GB2399728A - Voice synthesis of received information with a profile determined by the sender - Google Patents
Voice synthesis of received information with a profile determined by the sender Download PDFInfo
- Publication number
- GB2399728A GB2399728A GB0403016A GB0403016A GB2399728A GB 2399728 A GB2399728 A GB 2399728A GB 0403016 A GB0403016 A GB 0403016A GB 0403016 A GB0403016 A GB 0403016A GB 2399728 A GB2399728 A GB 2399728A
- Authority
- GB
- United Kingdom
- Prior art keywords
- information
- speech
- signals
- voice
- voice profiles
- 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- Withdrawn
Links
- 230000015572 biosynthetic process Effects 0.000 title claims abstract description 7
- 238000003786 synthesis reaction Methods 0.000 title claims abstract description 7
- 238000006243 chemical reaction Methods 0.000 claims abstract description 10
- 239000012634 fragment Substances 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims description 13
- 230000005540 biological transmission Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 2
- 208000032544 Cicatrix Diseases 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 231100000241 scar Toxicity 0.000 description 1
- 230000037387 scars Effects 0.000 description 1
- 238000001308 synthesis method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Circuits Of Receivers In General (AREA)
Abstract
In an information device (1) for vehicles with a receiving unit (2) for the receipt and decoding of coded digital information signals and with a speech reproduction device (3) for speech conversion of decoded information signals into synthetic speech signals and for the acoustic reproduction of the synthetic speech signals, speech conversion being achieved with the aid of voice profiles stored in the information device (1), the speech reproduction device (3) is formed for the selection of at least one stored voice profile depending on control information in the decoded digital information signals to reproduced. Voice profiles may additionally be transmitted with the information signals. The profiles may be sound fragments or parameters for speech synthesis algorithms.
Description
Information device, in particular for vehicles, and method for controlling
speech reproduction The invention relates to an information device, in particular for vehicles, with a receiving unit for the receipt and decoding of coded digital information signals and with a speech reproduction device for the speech conversion of decoded information signals into synthetic speech signals and for the acoustic reproduction of the synthetic speech signals, the speech conversion being achieved with the aid of voice profiles stored in the information device.
The invention also relates to a method for controlling the speech reproduction of digital information signals, which are transmitted in coded form to such an information device, decoded information signals being converted into synthetic speech signals and reproduced acoustically and the speech conversion being achieved with the aid of voice profiles stored in the information device.
The synthetic reproduction of digital text information is adequately known and described for example in DE 199 39 947 Al. In this document a digital speech synthesis method is disclosed, in which a text to be issued as speech is transferred into phoneme chains and converted into symbol chains. Voice profiles in the form of generalized microsegments, which have first been produced from recorded expressions of speech, are then assigned to the symbol chains.
Texts downloaded onto a computer via the Internet, for example, can be read aloud using this method. The voice profiles, i.e. the generalized microsegments, can be loaded optionally via the Internet. Various pronunciations can be realized hereby, for example depending on national language, dialect or gender.
In DE 199 05 602 Al, an information system for a vehicle is described, with an information receiver that has an evaluation unit fixed in the vehicle for the decoding and speech conversion of the coded information signals, which are then output synthetically by a reproduction device for the speech information. The digital information signals are converted into synthetic speech information using a speech reproduction program, which is filed in a storage device of the evaluation unit.
The digital information signals that are to be reproduced synthetically can be transmitted for example according to the Digital Audio Broadcast protocol (DAB) in a digital radio channel or the like.
Speech reproduction in an information device for vehicles is also used to read out electronic messages or short messages (SMS) transmitted to a mobile radio telephone.
The voice profile is fixedly predetermined in this case.
The object of the invention is to create an improved information device, in particular for vehicles, and a method for controlling the speech reproduction, with which simple adaptation of the voice profiles and individualization of the information signals to be reproduced are possible.
The object is achieved with the generic information device in that the speech reproduction device is formed for the selection of at least one stored voice profile depending on control information in the decoded digital information signals to be reproduced.
The voice profile can thus be predetermined individually by the information supplier by reverting to voice profiles sent with the information signals or already stored.
The receiving unit is preferably formed to decode voice profiles that are sent in the form of coded information signals in the data stream of digital information signals to the information device, and to store the voice profiles.
In addition to the transmission of voice profiles in the coded data stream, voice profiles can also be loaded locally into the voice profile storage device with the aid of a data medium, for example, such as a compact disc CD.
Voice profiles in the form of sound fragments are preferably digitally compressed in this case, e.g. according to the MP-3 standard.
The voice profiles are thus sent as coded information signals in combination with the information to be reproduced acoustically, so that the voice profile is no longer determined by the playing apparatus, but can be predetermined by the information supplier.
The voice profiles are for example sound fragments or parameters for speech synthesis algorithms, which describe for example the pitch, the gender, the accent, etc. Transmission of the voice profiles as parameters has the advantage that the amount of data is reduced considerably compared with sound fragments.
