Fig. 1). 4. Personal information system according to claim 1 or 2, characterized in that the speech recognition unit (SE), the translator unit (U), the speech generator unit (SG) and the transmitter (S) are housed at the speaker in a speaker unit (SPE). 5. Personal information system according to claim 1 to 4, characterized in that the corresponding electronic units (S, E, SE, U, SG, W) in the speaker unit (SPE) in a common housing with the microphone (0) or in the Handset unit (HE) are housed in a common housing with the playback sound transducer (H). 6. Personal information system according to one of claims 1 to 5, characterized in that the receiver units (HE) are each equipped for only one target language. 7. Personal information system according to one of claims 1 to 5, characterized in that the receiver units (HE) are equipped for several target languages and can be switched accordingly (W). 8. Personal information system according to claim 4, characterized in that the speaker unit (SE) is equipped for several target languages and the transmitter (S) is set up for the transmission of several target languages, including the source language, in the multiplex. 9. Personal information system according to one of claims 1 to 8, characterized in that the transmission takes place wirelessly by means of radio frequency. 10. Personal information system according to one of claims 1 to 8, characterized in that the transmission takes place wirelessly by means of infrared signals. 1 1. Personal information system according to one of the preceding claims, characterized by an output unit (display unit or printer D) connected to the output of the speech recognition unit (SE) or the translation unit (U) for outputting the recognized source information or translated target information. CHANGED REQUIREMENTS [Received at the International Bureau on January 3, 2001 (January 3, 2001); original claims 1-11 replaced by new claims 1-10; (3 pages)] 1 . Personal information system, in particular personal guidance system, for transmitting voice information from a microphone (M) of a speaker by means of a transmitter (S) to one or more listeners, the receiver (E) and playback sound transducer (H) for receiving the wirelessly transmitted signals of the transmitter (S ) are equipped, characterized in that parallel to the direct signal path (0) between the microphone (M) of the speaker and the playback sound transducer (H) of the listener or listeners, an additional signal path with a speech recognition unit (SE) for recognizing 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) for generating the target language from the target information. 2. Personal information system according to claim 1, characterized in that the receiver (E), the speech recognition (SE), the translator unit (U) and the speech generator unit (SG) for the listener are housed in a handset unit (HE, HE1, HE2) (Fig . 1 ). 3. Personal information system according to claim 1, characterized in that the speech recognition unit (SE), the translator unit (U), the speech generator unit (SG) and the transmitter (S) are housed at the speaker in a speaker unit (SPE). 4. Persroneninformationsanlage according to claim 1 to 3, characterized in that the corresponding electronic units (S, E, SE, U, SG, W) in the speaker unit (SPE) in a common housing with the microphone (O) or in the Handset unit (HE) are housed in a common housing with the playback sound transducer (H). 5. Personal information system according to one of claims 1 to 4, characterized in that the receiver units (HE) are each equipped for only one target language. 6. Personal information system according to one of claims 1 to 5, characterized gekennzeichbnet that the receiver units (HE) are equipped for several target languages and can be switched accordingly (W). 7. Personal information system according to claim 3, characterized in that the speaker unit (SE) is equipped for several target languages and the transmitter (S) is set up for the transmission of several target languages, including the source language, in the multiplex. 8. Personal information system according to one of claims 1 to 7, characterized in that the transmission takes place wirelessly by means of radio frequency. 9. Personal information system according to one of claims 1 to 7, characterized in that the transmission takes place wirelessly by means of infrared signals. CHANGED SHEET (ARTICLE 13) 10. Personal information system according to one of the preceding claims, marked by an output unit (display unit or printer D) connected to the output of the speech recognition unit (SE) or the translation unit (U) for outputting the recognized source information or translated target information.