EP1248251A2 - Method and device for automatically converting text messages to speech messages - Google Patents

Method and device for automatically converting text messages to speech messages Download PDF

Info

Publication number
EP1248251A2
EP1248251A2 EP02003909A EP02003909A EP1248251A2 EP 1248251 A2 EP1248251 A2 EP 1248251A2 EP 02003909 A EP02003909 A EP 02003909A EP 02003909 A EP02003909 A EP 02003909A EP 1248251 A2 EP1248251 A2 EP 1248251A2
Authority
EP
European Patent Office
Prior art keywords
speech
text
voice
profile
messages
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.)
Withdrawn
Application number
EP02003909A
Other languages
German (de)
French (fr)
Other versions
EP1248251A3 (en
Inventor
Volker Luegger
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.)
Unify GmbH and Co KG
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 EP1248251A2 publication Critical patent/EP1248251A2/en
Publication of EP1248251A3 publication Critical patent/EP1248251A3/en
Withdrawn legal-status Critical Current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

Definitions

  • the present invention relates to a method as well as a system that can write any machine readable Text messages, such as emails or fax messages, via a suitable acoustic reproduction system, for example, via a cell phone, based on a acoustically outputs previously generated voice profile.
  • a suitable acoustic reproduction system for example, via a cell phone, based on a acoustically outputs previously generated voice profile.
  • the present invention is therefore based on the object a speech reproduction of machine-readable texts with to achieve synthetically generated voices so that a Alienation when listening to the generated voice is avoided.
  • the user's voice sample data can be analyzed and created a language profile based on this analysis becomes. Based on the created language profile any text message data approximated, so good recognizable to output with the user's voice become.
  • the sender is identified on the basis of voice if the text message data matches the Voices can be assigned accordingly.
  • creating the language profile by comparing a written reference text with one generated by acoustic articulation of a speaker Reference text are made.
  • a system for implementing Text messages in voice messages claimed.
  • This has a speech analyzer based on a Analysis of voice sample data a voice profile for entered Voice sample data generated.
  • This system also includes a speech generator based on the speech profile any text message in synthetic Implements voice sample data.
  • the figure shows schematically a technique for automatic Conversion of text messages into voice messages.
  • a method or a system is shown schematically in the figure for the automatic conversion of text messages into voice messages shown.
  • One from any person spoken text 1 is replaced by a step S1 Analyzer 2 analyzed. This usually happens because that the acoustic signals are registered analogously and converted into digital voice files by an A / D converter become.
  • Step S3 based on the analysis of the digital Language files creates a voice profile 3 of this person become.
  • the spoken text 1 can be any Free text or a reference text 8, the one step S2 as part of the analysis with the written form of the Reference text 8 is compared.
  • Based on the language profile 3 can be in the following any text message 5 via a speech generator 4 translate into synthetic voice message data 6 (step S5 and step S6).
  • the text message 5 can then in a step S7 according to the created language profile 3 be output acoustically.
  • a speech generator 4 for a synthetically generated language can be set so that any texts 5 with the voice of this speaker acoustically can be spent. Because of the possible Narrator with a natural and above all familiar Voice becomes strange when you hear the speech avoided. Of course, it is also conceivable that Speech generator speech samples of different people and thus multiple language profiles are available. So that's one Different speakers can be selected.
  • an author sends one Recipient an email message.
  • the destination address is the Author the recipient's phone number.
  • the used Unified Message System determines that as a recipient no E-mail connection, but a telephone connection selected was and therefore puts the entered text in a Voice message around. A language profile is used for this, which was previously created based on a speech sample by this author has been. With this, the voice of the synthetically produced So far the natural voice of the author approximated that the recipient uses the synthetic voice as a recognizes the familiar voice of the sending person.
  • the Unified Message System now initiates the construction of a Connection to the telephone line of the receiver and gives the Voice message with the author's voice.

