EP0984427A2 - Method for acoustically outputting text and speech output system - Google Patents

Method for acoustically outputting text and speech output system Download PDF

Info

Publication number
EP0984427A2
EP0984427A2 EP99710007A EP99710007A EP0984427A2 EP 0984427 A2 EP0984427 A2 EP 0984427A2 EP 99710007 A EP99710007 A EP 99710007A EP 99710007 A EP99710007 A EP 99710007A EP 0984427 A2 EP0984427 A2 EP 0984427A2
Authority
EP
European Patent Office
Prior art keywords
text
language
words
output
identified
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
EP99710007A
Other languages
German (de)
French (fr)
Other versions
EP0984427B1 (en
EP0984427A3 (en
Inventor
Walter Fehrmann
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Siemens AG
Original Assignee
Siemens AG
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Siemens AG filed Critical Siemens AG
Publication of EP0984427A2 publication Critical patent/EP0984427A2/en
Publication of EP0984427A3 publication Critical patent/EP0984427A3/en
Application granted granted Critical
Publication of EP0984427B1 publication Critical patent/EP0984427B1/en
Anticipated expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L13/00—Speech synthesis; Text to speech systems
    • G10L13/08—Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination

Definitions

  • the invention relates to a method for acoustic output of text and a speech system that has an acoustic Text output allowed.
  • the acoustic is from the published patent application DE 195 03 419 A1 Output of digitally coded traffic reports using known synthetically generated language.
  • Location related words are sent to a speech synthesis facility in that language forwarded in the related sentences were taken from a memory.
  • An adaptation of foreign language Words made to the sound of the associated sentences through a prosody conversion.
  • the speech output system illustrated in Figure 1 is in integrated a multifunction control panel of a motor vehicle, with which a car radio, a mobile phone, a navigation system and air conditioning can be controlled.
  • a microprocessor 1 has a text memory 2, in which it is a RAM. Via a telephone module or Cellular unit 3, the microprocessor 1 can wirelessly send messages received, such as an email or fax.
  • a user By operating a single control element, a user can for example one marked with the letter "E" Push button, the microprocessor 1 cause one Establish a connection with his mailbox at the internet provider and check incoming emails. The received one Text is then stored in text memory 2 and without further User action issued.
  • the mobile radio unit 3 receives a fax
  • the Microprocessor 1 successively loads the one stored in text memory 2 Words and converts them into digitized phonemes, that is, a sequence of sounds or syllables.
  • the digitized phonemes are output to an output system, that from a digital / analog converter 4, an audio amplifier 5 and at least one speaker 6.
  • the digital / analog converter 4 converts the digitized phonemes to analog voice signal, which is from the audio amplifier 5 amplified to a volume desired by the user and from Speaker 6 is played acoustically.
  • the microprocessor 1 examines a text for the occurrence of keywords and typical letter combinations in those languages in which he uses a language conversion algorithm disposes.
  • keywords are Salutations and greetings, such as “Dear”, “Mr.”, “Mrs.”, “Dear”, “Cher”, “Chère”, etc.
  • pronouns and conjunctions words based on a language can be easily identified. Similar thing applies to typical character combinations or abbreviations such as "H.”, "Mr.”, “F.”, “Fr.”, “Mr.”, “Ms.”, “M.”, “Mme”.
  • the microprocessor guides languages, after getting the first keyword or the first typical Assign the character combination to a specific language could continue his search in the text. Contradictions occur so that more than one language is identified based on the characteristic words or characters recognized a majority decision is made. Narrator is then done in the language that is most common was recognized in the text. This also leads to typing errors not a misinterpretation of language.
  • Figure 2 shows a speech system in which an additional digital signal processor 7 and a screen 8 for additional optical information output are provided.
  • the mobile radio unit 3 receives a text message and transfers it them to the microprocessor 1. This directs the text into the text memory 2 further.
  • the digital signal processor 7 examines the text for characteristic Words and combinations of characters in the Available languages and chooses for language conversion the associated language conversion algorithm.
  • the synthetic generated phonemes are the signal processor 7 to the Output system 4, 5, 6 further.
  • the digital signal processor performs the message for a fax 7 in a first step a text recognition, only then to check the language of the text and convert the recognized characters into phonemes.

