Method and system for sharing portable voice profiles

• US 8,214,208 B2
• Filed: 09/28/2006
• Issued: 07/03/2012
• Est. Priority Date: 09/28/2006
• Status: Expired due to Fees

• Current Assignee: reQall, Inc.
• Original Assignee: reQall, Inc.
• Inventors: Mallett, Jacqueline, Vemuri, Sunil, Machiraju, N. Rao
• Primary Examiner(s): Godbold, Douglas
• Application Number:
  US11/536,117
• Publication Number:
  US 20080082332A1
• Time in Patent Office: 2,105 Days
• Field of Search: 704231-236
• US Class Current: 704/231
• CPC Class Codes: G10L 15/07 to the speaker
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques

Abstract

An embodiment of the present invention provides a speech recognition engine that utilizes portable voice profiles for converting recorded speech to text. Each portable voice profile includes speaker-dependent data, and is configured to be accessible to a plurality of speech recognition engines through a common interface. A voice profile manager receives the portable voice profiles from other users who have agreed to share their voice profiles. The speech recognition engine includes speaker identification logic to dynamically select a particular portable voice profile, in real-time, from a group of portable voice profiles. The speaker-dependent data included with the portable voice profile enhances the accuracy with which speech recognition engines recognize spoken words in recorded speech from a speaker associated with a portable voice profile.

Claims

1. An apparatus comprising:

a storage device configured to store portable voice profiles; and

a computer-based system coupled to the storage device, the computer-based system including (1) a speech recognition engine configured to utilize the portable voice profiles in recognizing speech from various speakers, wherein each portable voice profile is associated with and customized to a particular speaker, and enhances an-accuracy with which the speech recognition engine converts the particular speaker'"'"'s speech to text, and the speech recognition engine includes speaker identification logic to analyze voice signals to identify the particular speaker and then dynamically select a particular portable voice profile associated with the identified speaker;

(2) a local group manager-configured to facilitate establishing a local user of the apparatus as a member of a group and to manage access privileges to a portable voice profile associated with the local user according to connections between the local user and other members of the group and instructions of the local user; and

(3) a local voice profile manager configured to facilitate an exchange of the portable voice profile associated with the local user with another user that is a member of the group, wherein at least one of the portable voice profiles includes data derived from use with a variety of speech recognition engines.

2. The apparatus of claim 1, wherein the local voice profile manager is further configured to utilize a communication protocol to receive a portable voice profile from a remote apparatus associated with a member of the group to which the local user is a member.

3. The apparatus of claim 1, wherein the local voice profile manager is further configured to utilize a communication protocol to send the portable voice profile associated with the local user of the apparatus to a remote apparatus associated with a member of the group to which the local user is a member.

4. The apparatus of claim 1, wherein the group is initially defined by an administrative application executing on a remote apparatus, and the local group manager provides a listing of all groups to which the local user is allowed to join.

5. The apparatus of claim 4, wherein the group is defined as a secure group by the administrative application executing on the remote apparatus, and the local group manager utilizes cryptographic communication protocols to enable the local user to join the secure group.

6. The apparatus of claim 1, wherein each portable voice profile of the portable voice profiles is received by the local voice profile manager from a remote voice profile manager, wherein each remote voice profile manager communicates a portable voice profile to the local voice profile manager after a speaker associated with the local voice profile manager has agreed to exchange a portable voice profile with a speaker associated with the remote voice profile manager.

7. An apparatus, comprising:

a storage device configured to store a plurality of portable voice profiles; and

a computer-based system coupled to the storage device, the computer-based system including (1) a speech recognition engine configured to convert a voice signal to text, the speech recognition engine including speaker identification logic configured to analyze the voice signal to identify the speaker and then dynamically select a particular portable voice profile associated with the identified speaker, in real-time, from the plurality of portable voice profiles;

(2) a local group manager configured to manage access privileges to a local user'"'"'s portable voice profile according to connections between a local user of the apparatus and other members of a group to which the local user belongs and instructions of the local user; and

(3) a local voice profile manager configured to receive the plurality of portable voice profiles, each portable voice profile associated with a speaker and including speaker-dependent data accessible to a plurality of speech recognition engines through an interface, the speaker-dependent data to enhance an accuracy with which each speech recognition engine in the plurality of speech recognition engines recognizes spoken words in a voice signal from a speaker associated with a portable voice profile, wherein at least one of the plurality of portable voice profiles includes data derived from use with a variety of speech recognition engines.