Abstract

The conversion method has entered text information data (5) converted into synthetic speech information data (6) using a speech profile (3) obtained by analysis of sample speech data entered via a user, to allow the spoken text to approximate the speaking voice of the user. Also included are Independent claims for the following: (a) a system for automatic conversion of text information into speech information; (b) a mobile telephone with a system for automatic conversion of text information into speech information

Description

Die vorliegende Erfindung bezieht sich auf ein Verfahren sowie ein System, das beliebige geschriebene maschinenlesbare Text-Nachrichten, beispielsweise E-Mails oder Fax-Nachrichten, über ein geeignetes akustisches Wiedergabesystem, beispielsweise über ein Mobiltelephon, auf Grundlage eines zuvor generierten Stimmenprofils akustisch ausgibt.The present invention relates to a method as well as a system that can write any machine readable Text messages, such as emails or fax messages, via a suitable acoustic reproduction system, for example, via a cell phone, based on a acoustically outputs previously generated voice profile.

Nach dem Stand der Technik ist es bekannt, in einer Multimedia-Umgebung Inhalte von E-Mails, Fax-Nachrichten oder sonstigen Texten mittels fest vorgegebener synthetisch erzeugter Stimmen auszugeben. Um die Kommunikation in einer Multimedia-Umgebung (in der Literatur wird in diesem Zusammenhang häufig von einem "Unified Message System" gesprochen) so natürlich wie möglich erscheinen zu lassen, ist es von Interesse, die entsprechende Text-Nachricht mit der Stimme des jeweiligen Autors auszugeben.It is known in the prior art to be in a multimedia environment Contents of emails, faxes or other texts using fixed synthetic output generated voices. To communicate in one Multimedia environment (in the literature this is Often related to a "Unified Message System" spoken) to appear as natural as possible, it is of interest to use the appropriate text message the voice of the respective author.

Aus der DE 198 41 683 A1 ist eine Vorrichtung und ein Verfahren zur digitalen Sprachbearbeitung bekannt. Die in eine Sprachausgabe umsetzbaren Wörter sind in einer Tabelle (Wörterbuch) zusammen mit Informationen zu ihrer Aussprache (phonetische Einträge, phonetische Entsprechungen) verzeichnet. Ein Übersetzer erzeugt aus den phonetischen Einträgen der einzelnen Worte eine Sprachnachrichten-Datei, die in einem Editor (Editiereinrichtung) in Form einer Lautschrift angezeigt und bearbeitet werden kann. Zur Bearbeitung werden Parameter (Modifikatoren) hinzugefügt oder verändert. Die Parameter verschiedener Sprechertypen (Mann, Frau, Kind etc.) sind in jeweils einem Sprachprofil (Sprechermodell) zusammengefasst und als Standardmodelle vorgegeben. Durch Anpassung der Parameter gestaltet (editiert) der Benutzer die "Stimme" der anschließenden synthetischen Sprachausgabe bis zum gewünschten qualitativen Zustand.DE 198 41 683 A1 describes a device and a Methods for digital speech processing known. In the Words that can be implemented are in a table (Dictionary) along with information on their pronunciation (phonetic entries, phonetic equivalents) recorded. A translator creates from the phonetic Entries of the individual words a voice message file, which in an editor (editing facility) in the form of a Phonetic transcription can be viewed and edited. to Editing parameters (modifiers) are added or changed. The parameters of different types of speakers (man, Woman, child etc.) are each in a language profile (Speaker model) summarized and as standard models specified. Designed by adjusting the parameters (edited) the user the "voice" of the subsequent synthetic speech to the desired qualitative Status.

Bei dem bekannten Verfahren hat sich als nachteilig erwiesen, dass die erzeugte, natürlichen Stimmen nachempfundene Sprachausgabe meist immer noch künstlich oder fremd klingt und dem Hörer nicht vertraut ist.In the known method, it has proven to be disadvantageous that the generated, natural voices are modeled Narrator still sounds artificial or strange and is not familiar to the listener.