The receiving unit is a digital radio receiver, for example, for receiving digital audio data according to the Digital Audio Broadcast (DAB) standard. Other methods, such as Digital Radio Mondiale (DRM), InBand-On-Channel (IBOC), Satellite Digital Audio Radio Service (SCARS) or Digital Video Broadcast (DVB) are conceivable.
Bidirectional systems, such as the mobile radio systems Global System for Mobile Communications (GSM) and Universal Mobile Telecommunications System (UMTS), are also possible.
The object is achieved furthermore by the generic method by Decoding of voice profiles, which are sent in the form of coded information signals in the data stream of digital information signals to the information device, and storage of the voice profiles preferably take place.
The invention is explained in greater detail below with reference to the enclosed drawing.
Fig. 1 shows a block diagram of an information device according to the invention for vehicles.
Figure 1 shows an information device 1 for vehicles, which can be a digital car radio, a navigation device or multifunctional terminal, for example. The information device 1 has a receiving unit 2, with which coded digital information signals can be received, which are emitted for example by a radio transmitter. The digital information signals can be coded for example according to the Digital Audio Broadcast standard (DAB) and contain additional information as well as the radio transmissions to be played. To be able to reproduce this additional digital information acoustically, a speech reproduction device 3 is provided in the information device 1, in which reproduction device speech synthesis algorithms are implemented. The decoded digital information signals to be output acoustically are speech-converted with the aid of these speech synthesis algorithms into synthetic speech signals and output via the loudspeakers 4 available in the vehicle following conventional amplification.
The synthetically output speech information can be electronic messages (emails) or short messages (SMS) transmitted via mobile radio network, for example.
The speech conversion takes place in a known manner with the aid of voice profiles stored in a voice profile storage device 5. These voice profiles can be sound fragments or parameters, for example, which describe the pitch, gender, accent, etc. According to the invention, the receiving unit 2 is also formed for decoding voice profiles that are transmitted as coded digital information signals in the radio signal.
Following decoding, the voice profiles are extracted from the data stream and filed in the voice profile storage device 5.
The selection of the voice profiles to be used in each case for the synthetic speech reproduction of information is made with the aid of control information, which is contained in the decoded digital information signals to be reproduced. In this way the information supplier can specify a characteristic voice profile in each case for his specific information, for example. This results in the ability to individualize information provided by broadcasting institutions as well as in an increase in the recognition value.
In addition to the transmission of the voice profiles in the coded data stream, voice profiles can also be loaded locally into the voice profile storage device 5 with the aid of a data medium, for example, such as a compact disc CD. Voice profiles in the form of sound fragments are preferably digitally compressed in this case, e.g. according to the MP-3 standard.
Claims (14)
- Claims 1. Information device (1), in particular for vehicles, with areceiving unit (2) for the receipt and decoding of coded digital information signals and with a speech reproduction device (3) for speech conversion of decoded information signals into synthetic speech signals and for the acoustic reproduction of the synthetic speech signals, the speech conversion being achieved with the aid of voice profiles stored in the information device (1), characterized in that the speech reproduction device (3) is formed for the selection of at least one stored voice profile depending on control information in the decoded digital information signals to be reproduced.
- 2. Information device (1) according to claim 1, characterized in that the receiving unit (2) is formed for decoding voice profiles, which are sent in the form of coded information signals in the data stream of digital information signals to the information device (1), and for storing the voice profiles.
- 3. Information device (1) according to claim 1 or 2, characterized in that the receiving unit (2) is formed for loading voice profiles from a data medium into the voice profile storage device (5).
- 4. Information device (1) according to one of the preceding claims, characterized in that the voice profiles are sound fragments.
- 5. Information device (1) according to one of the preceding claims, characterized in that the voice profiles are parameters for speech synthesis algorithms.
- 6. Information device (1) according to one of the preceding claims, characterized in that the receiving unit is a Digital Audio Broadcast (DAB) receiver or Digital Radio Mondiale (DRM) receiver.
- 7. Method for controlling the speech reproduction of digital information signals, which are transmitted in coded form to an information device (1) according to one of the preceding claims, decoded information signals being converted into synthetic speech signals and reproduced acoustically and the speech conversion being achieved with the aid of voice profiles stored in the information device (1), characterized by selection of at least one stored voice profile depending on control information in the decoded digital information signals to be reproduced.
- 8. Method according to claim 7, characterized by decoding of voice profiles, which are sent in the form of coded information signals in the data stream of digital information signals to the information device (1), and storage of the decoded voice profiles.
- 9. Method according to claim 7, characterized by loading of voice profiles from a data medium into the voice profile storage device 5.
- 10. Method according to one of claims 6 to 9, characterized in that the voice profiles are sound fragments.
- 11. Method according to one of claims 6 to 9, characterized in that the voice profiles are parameters for speech synthesis algorithms.
