WO2012168405A2

WO2012168405A2 - Method for ascertaining audible voice signals

Info

Publication number: WO2012168405A2
Application number: PCT/EP2012/060857
Authority: WO
Inventors: Marcus Regensburger
Original assignee: Marcus Regensburger
Priority date: 2011-06-07
Filing date: 2012-06-08
Publication date: 2012-12-13
Also published as: DE102011077106A1; WO2012168405A3; DE102011077106A9

Abstract

A method for ascertaining audible voice signals from a text article (14b) that is available in written form particularly from a printed medium (14a) is described. A mobile communication appliance, particularly a mobile telephone (10), having a camera is present. A photograph of the text article (14b) is produced by the mobile telephone (10). The photograph is transmitted to a processing unit (16). The photograph of the text article (14b) is used by the processing unit (16) to ascertain first voice data. The first voice data are transmitted to the mobile telephone (10). The first voice data are output by the mobile telephone (10) as audible voice signals.

Description

Method for determining acoustic speech signals

The invention also relates to corresponding programs for executing the method and to a mobile communication device, in particular a mobile telephone, a user database and a processing unit on which these programs are loaded ,

Every day a large number of printed media are published. These printed media contain a large number of text contributions in written form. The text contributions can be read by persons. This information can be passed to people.

For many reasons, it may be difficult or at least not useful for a particular person to obtain the information in the known manner. For example, a person may have speech or visual or reading problems that make it difficult to read the text posts.

The invention has therefore set itself the task of transmitting a written text in a different way to a person.

The object is also achieved by methods and programs according to

claims

9, 10, 11, 14, and 15 as well as by a mobile communication device, in particular a mobile phone according to the object Claim 12, a user database according to claim 13 and a processing unit according to claim 16.

In the method according to the invention, a photo of the text contribution is created by the mobile telephone, first voice data are determined from the photo of the text contribution, and the first voice data are output by the mobile telephone as acoustic voice signals.

An advantage of the invention is that a person using the method according to the invention no longer has to read the text entry, but instead the text of the text contribution is read to this user via the mobile telephone. It can thus no visual or reading problems and - by a corresponding language selection - no more speech problems occur. Instead, the user can capture the read text and thus the information contained therein directly and without further difficulties by means of the acoustic transmission.

The inventive method is realized on the one hand by a program that is loaded on the mobile phone, and on the other hand by a program that is loaded on the processing unit.

In addition, it is possible for the user to be provided with additional data on the text contribution that makes it possible, for example, to simply order the products or services mentioned in the text post. In this way, the user can advantageously be addressed simply by additional data transmitted to the text entry. In another example, safety instructions for the safe use of products in the form of additional data can be provided and thus contribute to the safe use of products. In the latter case, for example, amended legal provisions regarding a stricter labeling requirement could be fulfilled by providing supplementary data accordingly.

It is particularly advantageous if the additional data are transmitted to the mobile telephone as further text and / or image data and / or multimedia data, and if the text and / or image data and / or multimedia data are displayed in particular on a screen of the mobile telephone and / or or on a speaker of the mobile phone. This makes it possible for the user to prepare and transmit the additional data associated with the photographed text contribution in a simple and understandable manner, in particular with the aid of additional images and the like.

A particularly advantageous embodiment of the invention consists in that a program is downloaded in advance from an application database to the mobile telephone, this program being suitable for carrying out the steps required for the method according to the invention. This makes it possible for a user in a simple manner to set up the inventive method on a mobile phone and then run with this mobile phone.

Other features, applications and advantages of the invention will become apparent from the following description of exemplary embodiments of the invention, which are illustrated in the drawing. All described or illustrated features, alone or in any combination form the subject matter of the invention, regardless of their summary in the claims or their dependency and regardless of their formulation or representation in the description or in the drawing.

The sole figure of the drawing shows a schematic block diagram of an exemplary embodiment of a method according to the invention for determining acoustic speech signals.

The method described below is intended to be carried out with the involvement of a mobile communication device. The communication device may be, for example, a mobile phone or a so-called "smartphone", for example a BlackBerry smartphone [BlackBerry is a trademark of Research In Motion Limited (RIM)]. Furthermore, it can also be a so-called "mobile digital device", for example an iPhone device or an iPad device [iPhone and iPad are trademarks of Apple Inc.]. It can also be a mobile computer, in particular a notebook, which is suitable for mobile telecommunications.