Der vorliegenden Erfindung liegt daher die Aufgabe zugrunde, eine Sprachwiedergabe von maschinenlesbaren Texten mit synthetisch erzeugten Stimmen so zu erreichen, dass ein Befremden beim Hören der erzeugten Stimme vermieden wird.The present invention is therefore based on the object a speech reproduction of machine-readable texts with to achieve synthetically generated voices so that a Alienation when listening to the generated voice is avoided.

Diese Aufgabe wird gemäß der Erfindung durch die Merkmale der unabhängigen Ansprüche gelöst. Die abhängigen Ansprüche bilden den zentralen Gedanken in vorteilhafter Weise weiter.This object is achieved according to the invention by the features of independent claims solved. The dependent claims develop the central idea in an advantageous manner.

Erfindungsgemäß wird vorgeschlagen, dass zur automatischen Umsetzung von Text-Nachrichten in Sprach-Nachrichten eines Benutzers Sprachprobedaten des Benutzers analysiert werden und auf Grundlage dieser Analyse ein Sprachprofil erstellt wird. Auf Grundlage des erstellten Sprachprofiles können beliebige Text-Nachrichtendaten angenähert, also gut wiedererkennbar, mit der Stimme des Benutzers auszugeben werden. Insbesondere ist ein Erkennen des Absenders anhand der Stimme möglich, wenn die Text-Nachrichtendaten den Stimmen ensprechend zugeordnet werden.According to the invention it is proposed that for automatic Conversion of text messages into voice messages The user's voice sample data can be analyzed and created a language profile based on this analysis becomes. Based on the created language profile any text message data approximated, so good recognizable to output with the user's voice become. In particular, the sender is identified on the basis of voice if the text message data matches the Voices can be assigned accordingly.

Das Erstellen des Sprachprofiles kann dabei beispielsweise durch einen Vergleich eines schriftlichen Referenz-Textes mit einem durch akustische Artikulation eines Sprechers erzeugten Referenz-Text erfolgen.For example, creating the language profile by comparing a written reference text with one generated by acoustic articulation of a speaker Reference text are made.

Erfindungsgemäß wird weiterhin ein System zur Umsetzung von Text-Nachrichten in Sprach-Nachrichten beansprucht. Dieses weist einen Sprachanalysator auf, der auf Grundlage einer Analyse von Sprachprobedaten ein Sprachprofil für eingegebene Sprachprobedaten erzeugt. Außerdem enthält dieses System einen Sprachgenerator, der auf Grundlage des Sprachprofils eine beliebige Text-Nachricht in synthetische Sprachprobedaten umsetzt.According to the invention, a system for implementing Text messages in voice messages claimed. This has a speech analyzer based on a Analysis of voice sample data a voice profile for entered Voice sample data generated. This system also includes a speech generator based on the speech profile any text message in synthetic Implements voice sample data.

Weitere Vorteile, Merkmale und Eigenschaften der vorliegenden Erfindung werden im folgenden anhand eines Ausführungsbeispiels unter Bezugnahme auf die begleitende Zeichnung näher erläutert.Other advantages, features and characteristics of the present Invention are based on a Embodiment with reference to the accompanying Drawing explained in more detail.

Die Figur zeigt schematisch eine Technik zur automatischen Umsetzung von Text-Nachrichten in Sprach-Nachrichten.The figure shows schematically a technique for automatic Conversion of text messages into voice messages.