- 12. Method according to one of claims 6 to 1 1, characterized in that the digital information signals are coded according to the Digital Audio Broadcast standard (DAB) or Digital Radio Mondiale standard (DRM).
- 13. Information device substantially as hereinbefore described with reference to the accompanying drawing.
- 14. Method substantially as hereinbefore described with reference to the accompanying drawing.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE2003105658 DE10305658A1 (en) | 2003-02-12 | 2003-02-12 | Information device for motor vehicles has a receiver unit for receiving and decoding encoded digital data signals and a voice playback device for speech conversion of decoded data signals |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| GB0403016D0 GB0403016D0 (en) | 2004-03-17 |
| GB2399728A true GB2399728A (en) | 2004-09-22 |
Family
ID=32010527
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| GB0403016A Withdrawn GB2399728A (en) | 2003-02-12 | 2004-02-11 | Voice synthesis of received information with a profile determined by the sender |
Country Status (2)
| Country | Link |
|---|---|
| DE (1) | DE10305658A1 (en) |
| GB (1) | GB2399728A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH05260082A (en) * | 1992-03-13 | 1993-10-08 | Toshiba Corp | Text reader |
| JPH06335822A (en) * | 1993-05-25 | 1994-12-06 | Sansei Kogyo Kk | Automatic thread cutting device |
| EP0901000A2 (en) * | 1997-07-31 | 1999-03-10 | Toyota Jidosha Kabushiki Kaisha | Message processing system and method for processing messages |
| EP1168297A1 (en) * | 2000-06-30 | 2002-01-02 | Nokia Mobile Phones Ltd. | Speech synthesis |
-
2003
- 2003-02-12 DE DE2003105658 patent/DE10305658A1/en not_active Withdrawn
-
2004
- 2004-02-11 GB GB0403016A patent/GB2399728A/en not_active Withdrawn
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH05260082A (en) * | 1992-03-13 | 1993-10-08 | Toshiba Corp | Text reader |
| JPH06335822A (en) * | 1993-05-25 | 1994-12-06 | Sansei Kogyo Kk | Automatic thread cutting device |
| EP0901000A2 (en) * | 1997-07-31 | 1999-03-10 | Toyota Jidosha Kabushiki Kaisha | Message processing system and method for processing messages |
| EP1168297A1 (en) * | 2000-06-30 | 2002-01-02 | Nokia Mobile Phones Ltd. | Speech synthesis |
Also Published As
| Publication number | Publication date |
|---|---|
| DE10305658A1 (en) | 2004-08-26 |
| GB0403016D0 (en) | 2004-03-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP3890108B2 (en) | Voice message transmitting apparatus, voice message receiving apparatus, and portable wireless voice message communication apparatus | |
| US6081780A (en) | TTS and prosody based authoring system | |
| CN101095287B (en) | Voice service over short message service | |
| US6246672B1 (en) | Singlecast interactive radio system | |
| US6163508A (en) | Recording method having temporary buffering | |
| US10542360B2 (en) | Reproduction system, terminal device, method thereof, and non-transitory storage medium, for providing information | |
| JP2009086662A (en) | Text pre-processing for text-to-speech generation | |
| KR100291155B1 (en) | Speech transmission/reception system in which error data is replaced by speech synthesized data | |
| US20200057601A1 (en) | Audio stream mixing system and method | |
| US20180197532A1 (en) | Audio content censoring in vehicle infotainment system | |
| GB2399728A (en) | Voice synthesis of received information with a profile determined by the sender | |
| US6502071B1 (en) | Comfort noise generation in a radio receiver, using stored, previously-decoded noise after deactivating decoder during no-speech periods | |
| US20080019541A1 (en) | Data recording apparatus, data recording method, and data recording program | |
| JP4845249B2 (en) | Method for wirelessly transmitting information between a communication system in a vehicle and a central computer outside the vehicle | |
| JP3684771B2 (en) | Music data income system for vehicles, wireless base station | |
| JP2974813B2 (en) | Traffic information broadcasting system | |
| KR101206113B1 (en) | Apparatus and method for alarming live bell in mobile terminal | |
| KR100695368B1 (en) | Sound processing device of mobile terminal to output high quality sound | |
| JP2005227544A (en) | Voice signal recording method and voice signal recording device | |
| JP2916307B2 (en) | Audio transmission device | |
| CA1309467C (en) | Paging receiver utilizing digital voice coding with improved voice reconstruction characteristics | |
| KR20020095778A (en) | Download and sound choise/generated equipment of warning horn for cars | |
| JPH1152974A (en) | Transmitter, receiver, and communication device | |
| JP2023148246A (en) | Broadcast radio system and master station facility for the same | |
| JPH088855A (en) | Guidance broadcasting equipment for transport |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| WAP | Application withdrawn, taken to be withdrawn or refused ** after publication under section 16(1) |