Abstract

The method involves using a microprocessor to examine a text for language-characterising words or character combinations, to identify the language. The text is converted into word syllables using an algorithm created for the identified language, for reproduction via a loudspeaker. The language which occurs most in the identification stage is selected. The text is received by a vehicle by wireless means and output to the driver. A facsimile transmission received from a mobile radio unit is resolved into text characters and output acoustically. An e-mail system may be coupled to the mobile radio unit.

Description

Die Erfindung betrifft ein Verfahren zum akustischen Ausgeben von Text und ein Sprachausgabesystem, das eine akustische Ausgabe von Text erlaubt.The invention relates to a method for acoustic output of text and a speech system that has an acoustic Text output allowed.

Aus der Offenlegungsschrift DE 195 03 419 A1 ist die akustische Ausgabe von digital codierten Verkehrsmeldungen mittels synthetisch erzeugter Sprache bekannt. Ortsbezogene Wörter werden in derjenigen Sprache an eine Sprachsynthese-Einrichtung weitergeleitet, in der die zugehörigen Sätze aus einem Speicher entnommen wurden. Eine Anpassung von fremdsprachigen Wörtern an den Klang der zugehörigen Sätze erfolgt durch eine Prosodie-Konversion.The acoustic is from the published patent application DE 195 03 419 A1 Output of digitally coded traffic reports using known synthetically generated language. Location related words are sent to a speech synthesis facility in that language forwarded in the related sentences were taken from a memory. An adaptation of foreign language Words made to the sound of the associated sentences through a prosody conversion.

Aus dem Textverarbeitungsprogramm Nisus® Writer von Nisus Software, Inc. ist eine Sprachausgabe oder ein "Vorlesen" von geschriebenem Text bekannt. Für jede Sprache, in der ein Text akustisch ausgegeben werden kann, steht ein eigener Sprachumwandlungs-Algorithmus (Text-to-speach-Algorithmus) zur Verfügung. Ein solcher Algorithmus wandelt Schriftzeichen in aufeinanderfolgende Phoneme oder Wortsilben um. Der Benutzer kann aus einem Menü für eine bestimmte Sprache den entsprechenden Sprachumwandlungs-Algorithmus wählen. Liegt der Text in einer Sprache vor, für die der Sprachumwandlungs-Algorithmus nicht bestimmt ist, so ist die Sprachausgabe nicht verständlich.From the Nisus® Writer word processor Software, Inc. is a speech or "reading aloud" from written text known. For every language in which a text can be output acoustically, there is a separate language conversion algorithm (Text-to-speach algorithm). Such an algorithm converts characters into successive ones Phonemes or syllables around. The user can choose from a menu for a specific language Select the language conversion algorithm. Is the text in a language for which the speech conversion algorithm is not determined, so is the speech output not understandable.

Bei verschiedenen Anwendungen ist es unvorteilhaft, wenn eine Benutzeraktion erforderlich ist, um für einen Text in einer bestimmten Sprache den dazugehörigen Sprachumwandlungs-Algorithmus auszuwählen. Insbesondere in einem Kraftfahrzeug wird der Sicherheitsvorteil für einen Fahrzeugführer, der in der akustischen Ausgabe eines Texts liegt, wenigstens teilweise zunichte gemacht, wenn der Fahrzeugführer zunächst die Sprache des Textes überprüfen muß und anschließend den entsprechenden Sprachumwandlungs-Algorithmus suchen und auswählen muß.In various applications, it is disadvantageous if one User response is required in order for a text in a specific language the associated language conversion algorithm to select. Especially in a motor vehicle becomes the safety benefit for a driver operating in the acoustic output of a text is, at least partially destroyed if the driver first the Check the language of the text and then the corresponding one Find and select the speech conversion algorithm got to.

