Telephone number retrieval system & method

• US 20050094782A1
• Filed: 10/29/2004
• Published: 05/05/2005
• Est. Priority Date: 10/29/2003
• Status: Active Grant

• Current Assignee: LG Electronics, Inc. (LG Corporation)
• Original Assignee: LG Electronics, Inc. (LG Corporation)
• Inventors: Kim, Chan-Woo
• Granted Patent: US 7,356,356 B2
• Time in Patent Office: Days
• US Class Current: 379/88.16
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: H04M 1/271 controlled by voice recognition
• CPC Class Codes: H04M 1/2753 providing data content
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2201/60 Medium conversion
• CPC Class Codes: H04M 2250/68 with means for recording information, e.g. telephone number during a conversation recording of telephone conversations H04M1/656
• CPC Class Codes: H04M 3/4931 Directory assistance systems

Abstract

Methods and systems directed to telephone number retrieval are provided. A terminal requests a telephone number from a telephone number service. A voice response comprising the telephone number is received from the telephone number service. A feature vector sequence is stored in memory of the terminal as a reference pattern for the received voice response. The voice response has designated words between and among numbers of the telephone number. A keyword spotting routine searches for the designated words. Connecting words, located between and among designated words, comprising the telephone number are extracted and stored in a buffer. A number recognizer analyzes contents of the buffer. The number recognizer outputs a recognized telephone number for display on a terminal and/or storage in memory for future use.

Claims

1. In a mobile communication device, a method for displaying and/or storing a recognized telephone number in a buffer for future retrieval by a user, the method comprising the steps of:

accessing a telephone number service;

receiving a voice response from the telephone number service, the voice response comprising a telephone number portion;

searching for at least one designated word of the telephone number service within the voice response according to a keyword spotting routine;

extracting and storing numbers between designated words in a buffer;

reading from a contents of the buffer a recognized telephone number utilizing a number recognizer; and

transferring the recognized telephone number for viewing by a user to at least one of a display and a memory location.

2. The method of claim 1, wherein the telephone number service is an Automatic Response System.

3. The method of claim 1, wherein the telephone number service has a voice type or a response type that has been changed and a terminal downloads a parameter file to maintain high performance of the telephone service.

4. The method of claim 1, further comprising the steps of:

providing by a service provider to the user information that the telephone number service has a format change and how to download the changed contents, and

charging a fee in the form of a business model.

5. The method of claim 1, further comprising the step of:

downloading of the reference pattern or the parameter file by the terminal through a personal computer upon receiving information from internet.

6. The method of claim 2, further comprising the step of downloading by the terminal directly the reference pattern on a wireless internet.

7. The method of claim 1, further comprising the step of listening by the user for the telephone number from at least one of a voice of a telephone operator and a speaker-dependent mechanical voice of an Automatic Response System.

8. The method of claim 1, wherein the designated words includes at least one specific word before and after the number portion of the telephone number.

9. The method of claim 1, wherein the recognized telephone number from the voice signals is recognized by a word recognition algorithm.

10. The method of claim 9, wherein the word recognition algorithm is a Dynamic Time Warping (DTW) algorithm.

11. The method of claim 9, wherein the DTW algorithm uses a feature vector sequence of 0 to 9 as a reference pattern.

12. The method of claim 9, wherein the word recognition algorithm is a Hidden Markov Model (HMM) algorithm.

13. The method of claim 9, wherein the word recognition algorithm is a Vector Quantization (VQ) algorithm.

14. The method of claim 9, wherein the word recognition algorithm is a Neural Network (NN) algorithm.

15. The method of claim 1, further comprising the step of defining feature vectors as a sequence produced by voice pre-processing technology upon completion of the keyword spotting routine.

17. The method of claim 1, wherein the voice response utilizes a voice pre-processing technology including Mel-Frequency Cepstral Coefficients (MFCC) for extracting characteristics of the voice response.

18. The method of claim 15, wherein the voice pre-processing technology utilizes Linear Predictive Cepstral Coefficients for extracting characteristics of the voice response.