8. The apparatus of claim 7, wherein the local group manager is further configured to facilitate establishing the local user of the apparatus as a member of the group, and to facilitate establishing connections with other users as members of the group.

9. The apparatus of claim 7, wherein the speech recognition engine accesses speaker-dependent data from one or more of the plurality of portable voice profiles, and utilizes the speaker-dependent data to enhance the accuracy with which the speech recognition engine converts the voice signal to text.

10. The apparatus of claim 7, wherein the interface is an application programming interface (API), and the speech recognition engine accesses speaker-dependent data from one or more of the plurality of portable voice profiles by making an API function call, and utilizes the accessed speaker-dependent data to enhance the accuracy with which the speech recognition engine converts the voice signal to text.

11. The apparatus of claim 7, wherein the plurality of portable voice profiles are received from a plurality of remote voice profile managers.

12. The apparatus of claim 7, wherein the local voice profile manager is associated with at least one local portable voice profile, and is further configured to automatically communicate the at least one local portable voice profile to a remote voice profile manager when a speaker associated with the local portable voice profile has provided instructions to the local voice profile manager to exchange the local portable voice profile with a speaker associated with the remote voice profile manager.

13. The apparatus of claim 7, wherein each portable voice profile of the plurality of portable voice profiles received by the local voice profile manager are received from a remote voice profile manager, wherein each remote voice profile manager communicates a portable voice profile to the local voice profile manager after a speaker associated with the local voice profile manager has agreed to exchange a portable voice profile with a speaker associated with the remote voice profile manager.

14. The apparatus of claim 13, wherein the local voice profile manager and each remote voice profile manager are associated with a user-interface, and each user-interface is configured to facilitate an exchange of portable voice profiles between speakers associated with different voice profile managers.

15. The apparatus of claim 7, wherein the voice signal is received from one of a plurality of applications, each application configured to generate a voice signal compatible for analysis by any one of the plurality of speech recognition engines.

16. The apparatus of claim 15, wherein the plurality of applications include at least one application from the following group of applications:

dictation application, command and control application, multi-user recorder application, multi-user conferencing application, communication-load management application, information update application, and information broadcast application.

17. The apparatus of claim 7, wherein the speaker-dependent data of each portable voice profile includes acoustic characteristics of a speaker associated with the portable voice profile.

18. The apparatus of claim 7, wherein the speaker-dependent data of each portable voice profile is derived from feedback provided by any one of said plurality of speech recognition engines.

19. The apparatus of claim 7, wherein the speaker-dependent data of each portable voice profile is derived without explicit training and is updated over time.

20. The apparatus of claim 7, wherein the portable voice profiles are communicated directly over a peer-to-peer network.

21. The apparatus of claim 7, wherein the portable voice profiles are communicated indirectly over a client-server network.

22. The apparatus of claim 7, wherein the portable voice profiles are communicated indirectly over a hybrid network.

23. A computer-implemented method comprising:

facilitating establishing a user as a member of a group using a group manager module of a speech recognition system executing on a computer-based platform;

automatically exchanging portable voice profiles, using said group manager module with at least one other user who is a member of the group provided said exchanges are permitted by access control privileges for the portable voice profiles established by owners thereof, said access control privileges accounting for connections between an owner of a portable voice profile and other members of a group to which the owner belongs and instructions of the owner, wherein at least one of the portable voice profiles includes data derived from use with a variety of speech recognition engines;

using at least one of the portable voice profiles to determine a current speaker within a voice recording; and

utilizing said at least one of the portable voice profiles within a speech recognition process to convert a speech recording to text.

24. The method of claim 23, wherein the portable voice profiles are exchanged over a network, and each portable voice profile is associated with a speaker and includes speaker-dependent data accessible to a plurality of speech recognition engines through an interface, the speaker-dependent data to enhance an accuracy with which each speech recognition engine in the plurality of speech recognition engines recognizes spoken words in recorded speech from a respective speaker associated with a respective portable voice profile.