In der Patentanmeldung EP 0 889 626 Al ist ein Nachrichtenübermittlungssystem für Fernsprechteilnehmer bekannt, bei dem ein System für aufgezeichnete akustische Nachrichten (voice mail) mit einem E-mail-System gekoppelt ist. E-mails können akustisch an einen Teilnehmer ausgegeben werden. Um für die Sprachausgabe den richtigen Sprachumwandlungs-Algorithmus wählen zu können, werden E-mails auf Buchstabenkombinationen mit drei aufeinanderfolgenden Buchstaben untersucht. Aufgrund der Häufigkeit des Auftretens der Buchstabenkombinationen werden Rückschlüsse auf die verwendete Sprache gezogen. Dieses Verfahren benötigt erheblichen Aufwand für die Implementierung des Systems. Es müssen in einem solchen System erhebliche Ressourcen an Speicher und Rechenleistung für den Programmablauf und für entsprechende Bibliotheken zur Verfügung gestellt werden. Dies ist insbesondere bei Anwendungen in Kraftfahrzeugen unerwünscht. Außerdem ist eine zuverlässige Unterscheidung zwischen ähnlichen Sprachen insbesondere dann problematisch, wenn die Nachrichten kurz sind und mit anderssprachlichen Fachbegriffen angereichert sind.In the patent application EP 0 889 626 A1 there is a message transmission system known for telephone subscribers, where a system for recorded acoustic messages (voice mail) is coupled with an e-mail system. E-mails can be acoustically output to a participant. To for the The correct speech conversion algorithm To be able to choose, e-mails are based on letter combinations examined with three consecutive letters. Because of the frequency of the combination of letters conclusions are drawn about the language used. This The process requires considerable effort for implementation of the system. It must be substantial in such a system Resources in memory and computing power for program execution and available for appropriate libraries be put. This is especially true for applications in Motor vehicles undesirable. It is also a reliable one Differentiation between similar languages especially then problematic when the news is short and with different language Technical terms are enriched.

Es ist ein Ziel der Erfindung, ein Verfahren zum akustischen Ausgeben von Text und ein Sprachausgabesystem bereit zu stellen, die auf besonders effiziente und zuverlässige Weise eine korrekte Wiedergabe von Texten erlauben, die in unterschiedlichen Sprachen vorliegen können.It is an object of the invention to provide an acoustic method Outputting text and providing a screen reader system which is particularly efficient and reliable allow correct reproduction of texts in different Languages can be available.

Dieses Ziel wird mit einem Verfahren und einem Sprachausgabesystem erreicht, wie sie in den unabhängigen Patentansprüchen definiert sind. Vorteilhafte Weiterbildungen der Erfindung sind in den Unteransprüchen angegeben. This goal is achieved with a procedure and a speech system achieved as in the independent claims are defined. Advantageous developments of the invention are specified in the subclaims.

Vor Beginn der Sprachausgabe wird ein Text auf Wörter oder Abkürzungen untersucht, die für eine Sprache charakteristisch sind, um die Sprache des Textes zu identifizieren. Aufgrund der erkannten Sprache wird ein speziell der erkannten Sprache zugeordneter Algorithmus für die akustische Ausgabe des Textes automatisch gewählt. Dadurch werden die synthetisch erzeugten Phoneme, bzw. die Wortsilben oder Laute, richtig betont.Before the speech begins, a text on words or Abbreviations examined that are characteristic of a language are used to identify the language of the text. Because of the recognized language becomes a specially the recognized language assigned algorithm for the acoustic output of the text automatically selected. This will produce the synthetically Phonemes, or the word syllables or sounds, emphasized correctly.

Trifft beispielsweise ein schriftlicher Text über Rundfunk oder Mobilfunk, insbesondere Mobiltelefon, z. B. über das Radio-Daten-System (RDS) bzw. beim Mobilfunk über Short Message Service (SMS), in einen Personenkraftwagen ein, so kann der Text ohne Bedienaktion des Fahrzeugführers in der für die Sprache des Textes geeignetes Sprechweise wiedergegeben werden. Dies ist insbesondere bedeutsam für Geschäftsreisende, die auch Kontakte mit fremdsprachigen Kunden pflegen.For example, meets a written text on broadcast or mobile communications, especially mobile phones, e.g. B. on the radio data system (RDS) or for mobile communications via short message Service (SMS) in a passenger car, so the Text without operator action by the driver in the for the Language of the text can be reproduced in a suitable manner. This is particularly important for business travelers, who also maintain contacts with foreign-language customers.

Weitere Vorteile, Merkmale und Anwendungsmöglichkeiten der Erfindung ergeben sich aus der Beschreibung von bevorzugten Ausführungsbeispielen in Verbindung mit den Zeichnungen. Es zeigen:

Figur 1
ein Sprachausgabesystem, bei dem ein zentraler Mikroprozessor Text in Sprachdaten umwandelt, und
Figur 2
ein Sprachausgabesystem mit digitalem Signalprozessor.
Further advantages, features and possible uses of the invention result from the description of preferred exemplary embodiments in conjunction with the drawings. Show it:
Figure 1
a speech output system in which a central microprocessor converts text into speech data, and
Figure 2
a speech system with a digital signal processor.