This mobile communication device is identified in the figure with the reference numeral 10 and is subsequently named for the sake of simplicity only as a mobile phone. The mobile telephone 10 is adapted to receive voice data from a transmitter and output as acoustic voice signals via a speaker to an operator. For this purpose, the mobile telephone 10 is usually associated with a telephone number and / or an Internet address. Optionally, the mobile telephone 10 is also adapted to receive text and / or image data and / or multimedia data from a transmitter and display the associated texts and / or images and / or multimedia data via a screen and / or a speaker of the operator or to spend. Furthermore, the mobile phone 10 includes a camera not shown in detail, with which the operator can create a photo of an object. This photo may be transmitted by the mobile telephone 10 in the form of digital data to a receiver. Furthermore, the mobile phone 10 includes a microprocessor or the like, on which a program can be loaded, which can then be executed by the mobile phone 10.

An application database 12 stores a plurality of digital programs, each of which can be transmitted to mobile communication devices as explained above and stored there. The transmission of a program from the application database 12 to a mobile communication device can take place in various ways and will not be explained in detail here.

On the application database 12, a program is stored, which is provided for determining voice data and possibly additional data. This program is downloaded in a preliminary step of the method according to the invention from the application database 12 to the mobile phone 10. This means that the program is transmitted in an unspecified manner from the application database 12 to the mobile phone 10 and then stored on the mobile phone 10. It is assumed that the program can run after the download on the mobile phone 10 and thus can be performed on the mobile phone 10. The aforementioned preliminary step is indicated by an arrow 12a in the figure.

It is now assumed that the operator is a newspaper, such as a newspaper, or a magazine, such as a weekly magazine, or a contract, an instruction manual or other similar printed medium. This printed medium is indicated in the figure by the reference numeral 14a. It is further assumed that this printed medium 14a contains at least one textual article in written form, which may in some way be provided with a name, for example a headline. This text entry is identified in the figure by the reference numeral 14b and the name or the title thereof by the reference numeral 14c. If appropriate, it is possible for a code 14d, for example a barcode or the like, to be present in addition to the name or heading 14c next to the text entry 14b.

After the downloaded program has been started on the mobile phone 10, the operator photographs with the camera of the mobile phone 10 the text contribution 14b of the printed medium 14a. The created photo (s) are then present in the mobile telephone 10 as digital data, in particular in the form of a multiplicity of so-called pixels (pixel = picture element). The process described above is indicated by a double arrow 15 in the figure.

The generated photo (s) are transmitted to a processing unit 16 by the mobile telephone 10 in the form of digital data. This transmission, which is indicated in the figure by an arrow 18, is carried out in particular with the aid of the downloaded program. For the transmission, the processing unit 16 is assigned a telephone number or optionally also an Internet address, which is dialed by the mobile telephone 10. In this way, a communication link between the mobile phone 10 and the processing unit 16 is established.

The transmission as such can be effected by means of UMTS (UMTS = universal mobile telecommunication system) or GPRS (GPRS = general packet radio service) or GSM (GSM = global system for mobile communications) or EDGE (EDGE = enhanced data rates for GSM evolution) or WLAN (WLAN = wireless local area network) or by means of another telecommunication method or other telecommunication system or service.

The processing unit 16 comprises a processor 24 for determining speech data and a database 26 with stored additional data. The voice data determined by the processor 24 may be output from the mobile phone 10 via the speaker as audible voice signals.

The processor 24 of the processing unit 16 determines from the created photo (s) in a first step machine-readable text and in a second step first speech data. The first voice data is transmitted from the processing unit 16 to the mobile telephone 10 according to the arrow 20.

In an alternative embodiment, the first voice data is not determined by the processing unit 16, but by the mobile phone 10. In a first step, in this case, machine-readable text is determined by the mobile phone 10 from the generated photo (s) and in a second Step are determined by the mobile phone 10, the first voice data from the machine-readable text.

From the received photo / s, the processor 24 of the processing unit 16 determines a comparison information. The comparison information may be, for example, a machine-readable text that is determined by the processing unit 16. But even a photo of the code 14d or data derived therefrom may represent the comparative information.