In der Figur ist schematisch ein Verfahren bzw. ein System zur automatischen Umsetzung von Text-Nachrichten in Sprach-Nachrichten dargestellt. Ein von einer beliebigen Person gesprochener Text 1 wird in einem Schritt S1 von einem Analysator 2 analysiert. Dies geschieht in der Regel dadurch, dass die akustischen Signale analog registriert werden und durch einen A/D-Wandler in digitale Sprachdateien umgesetzt werden. Mit einer entsprechenden Software kann in einem Schritt S3 auf Grundlage der erfolgten Analyse der digitalen Sprachdateien ein Sprachprofil 3 dieser Person erzeugt werden. Dabei kann der gesprochene Text 1 ein beliebiger Freitext oder ein Referenztext 8 sein, der in einem Schritt S2 im Rahmen der Analyse mit der schriftlichen Form des Referenztextes 8 verglichen wird.A method or a system is shown schematically in the figure for the automatic conversion of text messages into voice messages shown. One from any person spoken text 1 is replaced by a step S1 Analyzer 2 analyzed. This usually happens because that the acoustic signals are registered analogously and converted into digital voice files by an A / D converter become. With the appropriate software, one can Step S3 based on the analysis of the digital Language files creates a voice profile 3 of this person become. The spoken text 1 can be any Free text or a reference text 8, the one step S2 as part of the analysis with the written form of the Reference text 8 is compared.

Auf Grundlage des Sprachprofils 3 lässt sich im folgenden jede beliebige Text-Nachricht 5 über einen Sprachgenerator 4 in synthetische Sprachnachrichtendaten 6 übersetzen (Schritt S5 und Schritt S6). Die Textnachricht 5 kann anschließend in einem Schritt S7 gemäß dem erstellten Sprachprofil 3 akustisch ausgegeben werden. Based on the language profile 3 can be in the following any text message 5 via a speech generator 4 translate into synthetic voice message data 6 (step S5 and step S6). The text message 5 can then in a step S7 according to the created language profile 3 be output acoustically.

So kann anhand einer Sprachprobe 1 eines Sprechers über das dadurch gewonnene Sprachprofil 3 ein Sprachgenerator 4 für eine synthetisch erzeugte Sprache so eingestellt werden, dass beliebige Texte 5 mit der Stimme dieses Sprechers akustisch ausgegeben werden können. Durch die dadurch mögliche Sprachausgabe mit einer natürlichen und vor allem vertrauten Stimme wird ein Befremden beim Hören der ausgegebenen Sprache vermieden. Natürlich ist es auch denkbar, dass dem Sprachgenerator Sprachproben verschiedener Personen und damit mehrere Sprachprofile zur Verfügung stehen. Damit ist eine Auswahl verschiedener Sprecher möglich.So, based on a speech sample 1 of a speaker about the thus obtained speech profile 3 a speech generator 4 for a synthetically generated language can be set so that any texts 5 with the voice of this speaker acoustically can be spent. Because of the possible Narrator with a natural and above all familiar Voice becomes strange when you hear the speech avoided. Of course, it is also conceivable that Speech generator speech samples of different people and thus multiple language profiles are available. So that's one Different speakers can be selected.

Dies ist insbesondere innerhalb von Multimediaumgebungen von großem Wert, wenn nämlich die Verknüpfung von synthetisch erzeugter Sprache zu Dokumenten des Sprechers automatisch erstellt werden kann. Der Hörer kann den Absender der Nachricht dann anhand der Stimme erkennen, was einer angenehmen Kommunikation mit modernen technischen Mitteln entspricht. Dabei ist es zudem äußerst vorteilhaft, dass die Profilgenerierung für die Ausgabe der Sprache automatisch aus einer beliebigen Sprachprobe innerhalb des Multimediaumfeldes erfolgen kann.This is particularly true within multimedia environments from great value, namely when linking synthetic generated speech to the speaker's documents automatically can be created. The listener can choose the sender of the Then recognize the message by voice, what one pleasant communication with modern technical means equivalent. It is also extremely advantageous that the Profile generation for the output of the language automatically any speech sample within the multimedia environment can be done.