Das in Figur 1 veranschaulichte Sprachausgabesystem ist in ein Multifunktions-Bedienteil eines Kraftfahrzeugs integriert, mit dem ein Autoradio, ein Mobiltelefon, ein Navigationssystem und eine Klimaanlage gesteuert werden.The speech output system illustrated in Figure 1 is in integrated a multifunction control panel of a motor vehicle, with which a car radio, a mobile phone, a navigation system and air conditioning can be controlled.

Ein Mikroprozessor 1 weist einen Textspeicher 2, bei dem es sich um ein RAM handelt, auf. Über ein Telefonmodul oder eine Mobilfunkeinheit 3 kann der Mikroprozessor 1 drahtlos Nachrichten empfangen, wie beispielsweise ein E-Mail oder ein Telefax.A microprocessor 1 has a text memory 2, in which it is a RAM. Via a telephone module or Cellular unit 3, the microprocessor 1 can wirelessly send messages received, such as an email or fax.

Ein Benutzer kann durch Betätigung eines einzigen Bedienelements, beispielsweise eines mit dem Buchstaben "E" gekennzeichneten Druckknopfs, den Mikroprozessor 1 veranlassen, eine Verbindung mit seiner Mailbox beim Internet-Provider aufzubauen und eingetroffene E-Mails abzurufen. Der empfangene Text wird dann im Textspeicher 2 gespeichert und ohne weitere Aktion des Benutzers ausgegeben.By operating a single control element, a user can for example one marked with the letter "E" Push button, the microprocessor 1 cause one Establish a connection with his mailbox at the internet provider and check incoming emails. The received one Text is then stored in text memory 2 and without further User action issued.

Empfängt die Mobilfunkeinheit 3 ein Telefax, so wird der im Telefax als Bildpunkte enthaltene Text von einer Texterkennungssoftware in Worte mit definierten Schriftzeichen umgesetzt, um in dem Textspeicher 2 gespeichert zu werden. Der Mikroprozessor 1 lädt nacheinander die im Textspeicher 2 gespeicherte Worte und wandelt diese in digitalisierte Phoneme, also in eine Aufeinanderfolge von Lauten oder Wortsilben um.If the mobile radio unit 3 receives a fax, the Text contained as faxes from text recognition software translated into words with defined characters, to be stored in the text memory 2. The Microprocessor 1 successively loads the one stored in text memory 2 Words and converts them into digitized phonemes, that is, a sequence of sounds or syllables.

Die digitalisierten Phoneme werden an ein Ausgabesystem ausgegeben, das aus einem Digital-/Analogwandler 4, einem Audioverstärker 5 und mindestens einem Lautsprecher 6 besteht.The digitized phonemes are output to an output system, that from a digital / analog converter 4, an audio amplifier 5 and at least one speaker 6.

Der Digital-/Analogwandler 4 wandelt die digitalisierten Phoneme in analoges Sprachsignal um, das vom Audioverstärker 5 auf eine vom Benutzer gewünschte Lautstärke verstärkt und vom Lautsprecher 6 akustisch wiedergegeben wird.The digital / analog converter 4 converts the digitized phonemes to analog voice signal, which is from the audio amplifier 5 amplified to a volume desired by the user and from Speaker 6 is played acoustically.

Der Mikroprozessor 1 untersucht einen Text auf das Vorkommen von Schlüsselwörtern und typischen Buchstabenkombinationen in denjenigen Sprachen, in denen er jeweils über einen Sprachumwandlungs-Algorithmus verfügt. Solche Schlüsselwörter sind Anreden und Grußformeln, wie beispielsweise "Sehr geehrte(r)", "Herr", "Frau", "Dear", "Cher", "Chère", etc. Ferner sind Artikel, Pronomen und Konjunktionen Wörter, anhand denen auf einfache Weise eine Sprache identifizierbar ist. Ähnliches gilt für typische Schriftzeichenkombinationen oder Abkürzungen wie "H.", "Hr.", "F.", "Fr.", "Mr.", "Ms.", "M.", "Mme".The microprocessor 1 examines a text for the occurrence of keywords and typical letter combinations in those languages in which he uses a language conversion algorithm disposes. Such keywords are Salutations and greetings, such as "Dear", "Mr.", "Mrs.", "Dear", "Cher", "Chère", etc. Furthermore are articles, pronouns and conjunctions words based on a language can be easily identified. Similar thing applies to typical character combinations or abbreviations such as "H.", "Mr.", "F.", "Fr.", "Mr.", "Ms.", "M.", "Mme".