In an alternative embodiment, the comparison information is determined by the mobile telephone 10, wherein the comparison information is transmitted to the processor 24 of the processing unit 16. According to this embodiment, it is also possible that the code 14d is input from the user, and the mobile phone 10 transmits the code 14d to the processing unit 16 as comparison information.

According to an arrow 28, the comparison information is transmitted to the database 26. By means of the comparison information, additional data corresponding to the database 26 can be determined and transmitted to the processor 24 according to an arrow 30.

If additional data is determined from the database 26, this additional data is transmitted to the mobile telephone 10. In one embodiment, at least a portion of the overhead data may be communicated to the processor 24 for conversion by the processor 24 into second voice data. From this one part of the determined additional data, the processor 24 thus determines second voice data, which are transmitted to the mobile telephone 10 in the form of further additional data. There, the second voice data can then be output from the mobile telephone 10 in addition to the first voice data representing the text contribution 14b.

In a further embodiment, the processing unit 16 comprises no database 26 or not only the database 26. Rather, the processing unit 16 accesses at least one external database in order to determine there the additional data for the text contribution 14b.

The database 26 may be a central database in which a variety of additional data is offered for download by a service provider. According to the service provider, it is possible to automatically select the corresponding database, for example the database 26.

The processor 24 of the processing unit 16 may automatically associate a photographed newspaper post with a particular publisher of newspapers and / or magazines or multiple such publishers. In the case of a photographed instruction manual, the processor 24 may associate this instruction manual with a particular manufacturer and / or associated product. The text contribution 14b can be assigned by the processing unit 16 to an additional data provider, who is for example the publisher or manufacturer. A company can be a service provider and an additional data provider, but as a service provider it can also be responsible for several additional data providers.

For an additional data provider, for example by means of a unique identification code comparison information can be provided, according to which the additional data can be determined uniquely. By additional data are, for example, images or films to understand that serve, for example, advertising or information purposes and the text contribution 14b are assigned. The additional data can also be a service information for other services. Overall, additional data also means a mixed composition of the above types of additional data.

Likewise, the additional data may comprise further machine-readable text, from which the processor 24 or the mobile telephone 10 then determines second voice data. In the case of the determination of the second voice data by the processor 24, the second voice data is transmitted to the mobile telephone 10 according to the arrow 20.

It may be necessary to take into account the presence of several suppliers of additional data when submitting the photo (s) created. For example, it may be necessary for the photo (s) to be transmitted to different databases 26 as a function of the respective textual contribution 14b. The associated telephone numbers or Internet addresses of the respective database (s) 26 may be predetermined, for example, by the program downloaded by the user database 12, in which the code 14d photographed and evaluated by the mobile telephone 10 may be contained or predetermined by the processing unit 16. Optionally, it may also be necessary for the telephone number or Internet address to be stored by the operator in advance in the mobile telephone 10 or to be currently entered.

In particular, the processing unit 16, the processor 24 and the database 26 may be a digital computing device having a memory and an associated processor. It is understood that the computer is assigned a program with which the processing unit 16, the processor 24 and the database 26 are respectively managed and operated.

Alternatively, it is also possible for the operator to first create the photo (s), and only then to start the downloaded program and to transfer the photo (s) from the mobile telephone 10 to the processing unit 16.

In the database 26 recognition information for the detection of additional data are stored. This recognition information is compared with the determined comparison information and depending on this comparison, the additional data are determined. The identification information is, for example, identifiers which identify the individual text contributions. In another or additional variant, the recognition information is identifiers for the providers of additional data, i. For example, identifiers for the manufacturers of products or for the respective newspaper publishers, and possibly in addition to identifiers for the identification of the individual text contribution 14b. For example, brand names or personal names can also be recognized in the text contribution 14b, and the additional data from the database 26 are determined on the basis of the determined comparison information and the corresponding recognition information. The recognition information is present on the database 26 as digital data, for example in the form of machine-readable text or machine-readable digits.

Furthermore, the processing unit 16 and / or the database 26 is associated with a program that can be executed, for example, on the aforementioned computing device, and which is intended to determine the comparison information from the or the photo (s) and with those in the database 26 to compare stored recognition information. Furthermore, the processor 24 is associated with a program that can be executed, for example, on the aforementioned computing device, and is intended to determine from the photo or machine-readable text voice data. In the case of a present photo, the above program is designed to extract first machine-readable text from the photo and then to determine the language data from the machine-readable text initially determined.

