Use of speech recognition in pager and mobile telephone applications

• US 6,459,910 B1
• Filed: 06/07/1995
• Issued: 10/01/2002
• Est. Priority Date: 06/07/1995
• Status: Expired due to Term

• Current Assignee: Intel Corporation
• Original Assignee: Texas Instruments, Inc.
• Inventors: Houston, Theodore W.
• Primary Examiner(s): Nguyen, Lee
• Assistant Examiner(s): Ferguson, Keith
• Application Number:
  US08/481,972
• Time in Patent Office: 2,673 Days
• Field of Search: 379/55, 379/56, 379/57, 379/58, 379/59, 379/67, 379/88, 379/89, 379/68, 395/2.41, 455/563, 455/403, 455/422, 368/63
• US Class Current: 455/563
• CPC Class Codes: G10L 19/0018 Speech coding using phonetic or linguistical decoding of the source; Reconstruction using text-to-speech synthesis
• CPC Class Codes: H04W 88/023 with message or information receiving capability

Abstract

A method of and system for compressing and transmitting information which comprises recognizing a plurality of different types of information and providing a first representation of a recognized one of the plurality of different types of information having lower bandwidth transmission requirement than the recognized one of the plurality of different types of information. The first representation is transmitted to a remote receiver and a second representation of the recognized one of the recognized one of the plurality of different types of information at said remote receiver having greater information content than the first representation responsive to the first representation is provided. Responsive to the second representation, a recreation of the recognized one of the plurality of different types of information is provided. Recognizing includes providing a first data base and the second representation includes providing a second data base. The first data base provides the first representation in binary form and the second data base provides the second representation. The provision of a recreation of the recognized one of the plurality of different types of information responsive to the second representation is one of a visual display or a audible recreation.

Claims

1. A pager system which.comprises:

(a) voice recognition means for recognizing voice produced information and a characteristic of the voice produced information and providing a phoneme-identifying first representation of the voice produced information having reduced bandwidth transmission requirement relative to the recognized voice produced information and a representation of the characteristic of the voice produced information;

(b) transmission means for phonemically transmitting the first representation of the voice produced information and the characteristic of the voice produced information to receiving means;

(c) receiving means responsive to the first representation of the voice produced information for providing a phonemically-identifying second representation of the first representation of the voice produced information of increased bandwidth relative to the first representation; and

means responsive to the second representation and the characteristic of the voice produced information for phonemically recreating the voice produced information and the characteristic of the voice produced information.

2. The system of claim 1 wherein said means for providing a first representation includes a first data base responsive to said voice produced information.

3. The system of claim 2 wherein said means for providing a second representation includes a second data base responsive to said first representation.

4. The system of claim 3 wherein said first data base provides said first representation in binary form and said second data base provides said second representation.

5. The system of claim 4 wherein said means responsive to said second representation is one of a visual display or an audible recreation.

6. The system of claim 5 wherein said first representation is a combination of phoneme information and voice type information.

7. The system of claim 2 wherein said first data base provides said first representation in binary form.

8. The system of claim 3 wherein said means responsive to said second representation is one of a visual display or an audible recreation.

9. The system of claim 1 wherein said means for providing a second representation includes a second data base responsive to said first representation.

10. The system of claim 9 wherein said second data base provides said second representation in binary form.

11. The system of claim 1 wherein said means responsive to said second representation is one of a visual display or an audible recreation.

12. The system of claim 1 wherein said first representation is a combination of phoneme information and voice type information.

13. The system of claim 1 wherein said characteristic of said voice type information is one of a male or female voice.

14. The system of claim 1 wherein said characteristic of said voice type information is one of an accented male or accented female voice.

15. The system of claim 1, further including means at said receiving means for storing one of said first or second representations of said voice produced information and indicator means at said receiving means to indicate said storing of one of said first or second representations.

16. The radio transmitter of claim 15 wherein the voiced message signal has a non-phonemic component indicating a speaker'"'"'s voice type (e.g. male, female, child, foreign accent) and the encoder has a voice type recognition database storing data for recognizing each voice type and assigning it a corresponding voice type identification number.

17. A method of paging which comprises the steps of:

(a) recognizing voice produced information and a characteristic of the voice produced information and providing a phoneme-identifying first representation of the voice produced information having reduced bandwidth transmission requirement relative to the recognized voice produced information and a representation of the characteristic of the voice produced information;

(b) phonemically transmitting the first representation of the voice produced information and the characteristic of the voice produced information to a receiver;

(c) providing a phoneme-identifying second representation of the first representation of increased bandwidth relative to the first representation at the receiver; and

(d) phonemically recreating the voice produced information and the characteristic of the voice produced information responsive to the second representation and the characteristic of the voice produced information.

18. The method of claim 17 wherein said step of recognizing includes providing a first data base responsive to said voice produced information.

19. The method of claim 18 wherein said step of providing a second representation includes the step of providing a second data base responsive to said first representation.