Da manchmal die Anrede und der sich anschließende Text in unterschiedlichen Sprachen gehalten sind, führt der Mikroprozessor, nachdem er das erste Schlüsselwort oder die erste typische Schriftzeichenkombination einer konkreten Sprache zuordnen konnte, seine Suche im Text fort. Treten Widersprüche auf, so daß mehr als eine Sprache aufgrund der identifizierten charakteristischen Wörter oder Schriftzeichen erkannt wird, so erfolgt eine Mehrheitsentscheidung. Die Sprachausgabe wird dann in derjenigen Sprache vorgenommen, die am häufigsten im Text erkannt wurde. Damit führen auch Schreibfehler nicht zu einer Fehlinterpretation der Sprache.Because sometimes the title and the subsequent text in different The microprocessor guides languages, after getting the first keyword or the first typical Assign the character combination to a specific language could continue his search in the text. Contradictions occur so that more than one language is identified based on the characteristic words or characters recognized a majority decision is made. Narrator is then done in the language that is most common was recognized in the text. This also leads to typing errors not a misinterpretation of language.

Figur 2 zeigt ein Sprachausgabesystem, bei dem zusätzlich ein digitaler Signalprozessor 7 und ein Bildschirm 8 zur zusätzlichen optischen Informationsausgabe vorgesehen sind.Figure 2 shows a speech system in which an additional digital signal processor 7 and a screen 8 for additional optical information output are provided.

Die Mobilfunkeinheit 3 empfängt eine Textnachricht und übergibt sie an den Mikroprozessor 1. Dieser leitet den Text in den Textspeicher 2 weiter.The mobile radio unit 3 receives a text message and transfers it them to the microprocessor 1. This directs the text into the text memory 2 further.

Der digitale Signalprozessor 7 untersucht den Text auf charakteristische Wörter und Zeichenkombinationen in den zur Verfügung stehenden Sprachen und wählt zur Sprachkonversion den zugehörigen Sprachumwandlungs-Algorithmus aus. Die synthetisch erzeugten Phoneme gibt der Signalprozessor 7 an das Ausgabesystem 4, 5, 6 weiter. The digital signal processor 7 examines the text for characteristic Words and combinations of characters in the Available languages and chooses for language conversion the associated language conversion algorithm. The synthetic generated phonemes are the signal processor 7 to the Output system 4, 5, 6 further.

Handelt es sich bei der von der Mobilfunkeinheit 3 empfangenen Nachricht um ein Telefax, so führt der digitale Signalprozessor 7 in einem ersten Schritt eine Texterkennung durch, um erst anschließend die Sprache des Texts zu überprüfen und die erkannten Schriftzeichen in Phoneme zu wandeln.Is it the one received by the mobile radio unit 3 The digital signal processor performs the message for a fax 7 in a first step a text recognition, only then to check the language of the text and convert the recognized characters into phonemes.

Claims (5)