The additional data in the database 26 are entered into the database 26, for example, by the respective provider of a product in the form of the corresponding operating instructions or by the publisher of the printed medium, for example by the publisher of the magazine. The provider of additional data can thus store exactly those additional data in the database 26, which in his view could be important for an operator in connection with the text contribution 14b.

The first voice data of the text contribution 14b are determined by the processor 24 or the mobile telephone 10 independently of the additional data. Only the comparison information is transmitted to the database 26 in order to determine the corresponding additional data for the text contribution 14b.

The processing unit 16, in particular the processor 24, or the mobile telephone 10 may be designed such that a translation of the text contribution 14b into a language previously selected on the mobile telephone 10 is performed and the first speech data is determined according to the selected language. Thus, for example, the text contribution 14b may be in German language, which is output by the mobile telephone 10 in audible form to the operator with appropriate selection of the language in English. In the latter example, the machine-readable text is first determined in German, then a further machine-readable text in English is determined by a not further explained translation unit in a further step and from the other machine-readable text are then from the processor 24 and the mobile phone 10th the first voice data is determined in English and output by the mobile telephone 10 as audible signals.

For example, language selection from one of the selectable languages may be achieved by having the program downloaded to the cellular phone 10 in some way notify the processor 24 of a particular language as the desired language of the operator. This desired language may be, for example, the language implemented on the mobile phone 10 as the user language.

If, in the presently described exemplary embodiment, the processing unit 16 receives the operator-created photo (s) of the particular text contribution 14b, then the comparative information is first determined from the photo and then stored in the database's 26 recognition information, for example, the corresponding provider of Additional data wanted.

If matching additional data is found in the database 26, the additional data associated with the text contribution 14b or the additional data provider is transmitted from the processing unit 16 to the mobile telephone 10. This transmission, which is indicated in the figure as arrow 20, can be carried out by means of the already mentioned telecommunication methods or systems or services. It can be assumed that either the communication link between the mobile phone 10 and the processing unit 16 is still present from the transmission of the photos or a new communication link can be set up, with the telephone number or the Internet address of the mobile phone being taken from the former communication link can.

The first or second voice data received by the mobile telephone 10 or the first voice data determined by the mobile telephone 10 are then output as voice signals via the loudspeaker of the mobile telephone 10 to the operator. This output is indicated by the arrow 22 in the figure. The output can be done via the commonly available, so-called handset of the mobile phone 10 or via an optionally existing hands-free device or via an optionally connectable to the mobile phone 10 headphones. In this way, on the one hand, the text contribution 14b is read to the operator and, on the other hand, the additional data of the specific text contribution 14b stored in the database 26 is read to the operator via the mobile telephone 10 and / or displayed or played. This output of the voice data or additional data can be repeated by the operator and the received voice data or additional data can optionally also be stored on the mobile telephone 10.

According to an arrow 32, the operator can communicate with the mobile phone 10. The operator may in this way, for example, send further queries to the processing unit 16 or request translations or the like.

Furthermore, the operator can make emergency calls or request further information, for example advertising.

According to an arrow 34, the mobile telephone 10 can transmit further information to an additional service 36 for this purpose. This further information can be automated by the mobile phone 10 or on the operation by the operator out. For example, due to a product offered in the form of advertising goods, the operator want to order this product, whereupon the mobile phone 10 sends an automated order to the additional service 36. Likewise, an automated emergency call can be sent or information can be obtained or the like. The necessary personal data is provided by the user database 12.

Thus, for example, it is possible for the mobile phone 10 to automatically place an order to the supplementary service 36, with which any desired materials are ordered. For example, tablets which a user regularly requires, can be automatically reordered again after predetermined periods of time.

Another possibility is that the operator does not photograph the code 14d associated with the text contribution 14b with the mobile telephone 10, but that the operator manually enters the coding associated with the code 14d via the keyboard into the mobile telephone 10. It is assumed that the code associated with the code 14d is usually always printed in the immediate vicinity of the code 14d as a number or sequence of numbers in the printed medium 14a. The operator can thus read the printed coding directly from the printed medium 14a and enter via the keyboard in the mobile phone 10. In this case, it is not necessary for the mobile phone 10 to derive the code from the code 14d, but the mobile phone 10 may transmit the inputted coding directly to the processing unit 16. According to the code 14d, the additional data can be transmitted from the database 26 or the processing unit 16 to the mobile telephone 10.

