Apparatus and method for speech-text-transmit communication over data networks

• US 6,173,250 B1
• Filed: 06/03/1998
• Issued: 01/09/2001
• Est. Priority Date: 06/03/1998
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Corporation (AT&T, Inc.)
• Inventors: Jong, Kenneth
• Primary Examiner(s): Hudspeth, David R.
• Assistant Examiner(s): Lerner, Martin
• Application Number:
  US09/089,855
• Time in Patent Office: 951 Days
• Field of Search: 704/201, 704/221, 704/235, 704/260, 704/270, 704/500, 704/501, 704/249, 704/258, 704/272, 704/2, 704/3, 704/4, 379/88.05, 379/88.06, 379/88.16, 379/88.18
• US Class Current: 704/3
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 2201/60 Medium conversion
• CPC Class Codes: H04M 7/0045 where the text-based messaging service is an instant messaging service
• CPC Class Codes: H04M 7/12 for working between exchanges having different types of switching equipment, e.g. power-driven and step by step or decimal and non-decimal

Abstract

An apparatus and method for speech-text-transmit communication over data networks includes speech recognition devices and text to speech conversion devices that translate speech signals input to the terminal into text and text data received from a data network into speech output signals. The speech input signals are translated into text based on phonemes obtained from a spectral analysis of the speech input signals. The text data is transmitted to a receiving party over the data network as a plurality of text data packets such that a continuous stream of text data is obtained. The receiving party'"'"'s terminal receives the text data and may immediately display the text data and/or translate it into speech output signals using the text to speech conversion device. The text to speech conversion device uses speech pattern data stored in a speech pattern database for synthesizing a human voice for playing of the speech output signals using a speech output device.

Claims

1. A method of providing communication between a first party using a first communication device and a second party using a second communication device over a network, comprising:

generating a first textual representation by the first party using the first communication device;

sending the first textual representation over the network to the second communication device;

selecting a first speech pattern by the second party for converting the first textual representation into first speech output signals; and

converting the first textual representation into first speech output signals using the first selected speech pattern.

2. The method of claim 1, wherein the first selected speech pattern is selected from a plurality of speech patterns of different types of speakers stored in the second communication device.

3. The method of claim 1, wherein generating the first textual representation includes:

receiving, in the first communication device, first speech input from the first party; and

converting the first speech input into the first textual representation.

4. The method of claim 3, further comprising:

receiving, by the first party, a second textual representation sent from the second party over the network; and

converting the second textual representation into second speech output signals.

5. The method of claim 4, wherein communication between the first party and the second party is substantially continuous realtime communication.

6. The method of claim 4, further comprising storing at least one of the first textual representation and the second textual representation in a storage device for subsequent retrieval.

7. The method of claim 4, wherein the step of converting the second textual representation includes determining a second speech pattern to use for outputting the second speech output signals.

8. The method of claim 3, wherein the step of converting the first speech input signals includes determining phonemes included in the first speech input signals and converting the phonemes into at least one of textual words and textual codes.

9. The method of claim 3, wherein the step of converting the first speech input signals includes determining textual words included in the first speech input signals and arranging the textual words into textual sentences using grammar and semantic information for a first language.

10. The method of claim 9, wherein the step of converting the first speech input signals further includes translating the textual words of the first language into textual words of a second language.

11. The method of claim 9, wherein communication between the first party and the second part is substantially continuous realtime communication.

12. The method of claim 1, wherein selecting a speech pattern further comprises, prior to the first speech pattern being selected by the second party, determining if another speech pattern has been designated by the first party, and if the first party has not designated another speech pattern, then selecting the first speech pattern selected by the second party.

13. A communication apparatus that provides communication between a first party and a second party over a network, comprising:

an incoming text buffer that receives a first textual representation from the first party over the network;

a text-to-speech conversion device that converts the first textual representation into first speech output signals, wherein the text-to-speech conversion device uses a first speech pattern for outputting the first speech output signals, and wherein the first speech pattern is selected by the second party; and

a speech output device that outputs the first speech output signals.

14. The communication apparatus of claim 13, wherein the first speech pattern is selected from a plurality of speech patterns stored in the communication apparatus.

15. The communication apparatus of claim 13, further comprising:

a speech input device that receives speech input from the second party and converts the speech input into speech input signals;

a speech-to-text device that converts the speech input signals into a second textual representation of the speech input signals; and

a communications interface that sends the second textual representation over the network to the first party.

16. The communication apparatus of claim 15, further comprising a storage device for storing at least one of the first textual representation and the second textual representation for subsequent retrieval.

17. The communication apparatus of claim 15, wherein the communication apparatus provides substantially continuous realtime communication between the first party and the second party.

18. The communication apparatus of claim 15, wherein the speech-to-text device determines phonemes included in the speech input signals and converts the phonemes into at least one of textual words and textual codes.

19. The communication apparatus of claim 15, wherein the speech-to-text device determines the textual words included in the speech input signals and arranges the textual words into textual sentences using grammar and semantic information for a first language.

20. The communication apparatus of claim 19, wherein the speech-to-text device translates the textual words of the first language into textual words of a second language.