Remote server object architecture for speech recognition

• US 7,120,585 B2
• Filed: 03/23/2001
• Issued: 10/10/2006
• Est. Priority Date: 03/24/2000
• Status: Expired due to Term

• Current Assignee: Eliza Corporation (Gainwell Technologies)
• Original Assignee: Eliza Corporation (Gainwell Technologies)
• Inventors: Boulanov, Oleg
• Primary Examiner(s): Hudspeth, David
• Assistant Examiner(s): ALBERTALLI, BRIAN LOUIS
• Application Number:
  US09/815,808
• Publication Number:
  US 20010037197A1
• Time in Patent Office: 2,027 Days
• Field of Search: 704/270.1, 704/257, 704/231, 709/223, 709/224
• US Class Current: 704/270.1
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/14 using statistical models, e.g. Hidden Markov Models [HMMs] G10L15/18 takes precedence
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/193 Formal grammars, e.g. finite state automata, context free grammars or word networks
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/025 Phonemes, fenemes or fenones being the recognition units

Abstract

A speech recognition system includes a line of service including a first server object coupled to a telephone network for receiving a voice data message from the telephone network, a second server object having a first connection to the first server object for receiving the voice data message from the first server object and converting the voice data message to a phonetic data message, a third server object having a second connection to the second server object for receiving the phonetic data message from the second server object and converting the phonetic data message to a syntactic data message and a fourth server object having a third connection to the third server object for receiving the syntactic data message from the third server object and converting the syntactic data message to a semantic data message, which is representative of the voice data message. The first, second, third and fourth server objects may be remote with respect to each other and the first, second and third connections are formed over a first computer network.

Claims

1. A speech recognition system comprising:

a line of service including;

a first server object coupled to a telephone network for receiving a voice data message from said telephone network;

a second server object having a first connection to said first server object for receiving said voice data message from said first server object and converting said voice data message to a phonetic data message;

a third server object having a second connection to said second server object for receiving said phonetic data message from said second server object and converting said phonetic data message to a syntactic data message;

a fourth server object having a third connection to said third server object for receiving said syntactic data message from said third server object and converting said syntactic data message to a semantic data message that includes a plurality of possible valid interpretations of said voice data message; and

a control monitor for controlling the configuration of said first, second, third and fourth server objects in said line of service;

wherein said first, second and third connections are formed over a first computer network.

2. The system of claim 1 wherein said fourth server object is coupled to a second computer network for receiving an application code from a client of said second computer network, said application code providing control data for the operation of said speech recognition system.

3. The system of claim 1 wherein said first computer network is one of a local area network and the internet.

4. The system of claim 2 wherein said second computer network is one of a local area network and the internet.

5. The system of claim 4 wherein said first, second and third connections are formed from named pipes.

6. The system of claim 1 wherein at least one of said first, second, third and fourth server objects periodically transmits a status signal to said system monitor, wherein the transmission of said periodic status signal from said at least one of said first, second, third and fourth server objects to said system monitor indicates that said one of said first, second, third and fourth server objects is operational.

7. The system of claim 6 wherein a nontransmission of said periodic status signal from said at least one of said first, second, third and fourth server objects to said system monitor indicates that said one of said first, second, third and fourth server objects is disabled.

8. The system of claim 1 further comprising at least one backup server object which is configured into the system by the system monitor when said at least one of said first, second, third and fourth server objects is disabled.

9. The system of claim 1 wherein said first, second, third and fourth server objects are configured by said system monitor according to the Distributed Component Object Model (DCOM).

10. The system of claim 9 wherein each of said first, second, third and fourth server objects include a post office for addressing and routing said voice data message, said phonetic data message, said syntactic data message and said semantic data message through said line of service from said telephone network to said second computer network.

11. The system of claim 9 further comprising additional lines of service connected between said telephone network and said second computer network.

12. The system of claim 1 wherein said first, second, third and fourth server objects are remote with respect to each other.

13. A method of processing speech comprising:

(A) receiving, at a first server object, a voice data message from a telephone network;

(B) transmitting said voice data message over a first computer network to a second server object;

(C) converting said voice data message to phonetic data message in said second server object;

(D) transmitting said phonetic data message from said second server object to a third server object over said first computer network;

(E) converting said phonetic data message to a syntactic data message in said third server object;

(F) transmitting said syntactic data message from said third server object to a fourth server object over said first computer network; and

(G) converting, in said fourth server object, said syntactic data message to a semantic data message that includes a plurality of possible valid interpretations of said voice data message.