Normalerweise werden innerhalb eines einheitlichen Nachrichten-Systems (Unified Message System) verschiedene Dokumente, wie z.B. Sprachnachrichten (Anrufbeantworter), E-Mails, Faxnachrichten usw., des gleichen Autors verwaltet. Um beispielsweise E-Mails innerhalb dieses Systems z.B. auf einem Mobiltelephon auszugeben, wird der E-Mail-Text erfindungsgemäß in Sprache übersetzt. Vorteilhafterweise kann dabei mit Hilfe einer in demselben System eingegangenen Sprach-Nachricht 1 des gleichen Autors und des daraus generierten Stimmenprofils 3 die E-Mail-Nachricht mit der Stimme dieses Autors ausgegeben werden. Bei entsprechender Vorlage einer Sprachprobe anderer Personen, wie z.B. prominenter Personen, wäre auch eine Wiedergabe der Dokumente mit deren Stimme möglich. Usually within a uniform Message system (Unified Message System) various Documents such as Voice messages (answering machine), emails, Fax messages etc., managed by the same author. Around e.g. emails within this system e.g. on to output a cell phone becomes the email text translated into language according to the invention. Can advantageously thereby with the help of a received in the same system Voice message 1 from the same author and from it generated voice profile 3 the email message with the Voice of this author. With appropriate Submission of a voice sample from other people, e.g. prominent people would also be a reproduction of the documents possible with their voice.

Im zuvor beschriebenen Beispiel sendet also ein Autor einem Empfänger eine E-Mail-Nachricht. Als Zieladresse gibt der Autor die Telefonnummer des Empfängers an. Das verwendete Unified Message System stellt fest, dass als Empfänger kein E-Mail-Anschluß, sondern ein Fernsprechanschluß ausgewählt wurde und setzt daher den eingegebenen Text in eine Sprachnachricht um. Dazu wird ein Sprachprofil verwendet, welches zuvor anhand einer Sprechprobe dieses Autors erstellt worden ist. Damit wird die Stimme der synthetisch erzeugten Sprachausgabe der natürlichen Stimme des Autors soweit angenähert, dass der Empfänger die synthetische Stimme als die vertraute Stimme der sendenden Person erkennt. Das Unified Message System veranlasst nun den Aufbau einer Verbindung zum Fernsprechanschluß des Empfängers und gibt die Sprachnachricht mit der Stimme des Autors aus.In the example described above, an author sends one Recipient an email message. The destination address is the Author the recipient's phone number. The used Unified Message System determines that as a recipient no E-mail connection, but a telephone connection selected was and therefore puts the entered text in a Voice message around. A language profile is used for this, which was previously created based on a speech sample by this author has been. With this, the voice of the synthetically produced So far the natural voice of the author approximated that the recipient uses the synthetic voice as a recognizes the familiar voice of the sending person. The Unified Message System now initiates the construction of a Connection to the telephone line of the receiver and gives the Voice message with the author's voice.

Claims (6)

