Text to speech conversion in hearing systems

• US 7,412,288 B2
• Filed: 05/10/2004
• Issued: 08/12/2008
• Est. Priority Date: 05/10/2004
• Status: Active Grant

• Current Assignee: Sonova AG (Sonova Holding AG)
• Original Assignee: Phonak AG (Sonova Holding AG)
• Inventors: Berg, Christian
• Primary Examiner(s): EVANISKO, GEORGE ROBERT
• Application Number:
  US10/841,829
• Publication Number:
  US 20050251224A1
• Time in Patent Office: 1,555 Days
• Field of Search: 607 55- 57, 607136-137, 600/379, 381/312, 381/328
• US Class Current: 607/57
• CPC Class Codes: A61N 1/36038 Cochlear stimulation
• CPC Class Codes: H04R 25/505 using digital signal processing

Abstract

A hearing system for a person, comprising: an input device for providing electrical signals produced from sound, a signal processor for processing said electrical signals for producing audio signals, a digital text storage for storing digital text received from a source of digital text, a converter for converting digital text from said digital text storage into audio signals, and an output transducer for converting audio signals into a stimulation of a person'"'"'s hearing. The hearing system is designed to be worn at least partly within the person'"'"'s ear canal or behind the person'"'"'s ear or is designed to be at least partially implanted within the person'"'"'s skull.

Claims

1. A hearing system for a person, comprising:

input means for providing electrical signals produced from sound,

signal processing means for processing said electrical signals for producing audio signals,

means for storing digital text representative of text information to be provided to said person and received from a source of the digital text,

means for converting the digital text from said text storing means into speech audio signals, and

output transducer means for converting the audio signals produced by the signal processing means and the speech audio signals produced by the means for converting digital text into a stimulation of said person'"'"'s hearing,

wherein said hearing system is sized to fit at least partly within the person'"'"'s ear canal or behind the person'"'"'s ear or be at least partially implanted within the person'"'"'s skull; and

wherein the text converting means comprise a programmable digital signal processor and a program memory with a speech synthesis software for converting the digital text into speech audio signals.

2. The hearing system of claim 1, wherein said source of the digital text is external to said hearing system and wherein said hearing system comprises an interface for communication with said external source of digital text.

3. The hearing system of claim 2, wherein said interface is adapted for wireless communication.

4. The hearing system of claim 3, wherein said interface is adapted for wireless communication based on the Bluetooth standard.

5. The hearing system of claim 4, further comprising means for controlling operation of said hearing system according to pre-defined speech commands recognized by said means for converting speech to said digital text. electrical signals.

6. The hearing system of claim 2, wherein said means for converting the digital text from said storing means are also adapted to convert the digital text from said interface into audio signals.

7. The hearing system of claim 1, wherein said input means is an input transducer for converting ambient sounds into said electrical signals.

8. The hearing system of claim 1, wherein said input means is an input receiver means for receiving electrical signals from an external signal source.

9. The hearing system of claim 8, wherein said input receiver means is adapted to be connected to said external signal source via a wireless link.

10. The hearing system of claim 9, wherein a microphone is provided for converting ambient sounds into said electrical signals as said external signal source.

11. The hearing system of claim 1, wherein said hearing system is adapted for communication with external fining means designed for performing at least one function selected from the group consisting of:

determining a language of said audio signals converted from said digital text,

determining a speaker of said audio signals converted from said digital text,

adjusting a loudness of said audio signals produced by said digital text converting means,

activating said digital text converting means, deactivating said digital text converting means, and

controlling a mixing of said audio signals produced by said digital text converting means with said audio signals produced by said signal processing means from said input electrical signals.

12. The hearing system of claim 11, wherein said hearing system is adapted for communication with said external fining means via an interface.

13. The hearing system of claim 11, further comprising at least one of said text source, an external programming unit and an external personal computer or Personal Digital Assistant for serving as the fining means.

14. The hearing system of claim 1, wherein said signal processing means comprise said programmable digital signal processor and said program memory, said program memory comprising a control software, and wherein means for storing person-specific data used by said control software are provided.

15. The hearing system of claim 14, wherein said source of the digital text is external to said hearing system and wherein said hearing system comprises an interface for communication with said external source of digital text, and wherein said interface is designed to input at least one of said speech synthesis software, said control software and said person-specific data into said hearing system from an external programming unit.

16. The hearing system of claim 1, further comprising one of a Personal Digital Assistant, a portable computer, a personal computer, and a mobile telephone as the source of said digital text.

