Network/peer assisted speech coding

• US 9,245,535 B2
• Filed: 02/28/2013
• Issued: 01/26/2016
• Est. Priority Date: 10/22/2009
• Status: Active Grant

• Current Assignee: Avago Technologies International Sales Pte Limited (Broadcom, Inc.)
• Original Assignee: Broadcom Corporation (Broadcom, Inc.)
• Inventors: Zopf, Robert W., Hale, Kelly
• Primary Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US13/781,055
• Publication Number:
  US 20130179161A1
• Time in Patent Office: 1,062 Days
• Field of Search: 704/500
• US Class Current: 1/1
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• 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: G10L 19/16 Vocoder architecture
• CPC Class Codes: G10L 21/00 Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility G10L19/00 takes precedence

Abstract

A communications network is used to transfer user attribute information about participants in a communication session to their respective communication terminals for storage and use thereon to configure a speech codec to operate in a speaker-dependent manner, thereby improving speech coding efficiency. In a network-assisted model, the user attribute information is stored on the communications network and selectively transmitted to the communication terminals while in a peer-assisted model, the user attribute information is derived by and transferred between communication terminals.

Claims

1. An apparatus, comprising:

a server connected to a first database, the server being configured to;

obtain an identifier of a user of a first communication terminal;

retrieve user attribute information associated with the user of the first communication terminal from the first database based on an identifier of the user of the first communication terminal, and

provide the user attribute information associated with the user of the first communication terminal to a second communication terminal for use in decoding an encoded speech signal received from the first communication terminal during a communication session.

2. The apparatus of claim 1, wherein the server is configured to obtain the identifier of the user of the first communication terminal, retrieve the user attribute information, or provide the user attribute information responsive to the initiation of the communication session between the first communication terminal and the second communication terminal.

3. The apparatus of claim 1, wherein the server is further configured to:

provide the user attribute information associated with the user of the first communication terminal to the first communication terminal for use in encoding a speech signal for transmission to the second communication terminal during the communication session.

4. The apparatus of claim 1, wherein the server is further configured to:

obtain an identifier of a user of the second communication terminal;

retrieve user attribute information associated with the user of the second communication terminal from the first database based on the identifier of the user of the second communication terminal; and

provide the user attribute information associated with the user of the second communication terminal to the first communication terminal for use in decoding an encoded speech signal received from the second communication terminal during the communication session.

5. The apparatus of claim 4, wherein the server is further configured to:

provide the user attribute information associated with the user of the second communication terminal to the second communication terminal for use in encoding a speech signal for transmission to the first communication terminal during the communication session.

6. The apparatus of claim 1, wherein the server is further configured to:

retrieve input condition attribute information associated with a current input condition of the first communication terminal from a second database; and

provide the input condition attribute information associated with the current input condition of the first communication terminal to the second communication terminal for use in decoding the encoded speech signal received from the first communication terminal during the communication session.

7. The apparatus of claim 6, wherein the server is further configured to:

provide the input condition attribute information associated with the current input condition of the first communication terminal to the first communication terminal for use in encoding a speech signal for transmission to the second communication terminal during the communication session.

8. A communication terminal, comprising:

a processor configured to;

process speech signals originating from a first user to derive first user attribute information therefrom, and

use the first user attribute information to encode a speech signal originating from the first user for transmission to a remote communication terminal during a communication session;

a memory configured to store the first user attribute information; and

a transmitter configured to transmit the first user attribute information to the remote communication terminal for use in decoding an encoded speech signal received from the first communication terminal during the communication session responsive to the initiation of the communication session between the first communication terminal and the remote communication terminal.

9. The communication terminal of claim 8, wherein the processor is further configured to:

encode the speech signal originating from the first user using at least one of a speaker-dependent quantization table or a speaker-dependent encoding algorithm that is selected based on the first user attribute information.

10. The communication terminal of claim 8, further comprising:

a receiver configured to receive second user attribute information from the remote communication terminal; and

wherein the processor is further configured to use the second user attribute information to decode an encoded speech signal received from the remote communication terminal during the communication session.

11. The communication terminal of claim 10, the processor being further configured to use the second user attribute information to decode the encoded speech signal received from the remote communication terminal by configuring a speech decoder to decode the encoded speech signal received from the remote communication terminal using at least one of a speaker-dependent quantization table or a speaker-dependent encoding algorithm that is selected based on the second user attribute information.

12. The communication terminal of claim 10,

wherein the encoded speech signal received from the remote communication terminal comprises an encoded speaker-independent signal and an encoded speaker-dependent signal, and

the processor being further configured to:

decode the encoded speaker-independent signal to produce a decoded speaker-independent signal;

decode the encoded speaker-dependent signal to produce a decoded speaker-dependent signal; and

synthesize an output speech signal based on the decoded speaker-independent signal, the decoded speaker-dependent signal and the first user attribute information.

13. The communication terminal of claim 8, the transmitter being further configured to transmit the first user attribute information to the remote communication terminal responsive to the initiation of the communication session between the first communication terminal and the remote communication terminal and further responsive to a determination by a speaker identification module included in the first communication terminal that a user of the first communication terminal is the first user.

14. A method, comprising:

decoding a first encoded speech signal at a first communication terminal using user attribute information associated with a user of a second communication terminal to provide a decoded speech signal, the decoding comprising using the user attribute information to modify a configuration of a configurable speech codec of the first communication terminal to operate in a speaker-dependent manner; and

playing back a representation of the decoded speech signal by one or more speakers of the first communication terminal.

15. The method of claim 14, wherein the first encoded speech signal is encoded at the second communication terminal using the user attribute information associated with the user of the second communication terminal.

16. The method of claim 14, further comprising:

storing the user attribute information associated with the user of the second communication terminal in at least one of a memory of the first communication terminal or a memory of the second communication terminal.

17. The method of claim 14, further comprising:

transmitting a second encoded speech signal from the first communication terminal for decoding at the second communication terminal using user attribute information associated with a user of a first communication terminal.

18. The method of claim 17, wherein the second encoded speech signal is encoded at the first communication terminal using the user attribute information associated with the user of the first communication terminal.

19. The method of claim 17, further comprising:

storing the user attribute information associated with the user of the first communication terminal in at least one of a memory of the first communication terminal or a memory of the second communication terminal.

20. The method of claim 14, wherein decoding is performed using a configurable speech decoder.