Verfahren zur automatischen Umsetzung von Text-Nachrichten (5) in Sprach-Nachrichten (6), mit den folgenden Schritten: Erstellen (S3) eines Sprachprofils (3) und Umsetzen (4) von eingegebenen Text-Nachrichtendaten (5) in synthetische Sprach-Nachrichtendaten (6) auf Grundlage des Sprachprofils (3), dadurch gekennzeichnet, dass das Sprachprofil (3) nach Analyse (S1 von Sprachprobedaten (1) eines Benutzers auf Grundlage der vorgenommenen Analyse (S1) erstellt wird, um den Text angenähert mit der Stimme des Benutzers auszugeben.Method for automatically converting text messages (5) into voice messages (6), with the following steps: Creation (S3) of a language profile (3) and Converting (4) input text message data (5) into synthetic voice message data (6) based on the voice profile (3), characterized in that the speech profile (3) is created after analysis (S1 of speech sample data (1) of a user on the basis of the analysis (S1) carried out, in order to output the text approximately with the user's voice. Verfahren nach Anspruch 1,
dadurch gekennzeichnet, dass das Erstellen des Sprachprofils (3) auf Grundlage eines Vergleichs (S2) von Referenz-Textdaten (8) mit Referenz-Sprachprobedaten (1) erfolgt, wobei die Referenz-Sprachprobedaten (1) durch akustische Wiedergabe der Referenz-Textdaten (8) durch einen Sprecher erzeugt werden.Method according to claim 1,
characterized in that the speech profile (3) is created on the basis of a comparison (S2) of reference text data (8) with reference speech sample data (1), the reference speech sample data (1) by acoustic reproduction of the reference text data ( 8) generated by a speaker. System zur Umsetzung von Text-Nachrichten (5) in Sprach-Nachrichten (6), mit einem Sprachanalysator (2), der auf Grundlage einer Analyse (S1) von Sprachprobedaten (1) ein Sprachprofil (3) für eingegebene Sprachprobedaten (1) erzeugt, und mit einem Sprachgenerator (4), der auf Grundlage des Sprachprofils (3) eine beliebige Text-Nachricht (5) in synthetische Sprachprobedaten (6) umsetzt. System for converting text messages (5) into voice messages (6), with a speech analyzer (2), which generates a speech profile (3) for entered speech sample data (1) on the basis of an analysis (S1) of speech sample data (1), and with a speech generator (4), which converts any text message (5) into synthetic speech sample data (6) based on the speech profile (3). System nach Anspruch 3,
dadurch gekennzeichnet, dass der Sprachgenerator (4) dazu ausgelegt ist, das Sprachprofil (3) auf Grundlage eines Vergleichs eines schriftlichen Referenz-Textes (8) mit der von einem Benutzer gesprochenen Form (1) dieses Referenz-Textes (8) zu erzeugen.System according to claim 3,
characterized in that the speech generator (4) is designed to generate the speech profile (3) on the basis of a comparison of a written reference text (8) with the form (1) of this reference text (8) spoken by a user. System nach Anspruch 3 oder 4,
dadurch gekennzeichnet, dass in Multimediaumgebungen der Sprachanteil von Sprachnachrichten (1) automatisch analysiert wird (S1) und zur akustischen Wiedergabe (7) von Textnachrichten (5) verwendet wird.System according to claim 3 or 4,
characterized in that in multimedia environments the speech portion of voice messages (1) is automatically analyzed (S1) and used for acoustic reproduction (7) of text messages (5). Mobiltelephon, aufweisend ein System nach Anspruch 3, 4 oder 5,
dadurch gekennzeichnet, dass die Text-Nachrichten (5) Dokumente in einer Multimediaumgebung, beispielsweise E-Mail-Texte, sind, die auf dem Mobiltelephon in der Sprache gemäß dem zuvor erzeugten Sprachprofil (3) akustisch ausgegeben werden.Mobile phone, comprising a system according to claim 3, 4 or 5,
characterized in that the text messages (5) are documents in a multimedia environment, for example e-mail texts, which are acoustically output on the mobile phone in the language according to the previously generated language profile (3).
EP02003909A 2001-04-06 2002-02-21 Method and device for automatically converting text messages to speech messages Withdrawn EP1248251A3 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE10117367A DE10117367B4 (en) 2001-04-06 2001-04-06 Method and system for automatically converting text messages into voice messages
DE10117367 2001-04-06

Publications (2)

Publication Number Publication Date
EP1248251A2 true EP1248251A2 (en) 2002-10-09
EP1248251A3 EP1248251A3 (en) 2009-10-07

Family

ID=7680748

Family Applications (1)

Application Number Title Priority Date Filing Date
EP02003909A Withdrawn EP1248251A3 (en) 2001-04-06 2002-02-21 Method and device for automatically converting text messages to speech messages

Country Status (3)

Country Link
US (1) US20020169610A1 (en)
EP (1) EP1248251A3 (en)
DE (1) DE10117367B4 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2383502B (en) * 2001-11-02 2005-11-02 Nec Corp Voice synthesis system and method,and portable terminal and server therefor
WO2011083362A1 (en) * 2010-01-05 2011-07-14 Sony Ericsson Mobile Communications Ab Personalized text-to-speech synthesis and personalized speech feature extraction