17. The hearing system of claim 1, further comprising activation means for initiating conversion of digital text from said text storing means into audio signals, said activation means being adapted to be controlled by a timer or by operating means adapted to be operated by said person.

18. The hearing system of claim 1, wherein said signal processing means comprises means for speech recognition.

19. The hearing system of claim 18, wherein said speech recognition means are adapted to convert speech into the digital text and wherein an output of said speech recognition means is connected to said means for converting the digital text into audio signals.

20. The hearing system of claim 1, wherein said output transducer means is selected from the group consisting of an electro-acoustic transducer, an electromechanical transducer for stimulation of a middle ear, an electromechanical transducer for stimulation of an inner ear, and a cochlear electrode array for direct electrical stimulation of a cochlear nerve.

21. The hearing system of claim 1, further comprising a means for converting speech to the digital text located within the hearing system as the source of said digital text.

22. The hearing system of claim 1, wherein said signal processing means are adapted to provide for a hearing aid function of said hearing system.

23. The hearing system of claim 1, wherein said signal processing means are adapted to invert said electrical signals provided by said input means in phase for providing for an active hearing protection function of said hearing system.

24. The hearing system of claim 23, further comprising a sound analyzing processor for controlling said active hearing protection function depending on an analyzed auditory scene.

25. The hearing system of claim 1, wherein said signal processing means are adapted to attenuate said electrical signals provided by said input means in phase for providing for an active hearing protection function of said hearing system, said attenuation depending on a noise level detected by said hearing system.

26. The hearing system of claim 1, further comprising means for recognizing specific pre-defined non-speech sounds, means for associating a specific digital text stored in said text storage means to each of said pre-defined non-speech sounds, and means for retrieving a specific digital text associated to said recognized pre-defined non-speech sound from said text storage means and providing said specific digital text to said means for converting digital text into audio signals.

27. The hearing system of claim 26, wherein said pre-defined non-speech sounds comprise alarm signals, with said associated specific digital text comprising alarm messages.

28. The hearing system of claim 26, further comprising means for storing said pre-defined non-speech sounds.

29. The hearing system of claim 26, wherein said signal processing means is adapted to mix said audio signals produced from said associated specific text with audio signals produced from said electrical signals of said input means.

30. The hearing system of claim 1, further comprising means for recognizing specific pre-defined non-speech sound commands and means for controlling operation of said hearing system according to said pre-defined non-speech sound commands detected by said means for recognizing specific pre-defined non-speech sound commands.

31. The hearing system of claim 1, wherein said output transducer means comprises means for stimulation of said person'"'"'s hearing by one of direct electrical stimulation of the cochlear and electromechanical stimulation of the middle or inner ear.

32. A method for operating a hearing system which is worn at least partly within a person'"'"'s ear canal or behind a person'"'"'s ear or is at least partially implanted within a person'"'"'s skull, comprising:

inputting digital text from a source into said hearing system,

storing the digital text representative of text information to be provided to said person and received from said source of the digital text within said hearing system,

converting the stored digital text into speech audio signals,

converting ambient sounds into electrical signals within the hearing system,

processing said electrical signals for producing speech audio signals and converting the audio signals converted from ambient sounds and the audio signals converted from the stored digital text into a stimulation of said person'"'"'s hearing;

wherein the converting of the stored digital text into audio signals is performed by a programmable digital signal processor and a program memory using speech synthesis software for converting digital text into speech audio signals.

33. The method of claim 32, further comprising:

mixing said audio signals produced from said digital text with said audio signals produced from converted ambient sounds.

34. The method of claim 32, wherein said digital text is input from an external source.

36. The method of claim 32, wherein said stimulation of said person'"'"'s hearing is produced by one of direct electrical stimulation of the cochlear and electromechanical stimulation of the middle or inner ear.

35. A method for operating a hearing system which is worn at least partly within a person'"'"'s ear canal or behind a person'"'"'s ear or is at least partially implanted within a person'"'"'s skull, comprising:

inputting digital text from a source into said hearing system,

storing the digital text received from said source of the digital text within said hearing system, converting the stored digital text into audio signals,

converting ambient sounds into electrical signals within the hearing system,

processing said electrical signals for producing audio signals and converting the audio signals converted from ambient sounds and the audio signals converted from the stored digital text into a stimulation of said person'"'"'s hearing further comprising;

converting speech to digital text within said hearing system as said digital text source.