The steps explained above can be repeated as desired and / or carried out for different text contributions. The procedure can also be carried out for text contributions from different newspapers or magazines. As already mentioned, it is possible for different providers of additional data to be determined from the image (s) produced by the operator.

If no further information about any text contributions is desired by the operator, then the downloaded program and thus also the described method can be ended.

Claims

A method for determining acoustic speech signals of a written text (14b), in particular a printed medium (14a), wherein a mobile communication device, in particular a mobile telephone (10), with a camera is present, characterized in that a photo of the text contribution (14b ) is generated by the mobile telephone (10) that the photo is transmitted to a processing unit (16) that from the photo of the text contribution (14b) from the processing unit (16) first voice data is determined that the first voice data to the mobile phone ( 10) and that the first voice data is output from the mobile telephone (10) as acoustic voice signals.
A method for determining acoustic speech signals of a written text (14b), in particular a printed medium (14a), wherein a mobile communication device, in particular a mobile telephone (10), with a camera is present, characterized in that a photo of the text contribution (14b ) is created by the mobile telephone (10) that from the photo of the text contribution (14b) from the mobile phone (10) first voice data are determined, and that the first voice data from the mobile phone (10) are output as acoustic voice signals.
The method of claim 1, wherein from the photo of the text contribution (14b) in a first step, a machine-readable text and in a second step, the first voice data are determined.
Method according to one of the preceding claims, wherein a comparison information from the photo of the text contribution (14b) is determined, wherein the comparison information is transmitted to a database (26), and wherein depending on the comparison information additional data to the text contribution (14b) from the database (26).
The method of claim 4, wherein at least a portion of the additional data determined by the database (26) second voice data are determined, and wherein the second voice data transmitted to the mobile phone (10) and output from the mobile phone (10) as acoustic voice signals.
Method according to one of claims 4 or 5, wherein the additional data, in particular at least one further part of the additional data, displayed in the form of text and / or image data and / or multimedia data, in particular on a screen of the mobile phone (10) and / or via a Speaker of the mobile phone (10) will output.
Method according to one of the preceding claims, wherein the photo is transmitted in the form of digital data, in particular in the form of a plurality of so-called pixels (pixel = picture element).
A method according to any one of the preceding claims, wherein a program is pre-downloaded from an application database (12) to the mobile telephone (10), and wherein the program is adapted to carry out the steps of any one of the preceding claims.
On a provided with a camera mobile communication device, in particular a mobile telephone (10) running procedure for the determination of acoustic speech signals of a written text present contribution (14b) in particular a printed medium (14a), characterized in that a photo of the text contribution (14b) of the mobile telephone (10) is created, that the photo is transmitted to a processing unit (16) that first voice data from the processing unit (16) are received, and that first voice data from the mobile telephone (10) are output as acoustic voice signals, wherein the processing unit (16) from the photo of the text contribution (14b) first voice data are determined.
On a provided with a camera mobile communication device, in particular a mobile telephone (10) running procedure for the determination of acoustic speech signals of a written text present contribution (14b) in particular a printed medium (14a), characterized in that a photo of the text contribution (14b) of the mobile phone (10) is created that from the photo of the text contribution (14b) from the mobile phone (10) first voice data are determined, and that the first voice data from the mobile phone (10) are output as acoustic voice signals.
A program adapted to perform the method of claim 9 or claim 10 when loaded on a mobile telephone (10).
Mobile communication device, in particular a mobile telephone (10), on which the program according to claim 11 is loaded.
User database (12) on which the program is loaded according to claim 11.
Process on a processing unit (16) for determining acoustic speech signals of a written text contribution (14b), in particular of a printed medium (14a), characterized in that a photo of the text contribution (14b) transmitted by a mobile telephone (10) is received by the processing unit (16) is received, that from the photo of the text contribution (14b) from the processing unit (16) first voice data are determined, and that the first voice data are transmitted to the mobile telephone (10), wherein the photo of the text contribution (14b) of the Cell phone (10) is created, and wherein the first voice data from the mobile phone (10) are output as acoustic voice signals.
A program adapted to carry out the method of claim 14 when loaded on a processing unit (16).
Processing unit (16) on which the program according to claim 15 is loaded.