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2004090746A1 (en) * 2003-04-14 2004-10-21 Koninklijke Philips Electronics N.V. System and method for performing automatic dubbing on an audio-visual stream
US8005677B2 (en) * 2003-05-09 2011-08-23 Cisco Technology, Inc. Source-dependent text-to-speech system
US8068588B2 (en) * 2007-06-26 2011-11-29 Microsoft Corporation Unified rules for voice and messaging
US8285548B2 (en) 2008-03-10 2012-10-09 Lg Electronics Inc. Communication device processing text message to transform it into speech
KR101566379B1 (en) * 2009-05-07 2015-11-13 삼성전자주식회사 Method For Activating User Function based on a kind of input signal And Portable Device using the same
US9906927B2 (en) 2011-09-28 2018-02-27 Elwha Llc Multi-modality communication initiation
US9503550B2 (en) 2011-09-28 2016-11-22 Elwha Llc Multi-modality communication modification
US9794209B2 (en) 2011-09-28 2017-10-17 Elwha Llc User interface for multi-modality communication
US9699632B2 (en) 2011-09-28 2017-07-04 Elwha Llc Multi-modality communication with interceptive conversion
US9788349B2 (en) * 2011-09-28 2017-10-10 Elwha Llc Multi-modality communication auto-activation
US20130079029A1 (en) * 2011-09-28 2013-03-28 Royce A. Levien Multi-modality communication network auto-activation
US9002937B2 (en) 2011-09-28 2015-04-07 Elwha Llc Multi-party multi-modality communication
US9477943B2 (en) 2011-09-28 2016-10-25 Elwha Llc Multi-modality communication
US10424288B2 (en) 2017-03-31 2019-09-24 Wipro Limited System and method for rendering textual messages using customized natural voice
CN111369966A (en) * 2018-12-06 2020-07-03 阿里巴巴集团控股有限公司 Method and device for personalized speech synthesis

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE3416238A1 (en) * 1983-05-02 1984-12-20 Motorola, Inc., Schaumburg, Ill. EXTREME NARROW BAND TRANSMISSION SYSTEM
JPH05260082A (en) * 1992-03-13 1993-10-08 Toshiba Corp Text reader
US5774841A (en) * 1995-09-20 1998-06-30 The United States Of America As Represented By The Adminstrator Of The National Aeronautics And Space Administration Real-time reconfigurable adaptive speech recognition command and control apparatus and method
EP0901000A2 (en) * 1997-07-31 1999-03-10 Toyota Jidosha Kabushiki Kaisha Message processing system and method for processing messages

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6035273A (en) * 1996-06-26 2000-03-07 Lucent Technologies, Inc. Speaker-specific speech-to-text/text-to-speech communication system with hypertext-indicated speech parameter changes
US6216104B1 (en) * 1998-02-20 2001-04-10 Philips Electronics North America Corporation Computer-based patient record and message delivery system
US6081780A (en) * 1998-04-28 2000-06-27 International Business Machines Corporation TTS and prosody based authoring system
DE19841683A1 (en) * 1998-09-11 2000-05-11 Hans Kull Device and method for digital speech processing
US6243676B1 (en) * 1998-12-23 2001-06-05 Openwave Systems Inc. Searching and retrieving multimedia information
US20020072900A1 (en) * 1999-11-23 2002-06-13 Keough Steven J. System and method of templating specific human voices
US6801931B1 (en) * 2000-07-20 2004-10-05 Ericsson Inc. System and method for personalizing electronic mail messages by rendering the messages in the voice of a predetermined speaker
US6978239B2 (en) * 2000-12-04 2005-12-20 Microsoft Corporation Method and apparatus for speech synthesis without prosody modification

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE3416238A1 (en) * 1983-05-02 1984-12-20 Motorola, Inc., Schaumburg, Ill. EXTREME NARROW BAND TRANSMISSION SYSTEM
JPH05260082A (en) * 1992-03-13 1993-10-08 Toshiba Corp Text reader
US5774841A (en) * 1995-09-20 1998-06-30 The United States Of America As Represented By The Adminstrator Of The National Aeronautics And Space Administration Real-time reconfigurable adaptive speech recognition command and control apparatus and method
EP0901000A2 (en) * 1997-07-31 1999-03-10 Toyota Jidosha Kabushiki Kaisha Message processing system and method for processing messages