14. The method of claim 13 further comprising downloading an application code from a second computer networks wherein said application code includes control code for controlling operation of said first, second, third and fourth server objects.

15. The method of claim 14 wherein said first computer network is one of a local area network and the internet.

16. The method of claim 15 wherein said second computer network is one of a local area network and the internet.

17. The method of claim 16 wherein steps B, D and F comprise transmitting said voice data message, said phonetic data message and said syntactic data message, respectively, over named pipes.

18. The method of claim 16 further comprising configuring said first, second, third and fourth server objects with a control monitor.

19. The method of claim 18 further comprising the step of at least one of said first, second, third and fourth server objects transmitting a status signal to said control monitor, wherein the transmission of said periodic status signal from said at least one of said first, second, third and fourth server objects to said control monitor indicates that said at least of said first, second, third and fourth server objects is operational.

20. The method of claim 19 wherein the nontransmission of said periodic status signal from said at least one of said first, second, third and fourth server objects to said control monitor indicates that said at least of said first, second, third and fourth server objects is disabled.

21. The method of claim 16 wherein said first, second, third and fourth server objects are configured by said system monitor according to the Distributed Component Object Model (DCOM).

22. The method of claim 16 further comprising processing said semantic data message in said fourth server object according to said application code.

23. A speech recognition system comprising:

a line of service including;

a voice server object coupled to a telephone network for receiving a voice data message from said telephone network;

a speech recognition server having a connection to said voice server object for receiving said voice data message from said voice server object and converting said voice data message to a phonetic data message and converting said phonetic data message to a syntactic data message;

a task server object having a connection to said speech recognition server 6 receiving said syntactic data message from said speech recognition server object and convering said syntactic data message to a semantic data message that includes a plurality of possible valid interpretations of said voice data message; and

a control monitor for controlling the configuration of said voice server object,

said speech recognition server and said task server object in said line of service;

wherein said connections between said voice server object, said speech recognition server, said task server object and said control monitor are formed over a first computer network.

24. The system of claim 23 wherein said task server object is coupled to a second computer network for receiving an application code from a client of said second computer network, said application code providing control data for the operation of said speech recognition system.

25. The system of claim 24 wherein said second computer network is one of a local area network and the internet.

26. The system of claim 25 wherein said connections are formed from named pipes.

27. The system of claim 23 wherein said first computer network is one of a local area network and the internet.

28. The system of claim 23 wherein at least one of said voice server object, said speech recognition server and said task server object periodically transmits a status signal to said system monitor, wherein the transmission of said periodic status signal from said at least one of said first, second, third and fourth server objects to said system monitor indicates that said one of said first, second, third and fourth server objects is operational.

29. The system of claim 28 wherein a nontransmission of said periodic status signal from said at least one of said voice server object, said speech recognition server and said task server object to said system monitor indicates that said at least one of said voice server object, said speech recognition server and said task server object is disabled.

30. The system of claim 23 further comprising at least one backup saver object which is configured into the system by the system monitor when said at least one of said voice server object, said speech recognition server and said task server object is disabled.

31. The system of claim 23 wherein said voice server object, said speech recognition server and said task server object are configured by said system monitor according to the Distributed Component Object Model (DCOM).

32. The system of claim 31 wherein each of said voice server object, said speech recognition server and said task server object include a post office for addressing and routing said voice data message, said phonetic data message, said syntactic data message and said semantic data message through said line of service from said telephone network to said second computer network.

33. The system of claim 31 further comprising additional lines of service connected between said telephone network and said second computer network.

34. The system of claim 23 wherein said speech recognition server comprises (1) an acoustic server object for receiving said voice data message from said voice saver object and converting said voice data message to said phonetic data message and (2) a symbolic server object for receiving said phonetic data message from said acoustic server object and converting said phonetic data message to said syntactic data message.

35. The system of claim 34 wherein said voice, acoustic, symbolic and task server objects are remote with respect to each other.

36. The system of claim 23 wherein said voice server object, said speech recognition server and said task server object are remote with respect to each other.