Verfahren zum akustischen Ausgeben von Text, bei dem ein Text von einem Mikroprozessor (1) auf für eine Sprache charakteristische Wörter oder Abkürzungen untersucht wird, um die Sprache des Texts zu identifizieren, und der Text mit einem Algorithmus, der für die identifizierte Sprache geschaffen ist, in Wortsilben umgerechnet wird, um über einen Lautsprecher wiedergegeben zu werden. Method for the acoustic output of text, in which a text is examined by a microprocessor (1) for words or abbreviations characteristic of a language in order to identify the language of the text, and the text is converted into word syllables using an algorithm that is created for the identified language in order to be reproduced via a loudspeaker. Verfahren nach Anspruch 1, dadurch gekennzeichnet, daß bei Identifizierung von Wörtern oder Schriftzeichenkombinationen unterschiedlicher Sprachen diejenige Sprache gewählt wird, die am häufigsten identifiziert wurde.A method according to claim 1, characterized in that at Identification of words or combinations of characters different languages the language is selected, most commonly identified. Verfahren nach einem der vorhergehenden Patentansprüche, dadurch gekennzeichnet, daß der Text drahtlos in einem Fahrzeug empfangen und an einen Fahrzeugführer ausgegeben wird.Method according to one of the preceding claims, characterized in that the text is wireless in a vehicle received and issued to a driver. Verfahren nach Anspruch 1 oder 2, dadurch gekennzeichnet, daß eine mit einer Mobilfunkeinheit (3) empfangene Telefax-Nachricht in Schriftzeichen aufgelöst und akustisch ausgegeben wird.A method according to claim 1 or 2, characterized in that that a fax message received with a mobile radio unit (3) resolved in characters and output acoustically becomes. Sprachausgabesystem für ein E-mail-System, das mit einer Mobilfunkeinheit (3) gekoppelt ist, das aufweist: ein Bedienelement, über dessen Betätigung automatisch eine Anwahl in eine Internet-Mailbox des Benutzers und ein Laden der eingegangenen E-mails erfolgt, einen Textspeicher (2), einen Mikroprozessor (1; 7), mit dem die für einen in dem Textspeicher (2) gespeicherter Text verwendete Sprache aufgrund von für eine Sprache charakteristischen Wörtern oder Abkürzungen identifizierbar ist und mit dem der Text in digitalisierte Phoneme der identifizierten Sprache umwandelbar ist, ein Ausgabesystem (4, 5, 6) zur Ausgabe der digitalisierten Phoneme als Sprache. Speech system for an e-mail system, which is coupled to a mobile radio unit (3), comprising: a control element which, when activated, is automatically dialed into a user's Internet mailbox and the incoming e-mails are loaded a text memory (2), a microprocessor (1; 7) with which the language used for a text stored in the text memory (2) can be identified on the basis of words or abbreviations characteristic of a language and with which the text can be converted into digitized phonemes of the identified language, an output system (4, 5, 6) for outputting the digitized phonemes as speech.
EP19990710007 1998-09-03 1999-09-03 Method for acoustically outputting text Expired - Lifetime EP0984427B1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE1998140890 DE19840890A1 (en) 1998-09-03 1998-09-03 Process for acoustic output of text and speech system
DE19840890 1998-09-03

Publications (3)

Publication Number Publication Date
EP0984427A2 true EP0984427A2 (en) 2000-03-08
EP0984427A3 EP0984427A3 (en) 2000-11-02
EP0984427B1 EP0984427B1 (en) 2013-01-30

Family

ID=7880157

Family Applications (1)

Application Number Title Priority Date Filing Date
EP19990710007 Expired - Lifetime EP0984427B1 (en) 1998-09-03 1999-09-03 Method for acoustically outputting text

Country Status (3)

Country Link
EP (1) EP0984427B1 (en)
JP (1) JP2000089776A (en)
DE (1) DE19840890A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2002021508A1 (en) * 2000-09-06 2002-03-14 Telefonaktiebolaget Lm Ericsson (Publ) Text language detection
CN109086026A (en) * 2018-07-17 2018-12-25 阿里巴巴集团控股有限公司 Broadcast the determination method, apparatus and equipment of voice

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE19963812A1 (en) * 1999-12-30 2001-07-05 Nokia Mobile Phones Ltd Method for recognizing a language and for controlling a speech synthesis unit and communication device
JP3908437B2 (en) 2000-04-14 2007-04-25 アルパイン株式会社 Navigation system
DE10047279A1 (en) * 2000-09-23 2002-04-18 Henryk Bury Gmbh Dipl Ing Motor vehicle with car telephone with small display and navigation system with display has ability to transfer short text messages to display of navigation system

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4829580A (en) * 1986-03-26 1989-05-09 Telephone And Telegraph Company, At&T Bell Laboratories Text analysis system with letter sequence recognition and speech stress assignment arrangement
US5062143A (en) * 1990-02-23 1991-10-29 Harris Corporation Trigram-based method of language identification
EP0776097A2 (en) * 1995-11-23 1997-05-28 Wireless Links International Ltd. Mobile data terminals with text-to-speech capability
US5664027A (en) * 1993-04-20 1997-09-02 Lucent Technologies Inc. Methods and apparatus for inferring orientation of lines of text
GB2318659A (en) * 1996-09-30 1998-04-29 Ibm Natural language determination using letter pairs in commonly occuring words
EP0845894A2 (en) * 1996-11-05 1998-06-03 Boston Technology Inc. A system for accessing multimedia mailboxes and messages over the internet and via telephone
EP0849925A1 (en) * 1996-12-17 1998-06-24 ICO Services Ltd. Enhanced message centre