19. The method of claim 15, wherein the voice pre-processing technology utilizes Perceptual Linear Prediction for extracting characteristics of the voice response.

16. The method of claim 16, further comprising storing in the memory of the terminal the defined feature vectors.

20. A method for a mobile communication terminal to store a specific reference feature vector sequence in memory associated with a telephone number comprising:

searching a terminal accessing a telephone number service for at least one of a voice of a telephone operator and mechanical voice of an Automatic Response System (ARS);

searching for a first specified word and a second specified word in the at least one of the voice of the telephone operator and the mechanical voice of the Automatic Response System, utilizing a keyword spotting routine;

storing a voice response between the first specified word and the second specified word searched in a buffer;

applying a word recognition algorithm to the voice response stored in the buffer;

recognizing a telephone number from the contents of the buffer, and

displaying the recognized telephone number on the display and storing the telephone number in a phonebook of the terminal.

21. The method of claim 20, further comprising the steps of:

defining feature vectors as a sequence according to a voice pre-processing technology, and

applying the keyword spotting routine using specific reference vector obtained from the defined feature vectors.

22. The method of claim 21, wherein the voice pre-processing technology utilizes Mel-Frequency Cepstral Coefficients for extracting characteristics of voice.

23. The method of claim 21, wherein the voice pre-processing technology utilizes Linear Predictive Cepstral Coefficients for extracting characteristics of voice.

24. The method of claim 21, wherein the voice pre-processing technology utilizes Perceptual Linear Prediction for extracting characteristics of voice.

25. The method of claim 21, wherein the keyword spotting routine uses a feature vector sequence of ‘

The number is’

as a reference pattern.

26. The method of claim 21, wherein the word recognition algorithm is a Dynamic Time Warping algorithm.

27. The method of claim 26, wherein the Dynamic Time Warping algorithm uses a feature vector sequence of ‘

0, 1, 2, 3, 4, 5, 6, 7, 8, 9’

as a reference pattern.

28. The method of claim 20, wherein the word recognition algorithm is a Hidden Markov Model algorithm.

29. The method of claim 20, wherein the word recognition algorithm is a Vector Quantization algorithm.

30. The method of claim 20, wherein the word recognition algorithm is a Neural Network algorithm.

31. A mobile communication device for managing messages communicated in a mobile communication system, the mobile communication device comprising:

an RF module comprising a transmitter and a receiver communicating messages in a mobile communication system; and

means for accessing a telephone number service;

means for receiving a voice response from the telephone number service including a telephone number portion;

means for searching for at least one designated word of the telephone number service within the voice response according to a keyword spotting routine;

means for extracting and storing numbers between the designated words in a buffer;

means for reading from a contents of the buffer a recognized telephone number utilizing a number recognizer; and

means for transferring the recognized telephone number to a display for viewing by a user and/or to a memory location for future use.

32. The device of claim 31, wherein the telephone number service is an Automatic Response System.

33. The device of claim 31, wherein the telephone number service has a voice type or a response type that has been changed and a terminal downloads a parameter file to maintain high performance of the telephone service.

34. The device of claim 31, wherein the telephone number service has a format change and a service provider informs the user how to download the changed contents, and charges a fee in the form of a business model.

35. A network for radio communication with a terminal in a mobile communication system, the network comprising:

at least one transmitter and at least one receiver communicating in a mobile communication network;

means for accessing a telephone number service;

means for receiving a voice response from the telephone number service including a telephone number portion;

means for searching for at least one designated word of the telephone number service within the voice response according to a keyword spotting routine;

means for extracting and storing numbers between the designated words in a buffer;

means for reading from a contents of the buffer a recognized telephone number utilizing a number recognizer; and

means for transferring the recognized telephone number to a display for viewing by a user and to a memory location for future use.

36. The network of claim 35, wherein the telephone number service is an Automatic Response System.

37. The network of claim 35, wherein the telephone number service has a voice type or a response type that has been changed and a terminal downloads a vector reference pattern to change variables of the telephone service.

38. The network of claim 35, wherein the telephone number service has a format change and a service provider informs the user how to download the changed contents, and charges a fee in the form of a business model.