System and method for providing a textual representation of an audio message to a mobile device

• US 8,244,540 B2
• Filed: 02/20/2012
• Issued: 08/14/2012
• Est. Priority Date: 05/02/2006
• Status: Expired due to Fees

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Proux, Denys M., Cheminot, Eric H.
• Primary Examiner(s): He, Jialong
• Application Number:
  US13/400,288
• Publication Number:
  US 20120150538A1
• Time in Patent Office: 176 Days
• Field of Search: 704/270, 704/275, 455/563, 455/413, 379/88.01, 379/93.24
• US Class Current: 704/270
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 1/72436 for text messaging, e.g. short messaging services [SMS] or e-mails
• CPC Class Codes: H04M 2201/60 Medium conversion
• CPC Class Codes: H04M 3/42382 Text-based messaging services in telephone networks such as PSTN/ISDN, e.g. User-to-User Signalling or Short Message Service for fixed networks
• CPC Class Codes: H04W 4/12 Messaging; Mailboxes; Announcements

Abstract

A textual representation of a voice message is provided to a communication device, such as a mobile phone, for example, when the mobile phone is operating in a silent mode. The voice message is input by a caller and the voice message converted to phonemes. A text representation of the voice message is transmitted to the mobile phone. The representation includes characters based on the phonemes with well known words being represented in an easily understood shorthand format.

Claims

1. A method of providing a first communication device with a textual representation of a voice message input at a second communication device, the method comprising:

automatically detecting that the first communication device is operating in a silent mode in which the first communication device is switched on but wherein calls are directly routed to a user'"'"'s messaging system;

in response to said detection, prompting input of a voice message at the second communication device;

automatically converting the voice message input at the second communication device to phonemes by;

(i) accessing a dictionary of words and their corresponding phonemes to identify, where present, a word which corresponds to a group of the phonemes;

(ii) for a phoneme not recognized as part of a word in the dictionary, representing the phoneme as a representative character; and

automatically transmitting a textual representation of the converted voice message to the first communication device, the textual representation including characters representative of at least some of the phonemes.

2. The method of claim 1, further comprising:

automatically displaying the textual representation on the first communication device.

3. The method of claim 1, wherein the phonemes are selected from a finite set of phonemes and wherein each phoneme is associated with a representative character and wherein the representation of phonemes not recognized as part of a word includes representing the phoneme as its representative character.

4. The method of claim 3, wherein the representative characters include letters and numbers.

5. The method of claim 3, wherein for at least a majority of the phonemes, each phoneme is associated with a single representative character.

6. The method of claim 1, wherein the conversion of the voice message includes converting the voice message to feature vectors, each feature vector corresponding to at least one phoneme.

7. The method of claim 1, wherein the first communication device comprises a mobile phone.

8. The method of claim 1, wherein the prompting of the user further comprises prompting the user to space each word of the message by a gap while speaking the message.

9. The method of claim 1, wherein the transmitting of the textual representation of the voice message to the first communication device includes wirelessly transmitting the textual representation to the first communication device.

10. The method of claim 1, wherein the converting of the voice message to phonemes and the transmitting of the textual representation of the voice message to the first communication device are performed by a communication station remote from the first and second communication devices.

11. The method of claim 1, further comprising:

prompting a user of the second communication device to input a second voice message; and

storing the second voice message in a message server accessible by the first communication device.

12. A system for providing a first communication device with a textual representation of a voice message input at a second communication device comprising:

a voice message conversion system which converts an input voice message input at the second communication device to phonemes and generates a textual representation of the input voice message, the textual representation including characters representative of at least some of the phonemes, wherein the voice message conversion system comprises a dictionary of words and their corresponding phonemes for identifying, where present, a word which corresponds to a group of the phonemes, and where absent, representative characters; and

a switching center in communication with the voice message conversion system, which is capable of receiving and transmitting messages, the switching center receiving the input voice message from the second communication device and transmitting a message to the first communication device, the message comprising the textual representation generated by the voice message conversion system, the switching center detecting that the first communication device is operating in a silent mode and, in response to said detecting that the first communication device is operating in a silent mode, prompts a user of the second communication device to input the voice message for conversion by the voice message conversion system to the textual representation.

13. The system of claim 12, wherein the voice message conversion system is remote from the first and second communication devices.

14. The system of claim 12, wherein the switching center transmits the message comprising the textual representation wirelessly to the first communication device.

15. The system of claim 12, wherein the voice message conversion system further comprises:

a first transducer which accesses the dictionary of words to identify a group of the phonemes which corresponds to a word; and

a second transducer which, for at least one phoneme not recognized as part of the word in the dictionary of words, represents the phoneme as a character.

16. The system of claim 12, further comprising a messaging system in communication with the switching center, which stores at least one of the voice message and a second voice message received from the second communication device.

17. The system of claim 12, wherein the voice message conversion system is remote from the first and second communication devices.

18. A method of providing a first communication device with a textual representation of a voice message transmitted from a second communication device, comprising:

detecting that the first communication device is operating in a silent mode;

in response to said detection, prompting a user of the second communication device to input a voice message;

converting the voice message input at the second communication device to phonemes, the phonemes being selected from a finite set of phonemes,

accessing a dictionary of words to identify any words which correspond to a group of the phonemes in the voice message, the dictionary storing words along with their corresponding phonemes;

for a phoneme not recognized as being a part of one of groups of phonemes that correspond to a word in the dictionary, representing the phoneme as a representative character; and

transmitting a textual representation of the voice message to the first communication device, the representation including characters representative of at least some of the phonemes.

19. The method of claim 18, further comprising displaying the textual representation on the first communication device.

20. The method of claim 18, wherein for a majority of the phonemes in the set, each phoneme is associated in memory with a single representative character.

21. The method of claim 18, wherein at least some of the words in the dictionary of words comprising Short Message Service (SMS) expressions.