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE19503419A1 (en) * 1995-02-03 1996-08-08 Bosch Gmbh Robert Method and device for outputting digitally coded traffic reports using synthetically generated speech
EP0889626A1 (en) * 1997-07-04 1999-01-07 Octel Communications Corporation Unified messaging system with automatic language identifacation for text-to-speech conversion

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4829580A (en) * 1986-03-26 1989-05-09 Telephone And Telegraph Company, At&T Bell Laboratories Text analysis system with letter sequence recognition and speech stress assignment arrangement
US5062143A (en) * 1990-02-23 1991-10-29 Harris Corporation Trigram-based method of language identification
US5664027A (en) * 1993-04-20 1997-09-02 Lucent Technologies Inc. Methods and apparatus for inferring orientation of lines of text
EP0776097A2 (en) * 1995-11-23 1997-05-28 Wireless Links International Ltd. Mobile data terminals with text-to-speech capability
GB2318659A (en) * 1996-09-30 1998-04-29 Ibm Natural language determination using letter pairs in commonly occuring words
EP0845894A2 (en) * 1996-11-05 1998-06-03 Boston Technology Inc. A system for accessing multimedia mailboxes and messages over the internet and via telephone
EP0849925A1 (en) * 1996-12-17 1998-06-24 ICO Services Ltd. Enhanced message centre

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
"LANGUAGE IDENTIFICATION IN TELETEXT TRANSMISSIONS" RESEARCH DISCLOSURE,GB,INDUSTRIAL OPPORTUNITIES LTD. HAVANT, Nr. 368, 1. Dezember 1994 (1994-12-01), Seite 695 XP000497350 ISSN: 0374-4353 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2002021508A1 (en) * 2000-09-06 2002-03-14 Telefonaktiebolaget Lm Ericsson (Publ) Text language detection
GB2366940B (en) * 2000-09-06 2004-08-11 Ericsson Telefon Ab L M Text language detection
US7035801B2 (en) 2000-09-06 2006-04-25 Telefonaktiebolaget L M Ericsson (Publ) Text language detection
CN109086026A (en) * 2018-07-17 2018-12-25 阿里巴巴集团控股有限公司 Broadcast the determination method, apparatus and equipment of voice

Also Published As

Publication number Publication date
JP2000089776A (en) 2000-03-31
EP0984427B1 (en) 2013-01-30
DE19840890A1 (en) 2000-04-06
EP0984427A3 (en) 2000-11-02

Similar Documents

Publication Publication Date Title
DE60036931T2 (en) USER LANGUAGE INTERFACE FOR VOICE-CONTROLLED SYSTEMS
DE60033122T2 (en) User interface for text-to-speech conversion
US5920835A (en) Method and apparatus for processing and transmitting text documents generated from speech
DE60217241T2 (en) Focused language models to improve the speech input of structured documents
US20060069567A1 (en) Methods, systems, and products for translating text to speech
DE112005000924T5 (en) Voice over Short Message Service
DE10117367B4 (en) Method and system for automatically converting text messages into voice messages
EP1282897B1 (en) Method for creating a speech database for a target vocabulary in order to train a speech recognition system
EP0984427B1 (en) Method for acoustically outputting text
EP1241600A1 (en) Method and communication system for the generation of responses to questions
DE69933614T2 (en) SYSTEM FOR DISTRIBUTING, TRANSMITTING AND RECEIVING NEWS AND METHOD FOR DISTRIBUTING MESSAGES
EP2047668A1 (en) Method, spoken dialog system, and telecommunications terminal device for multilingual speech output
WO2005106847A2 (en) Method and device for acoustic access to an application computer
DE19503419A1 (en) Method and device for outputting digitally coded traffic reports using synthetically generated speech
DE102006056286B4 (en) A method of reproducing text information by voice in a vehicle
EP1251680A1 (en) Voice-controlled directory service for connection to a Data Network
DE69910412T2 (en) VOICE CONTROLLED NAVIGATION FOR AN ELECTRONIC POST READER
DE3300053A1 (en) LANGUAGE-RELATED MOBILE STATUS UNIT
EP1071056B1 (en) Method for wireless information transmission between a vehicle internal terminal and a central computer
Sala et al. Speechdat-Car: Speech databases for voice driven teleservices and control of in-car applications
DE10163277C2 (en) Method for sending a message to a phone number, and device therefor
DE10132871B4 (en) Method and device for sending previously stored voice messages
EP2051242B1 (en) Method for generating speech patterns for speech controlled station tuning
DE10144688A1 (en) SMS message from speech recognition is reconverted at receiving telephone
EP1122716A2 (en) Appararus for the transformation of printed text into speech