20. The method of claim 19 wherein said first data base provides said first representation in binary form and said second data base provides said second representation.

21. The method of claim 20 wherein said step of providing a recreation of said recognized one of said plurality of different types of information responsive to said second representation is one of a visual display or an audible recreation.

22. The method of claim 18 wherein said first data base provides said first representation in binary form.

23. The method of claim 19 wherein said step of providing a recreation of said recognized one of said plurality of different types of information responsive to said second representation is one of a visual display or an audible recreation.

24. The method of claim 21 wherein said first representation is a combination of phoneme information and voice type information.

25. The method of claim 17 wherein said step of providing a second representation includes the step of providing a second data base responsive to said first representation.

26. The method of claim 25 wherein said second data base provides said second representation in binary form.

27. The method of claim 17 wherein said step of providing a recreation of said recognized one of said plurality of different types of information responsive to said second representation is one of a visual display or an audible recreation.

28. The method of claim 17 wherein said first representation is a combination of phoneme information and voice type information.

29. The method of claim 17 further including the step of storing one of said first or second representations of said voice produced information and indicating at said receiver the storage of one of said first or second representations.

30. A pager system comprising:

(a) a base station for receiving a standard telephone voice message, encoding the message into a phoneme-identifying reduced binary representation thereof and transmitting the encoded representation as a stream of phoneme identification numbers; and

(b) a mobile unit for receiving the encoded representation and recreating an expanded representation of the phoneme-identifying reduced binary representation of the voice message.

31. The system of claim 30 wherein said encoding is provided by phoneme recognition.

32. The system of claim 31 wherein said encoding includes code representing voice characteristics.

33. The system of claim 32 wherein said mobile unit includes means for storing said encoded representation and reproducing a representation of the voice message on command.

34. The system of claim 31 wherein said mobile unit includes means for storing said encoded representation and reproducing a representation of the voice message on command.

35. The system of claim 30 wherein said encoding is provided by speech recognition.

36. The system of claim 35 wherein said mobile unit includes means for storing said encoded representation and reproducing a representation of the voice message on command.

37. The system of claim 30 wherein said mobile unit includes means for storing said encoded representation and reproducing a representation of the voice message on command.

38. A communication system comprising:

(a) a mobile unit for receiving a voice message and encoding said voice message to a reduced binary representation thereof and transmitting said reduced binary representation to a base station; and

(b) a base station for receiving said binary representation, recreating a representation of said voice message in standard telephone format for transmission in a standard telephone network.

39. A communication system comprising:

(a) a mobile unit for receiving a voice message and encoding said voice message to a reduced binary representation thereof and transmitting said reduced binary representation to a base station, and

(b) a base station for receiving said binary representation, recreating a representation of said voice message in standard telephone format for transmission in a standard telephone network;

said base station includes a data base having voice characteristics of system users stored therein for use in recreating said voice message.

40. A pager system which comprises:

(a) voice recognition means for recognizing voice produced information and providing a phoneme-identifyng first representation of the voice produced information having reduced bandwidth transmission requirement relative to the recognized voice produced information;

(b) transmission means for phonemically transmitting the first representation of the voice produced information to receiving means;

(c) receiving means responsive to the first representation of the voice produced information for providing a phoneme-identifying second representation of the first representation of the voice produced information of increased bandwidth relative to the first representation; and

(d) means responsive to the second representation for phonemically recreating the voice produced information.

41. A method of paging which comprises the steps of:

(a) recognizing voice produced information and providing a phoneme-identifying first representation of the voice produced information having reduced bandwidth transmission requirement relative to the recognized voice produced information;

(b) phonemically transmitting the first representation of the voice produced information to a receiver;

(c) providing a phoneme-identifying second representation of the first representation of increased bandwidth relative to the first representation at the receiver; and

(d) phonemically recreating the voice produced information responsive to the second representation.

42. A radio transmitter for phonemically transmitting a voiced message signal spoken in a particular language having a set of phonemes, comprising:

an encoder, having a phonemic recognition database storing data for recognizing each phoneme and assigning it a corresponding distinct phoneme identification number for analyzing the voiced message signal into a stream of phoneme identification numbers, and

radio transmitter for transmitting a radio signal modulated by the stream of phonemic identification numbers.

43. A radio receiver for converting a radio signal modulated by a corresponding stream of phonemic identification numbers into a corresponding voiced message signal, comprising:

a radio receiver for receiving the radio signal and recovering the stream of phonemic identification numbers from it; and

a decoder, having a phonemic speech generation database storing data for synthesizing the stream of phoneme identification numbers back into the corresponding voiced message signal.

44. The radio receiver of claim 43 for receiving radio signals further modulated by a voice type identification number, wherein the radio receiver receives and recovers the voice type identification number, and

the decoder has a voice type generation database storing data for synthesizing the voiced message signal with a voice type that corresponds to the voice type identification number.