Speech information communication system

• US 6,498,834 B1
• Filed: 04/30/1998
• Issued: 12/24/2002
• Est. Priority Date: 04/30/1997
• Status: Expired due to Fees

• Current Assignee: NEC Corporation
• Original Assignee: NEC Corporation
• Inventors: Sera, Takafumi
• Primary Examiner(s): Hoosain, Allan
• Application Number:
  US09/069,791
• Time in Patent Office: 1,699 Days
• Field of Search: 379/67.1, 379/88.01, 379/88.02, 379/88.17, 379/88.19, 379/93.03, 379/91.01, 379/93.12, 379/93.25, 379/88.07, 379/88.11, 379/88.12, 379/88.13, 379/88.05, 379/88.16, 379/88.06, 379/88.08, 379/88.14, 379/88.15, 704/203, 704/234, 704/246, 704/260, 704/243, 704/251, 704/273, 704/270, 704/272
• US Class Current: 379/88.02
• 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: H04M 1/57 Arrangements for indicating or recording the number of the calling subscriber at the called subscriber's set at the operator set in a manual exchange H04M5/20
• CPC Class Codes: H04M 1/663 Preventing unauthorised calls to a telephone set

Abstract

A speech information communication system includes a speech recognizer which converts an input speech signal to character code information and speech feature information. The character code information and the speech feature information are transmitted to a receiving side where the received character code information is converted to an output speech signal depending on the received speech feature information.

Claims

1. A system comprising:

a first converter for converting an input speech signal to character code information representative of recognized words of said input speech signal and speech feature information representative of user specific speech characteristics of a speaker generating said input speech signal, said user specific speech characteristics comprising a vocal tract feature of the speaker and a speed of the speech of the speaker;

a character code transmitter for transmitting the character code information to a transmission line;

a speech feature information transmitter for transmitting the speech feature information to a transmission line;

a receiver for receiving character code information corresponding to said recognized words and speech feature information from the transmission line; and

a second converter for converting received character code information and speech information to an output speech signal corresponding to said recognized words and having audible speech characteristics substantially identical to the content of said input speech signal and the user specific speech characteristics of said speaker.

2. The system according to claim 1, wherein the first converter comprises:

a speech recognizer for recognizing the input speech signal to produce the character code information representative of said recognized words and the speech feature information of said speaker.

3. The system according to claim 1, wherein the receiver comprises:

a first receiver for receiving the character code information from the transmission line; and

a second receiver for receiving the speech feature information from the transmission line.

4. The system according to claim 1, wherein the second converter comprises:

a speech synthesizer for synthesizing said output speech signal from the received character code information and the received speech feature information.

5. The system according to claim 1, further comprising:

a memory for storing at least one piece of registered speech feature information;

a searcher for searching the memory for the received speech feature information; and

a controller for producing a screening signal.

6. The system according to claim 5, wherein the controller disconnects communication between the transmitter and the receiver when no match is found.

7. The system according to claim 5, further comprising:

a translator provided between the character code transmitter and the receiver, for translating the character code information from a first language of the input speech signal to a second language of the output speech signal.

8. The system according to claim 1, further comprising:

a display;

a memory for storing at least one piece of registered speech feature information and at least one piece of registered speaker information which correspond to each other;

a searcher for searching the memory for a match between the received speech feature information and the registered speech feature information; and

a controller for controlling the display such that, when a match is found in the memory, registered speaker information corresponding to the matched registered speech feature information is displayed on said display.

9. The system according to claim 8, wherein the controller further disconnects communication between the transmitter and the receiver whether no match is found.

10. The system according to claim 8, further comprising:

a translator provided between the character code transmitter and the receiver, for translating the character code information from a first language of the input speech signal to a second language of the output speech signal.

11. The system according to claim 1, further comprising:

a translator provided between the character code transmitter and the receiver, for translating the character code information from a first language of the input speech signal to a second language of the output speech signal.

12. A method for transmitting speech information from a sending side to a receiving side, comprising the steps of:

at the sending side,

converting an input speech signal to character code information representative of recognized words of said input speech signal and speech feature information representative of user specific speech characteristics of a speaker generating said input speech signal, said user specific speech characteristics comprising a vocal tract feature of the speaker and a speed of the speech of the speaker; and

transmitting the character code information from a character code transmitter to a transmission line,

transmitting the speech feature information from a speech feature transmitter to the transmission line, and

at the receiving side,

receiving character code information corresponding to said recognized words and speech feature information from the transmission line; and

converting received character code information and speech feature information to an output speech signal corresponding to said recognized words and having audible speech characteristics substantially identical to the content of said input speech signal and the user specific speech characteristics of said speaker.

13. The method to claim 12, further comprising the steps of:

storing at least one piece of registered speech feature information onto a memory;

searching the memory for a match between the registered speech feature information and the received speech feature information; and

producing a screening signal to a display depending on whether a match is found in the memory.

14. The method according to claim 13, further comprising the step of disconnecting communication between the transmitting side and the receiving side whether no match is found.

15. The method according to claim 12, further comprising the steps of:

storing at least one piece of registered speech feature information and at least one piece of registered speaker information which correspond to each other onto a memory;

searching the memory for a match between the registered speech feature information and the received speech feature information; and

controlling a display in a manner that, when a match is found in the memory, registered speaker information corresponding to the matched registered speech feature information said display.

16. The method according to claim 12, further comprising the steps of:

receiving the character code information from the sending side;

translating the character code information from a first language of the input speech signal to a second language of the output speech signal; and

transmitting the character code information of the second language to the receiving side.

17. A receiver connected to a transmission line, comprising:

a receiving section including a character code receiver for receiving character code information representative of recognized words of an input speech signal, and a speech feature information receiver for receiving speech feature information representative of user specific speech characteristics of a speaker generating said input speech signal from the transmission line, wherein the character code information and the speech feature information are generated from an input speech signal by speech recognition, and wherein the user specific speech characteristics include a vocal tract feature of the speaker and a speed of the speech of the speaker; and

a converter for converting received character code information and speech feature information to an output speech signal providing audible speech characteristics substantially identical to the content of said input speech signal and the user specific speech characteristics of said speaker.

18. The receiver according to claim 17, further comprising:

a memory for storing at least one piece of registered speech feature information;

a searcher for searching the memory for the received speech feature information; and

a controller for producing a screening signal for a display depending on whether a match is found in the memory.

19. The receiver according to claim 18, wherein the controller disconnects communication of the receiver when no match is found.

20. The receiver according to claim 17, further comprising:

a display;

a memory for storing at least one piece of registered speech feature information and at least one piece of registered speaker information which correspond to each other;

a searcher for searching the memory for a match between the received speech feature information and the registered speech feature information; and

a controller for controlling the display in a manner that, when a match is found in the memory, registered speaker information corresponding to the matched registered speech feature information is displayed on said display.