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

AK Designated contracting states

Kind code of ref document: A2

Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE

AX Request for extension of the european patent

Free format text: AL;LT;LV;MK;RO;SI

PUAL Search report despatched

Free format text: ORIGINAL CODE: 0009013

AK Designated contracting states

Kind code of ref document: A3

Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE

AX Request for extension of the european patent

Free format text: AL;LT;LV;MK;RO;SI

17P Request for examination filed

Effective date: 20010122

AKX Designation fees paid

Free format text: AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE

17Q First examination report despatched

Effective date: 20071120

GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

GRAS Grant fee paid

Free format text: ORIGINAL CODE: EPIDOSNIGR3

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

AK Designated contracting states

Kind code of ref document: B1

Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE

REG Reference to a national code

Ref country code: GB

Ref legal event code: FG4D

Free format text: NOT ENGLISH

REG Reference to a national code

Ref country code: CH

Ref legal event code: EP

REG Reference to a national code

Ref country code: AT

Ref legal event code: REF

Ref document number: 595837

Country of ref document: AT

Kind code of ref document: T

Effective date: 20130215

Ref country code: CH

Ref legal event code: EP

REG Reference to a national code

Ref country code: IE

Ref legal event code: FG4D

Free format text: LANGUAGE OF EP DOCUMENT: GERMAN

RAP2 Party data changed (patent owner data changed or rights of a patent transferred)

Owner name: SIEMENS AKTIENGESELLSCHAFT

REG Reference to a national code

Ref country code: DE

Ref legal event code: R096

Ref document number: 59915366

Country of ref document: DE

Effective date: 20130328

REG Reference to a national code

Ref country code: NL

Ref legal event code: VDEP

Effective date: 20130130

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130130

Ref country code: CY

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130130

Ref country code: ES

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130511

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: PT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130530

Ref country code: NL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130130

Ref country code: GR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130501

Ref country code: FI

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130130

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: DK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130130

PLBE No opposition filed within time limit

Free format text: ORIGINAL CODE: 0009261

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: IT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130130

26N No opposition filed

Effective date: 20131031

REG Reference to a national code

Ref country code: DE

Ref legal event code: R097

Ref document number: 59915366

Country of ref document: DE

Effective date: 20131031

BERE Be: lapsed

Owner name: SIEMENS A.G.

Effective date: 20130930

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: MC

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130130

REG Reference to a national code

Ref country code: CH

Ref legal event code: PL

REG Reference to a national code

Ref country code: IE

Ref legal event code: MM4A

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: LI

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20130930

Ref country code: IE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20130903

Ref country code: BE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20130930

Ref country code: CH

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20130930

REG Reference to a national code

Ref country code: AT

Ref legal event code: MM01

Ref document number: 595837

Country of ref document: AT

Kind code of ref document: T

Effective date: 20130903

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: AT

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20130903

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: LU

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20130903

REG Reference to a national code

Ref country code: FR

Ref legal event code: PLFP

Year of fee payment: 18

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: GB

Payment date: 20160914

Year of fee payment: 18

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: FR

Payment date: 20160914

Year of fee payment: 18

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: DE

Payment date: 20161121

Year of fee payment: 18

REG Reference to a national code

Ref country code: DE

Ref legal event code: R119

Ref document number: 59915366

Country of ref document: DE

GBPC Gb: european patent ceased through non-payment of renewal fee

Effective date: 20170903

REG Reference to a national code

Ref country code: FR

Ref legal event code: ST

Effective date: 20180531

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: GB

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20170903

Ref country code: DE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20180404

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: FR

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20171002