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2383502B (en) * 2001-11-02 2005-11-02 Nec Corp Voice synthesis system and method,and portable terminal and server therefor
US7313522B2 (en) 2001-11-02 2007-12-25 Nec Corporation Voice synthesis system and method that performs voice synthesis of text data provided by a portable terminal
WO2011083362A1 (en) * 2010-01-05 2011-07-14 Sony Ericsson Mobile Communications Ab Personalized text-to-speech synthesis and personalized speech feature extraction
CN102117614B (en) * 2010-01-05 2013-01-02 索尼爱立信移动通讯有限公司 Personalized text-to-speech synthesis and personalized speech feature extraction
US8655659B2 (en) 2010-01-05 2014-02-18 Sony Corporation Personalized text-to-speech synthesis and personalized speech feature extraction

Also Published As

Publication number Publication date
DE10117367A1 (en) 2002-10-17
US20020169610A1 (en) 2002-11-14
EP1248251A3 (en) 2009-10-07
DE10117367B4 (en) 2005-08-18

Similar Documents

Publication Publication Date Title
EP1248251A2 (en) Method and device for automatically converting text messages to speech messages
DE60222093T2 (en) METHOD, MODULE, DEVICE AND VOICE RECOGNITION SERVER
DE102019200954A1 (en) Signal processing device, system and method for processing audio signals
EP0644680A2 (en) Method and device for establishing and processing text documents
DE102004050785A1 (en) Method and arrangement for processing messages in the context of an integrated messaging system
EP1051701B1 (en) Method for voice data transmission
DE102019200956A1 (en) Signal processing device, system and method for processing audio signals
DE112006000322T5 (en) Audio recognition system for generating response audio using extracted audio data
DE60008893T2 (en) Voice-controlled portable terminal
WO2001069591A1 (en) Method for recognition of verbal utterances by a non-mother tongue speaker in a speech processing system
EP2047668B1 (en) Method, spoken dialog system, and telecommunications terminal device for multilingual speech output
DE60020504T2 (en) ADJUSTING A LANGUAGE IDENTIFIER TO CORRECTED TEXTS
DE19920501A1 (en) Speech reproduction method for voice-controlled system with text-based speech synthesis has entered speech input compared with synthetic speech version of stored character chain for updating latter
EP1282897A1 (en) Method for creating a speech database for a target vocabulary in order to train a speech recognition system
WO2020221865A1 (en) Method, computer program product, system and device for modifying acoustic interaction signals, which are produced by at least one interaction partner, in respect of an interaction target
DE19918382B4 (en) Creation of a reference model directory for a voice-controlled communication device
DE60022976T2 (en) LANGUAGE RECOGNITION WITH TRANSFER
EP0984427B1 (en) Method for acoustically outputting text
DE10033104C2 (en) Methods for generating statistics of phone durations and methods for determining the duration of individual phones for speech synthesis
DE10163277C2 (en) Method for sending a message to a phone number, and device therefor
WO2004047466A2 (en) Method for the reproduction of sent text messages
DE60025158T2 (en) Method for speed modification of speech signals, use of the method, and arrangement for carrying out the method
WO2023061701A1 (en) Assistance system, and method for interacting with at least one user
DE10056762B4 (en) Method for creating electronic messages
DE102016002496A1 (en) Method and system for playing a text message

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 TR

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 TR

AX Request for extension of the european patent

Extension state: AL LT LV MK RO SI

17P Request for examination filed

Effective date: 20100329

AKX Designation fees paid

Designated state(s): DE FR GB IT SE

17Q First examination report despatched

Effective date: 20101201

RAP1 Party data changed (applicant data changed or rights of an application transferred)

Owner name: SIEMENS ENTERPRISE COMMUNICATIONS GMBH & CO. KG

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

Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN

18D Application deemed to be withdrawn

Effective date: 20110615