System and method of transmitting speech at low line rates

• US 6,219,641 B1
• Filed: 12/09/1997
• Issued: 04/17/2001
• Est. Priority Date: 12/09/1997
• Status: Expired due to Term

• Current Assignee: Empirix Incorporated (Empirix Holdings I, Inc.)
• Original Assignee: Michael V. Socaciu
• Inventors: Socaciu, Michael V.
• Primary Examiner(s): Hudspeth, David
• Assistant Examiner(s): Chawan, Vijay B
• Application Number:
  US08/987,412
• Time in Patent Office: 1,225 Days
• Field of Search: 704/229, 704/235, 704/254, 704/251, 704/201, 704/260
• US Class Current: 704/251
• CPC Class Codes: G10L 19/0018 Speech coding using phonetic or linguistical decoding of the source; Reconstruction using text-to-speech synthesis

Abstract

A method of transmitting spoken words including a speech recognition engine in a computer system, the speech recognition engine having a data dictionary containing a number of words associated with a corresponding number of codes, receiving a word in a microphone system of the computer system, recognizing the word, checking the word in the data dictionary for an associated code, assigning the word the associated code, determining whether another word has been received, repeating the steps of recognizing, checking, assigning, and determining the end of speech, packing the associated codes into a first sequence; and transmitting the first sequence via a communication link attached to the computer system. As an enhancement, translating the phrases before encoding them provides automatic language translation. At receiving side, decomposing the received sequence of codes, transforming the sequence of codes into text words and reproducing the text into the original or the translated speech through a text to speech engine.

Claims

1. A method of transmitting a plurality of codes associated with individual words of speech comprising:

providing a speech recognition engine in a computer system, the speech recognition engine having a data dictionary containing a plurality of words associated with a corresponding plurality of codes;

receiving a word of speech in a microphone system of the computer system;

recognizing the word of speech;

checking the word of speech in the data dictionary for an associated code;

assigning the word of speech the associated code;

determining whether another word of speech has been received;

repeating the steps of recognizing, checking, assigning, and determining the presence of new input words of speech; and

transmitting the plurality of associated codes via a communication link attached to the computer system.

2. The method of transmitting a plurality of codes associated with individual words of speech according to claim 1 wherein the associated code is log(base 2) N bits long where N is equal to the number of words in the data dictionary.

3. A speech transmission system comprising:

a computer system, the computer system comprising;

a microphone system;

a speech recognition engine, the speech recognition engine having a data dictionary containing a plurality of words of speech,

a speech translation engine, the speech translation engine outputting a plurality of word phrases corresponding to the plurality of words of speech recognized in the speech recognition engine;

a coding unit, the coding unit assigning a plurality of codes to the plurality of word phrases which represent speech; and

a communications line, the communications line providing connection to a plurality of additional systems, the communications line used to transmit the assigned plurality of codes.

4. The system according to claim 3 wherein the speech translation engine includes a dictionary containing a plurality of foreign language translation codes.

5. An efficient high speed speech transmission system comprising:

a microphone, said microphone receiving a plurality of spoken words of speech;

a first computer system, said microphone adapted to said first computer system, said first computer system further comprising;

a speech recognition engine, said speech recognition engine identifying the plurality of spoken words of speech received by said microphone;

a coding unit connected to said speech recognition engine, said coding unit having a mapping function to map one of a unique plurality of codes to each of the plurality of spoken words;

a transmission line, said transmission line connected to the coding unit and providing transmission of each of the unique plurality of codes to a second computer system.

6. The efficient high speed speech transmission system according to claim 5 wherein the second computer system comprises:

a decoding unit, the decoding unit converting each of the unique plurality of codes to an associated plurality of words of speech;

a speech recognition unit for receipt of each of the associated plurality of words of speech;

a speaker subsystem, said speaker subsystem receiving and outputting the associated plurality of words of speech.