Real-time speech processing development system

• US 5,036,539 A
• Filed: 07/06/1989
• Issued: 07/30/1991
• Est. Priority Date: 07/06/1989
• Status: Expired due to Term

• Current Assignee: ITT Corporation (ITT, Inc.)
• Original Assignee: ITT Corporation (ITT, Inc.)
• Inventors: Wrench, Edwin H. Jr., Higgins, Alan L.
• Primary Examiner(s): Harkcom, Gary V.
• Assistant Examiner(s): Doerrler, Michelle
• Application Number:
  US07/376,076
• Time in Patent Office: 754 Days
• Field of Search: 381/41-46, 364/513.5
• US Class Current: 704/246
• CPC Class Codes: G06F 3/16 Sound input; Sound output speech processing G10L
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques

Abstract

A real-time speech processing development system has a control subsystem (CS) and a recognition subsystem (RS) interconnected by a CS/RS interface. The control subsystem includes a control processor, an operator interface, a user interface, and a control program module for loading any one of a plurality of control programs which employ speech recognition processes. The recognition system RS includes a master processor, speech signal processor, and template matching processors all interconnected on a common bus which communicates with the control subsystem through the mediation of the CS/RS interface. The two-part configuration allows the control subsystem to be accessed by the operator for non-real-time system functions, and the recognition subsystem to be accessed by the user for real-time speech processing functions. An embodiment of a speaker verification system includes template enrollment, template training, recognition by template-concatenation and time alignment, silence and filler template generation, and speaker monitoring modes.

Claims

1. A real-time speech processing development system comprising:

(a) a speech recognition subsystem including a master processor, a template matching processor, a speech signal processor, and speech signal input means coupled to said speech signal processor, wherein said master processor is configured to receive internal subsystem operation commands for performing speech recognition and to thereupon generate subsystem execution commands for real-time operation of said speech signal processor to process speech signals received from a user through said speech signal input means into corresponding digital representations, and of said template matching processor to compare the digital representations provided by said speech signal processor with stored templates of word or sound units and to produce a real-time speech recognition output based thereon;

(b) a control subsystem including an operator interface for control communications with a system operator, a user interface for control communications with a user, a control program module, a database storage used by said control subsystem for storing data files for said speech processing development system, and a control processor connected to said operator interface, said user interface, and said control program module, wherein said control processor is configured to receive operator control input through said operator interface and to access said control program module to load one of plurality of control programs selected by the operator, including a speech recognition control program, and wherein said control processor is further configured to operate said user interface, when the speech recognition control program is selected by the operator, for control communications with the user, and to execute said speech recognition control program so as to generate the internal subsystem operation commands for performing speech recognition provided to said master processor of said recognition subsystem; and

(c) an interface connected between said control subsystem and said recognition system for transmitting the internal subsystem operation commands for performing speech recognition from said control processor of said control subsystem to said recognition subsystem and the real-time speech recognition output from said recognition subsystem to said user interface of said control subsystem, whereby said control subsystem can be accessed by the operator for non-real-time system development functions while said recognition subsystem can be accessed by the user for real-time speech recognition functions.

wherein said recognition subsystem includes an execution control program executed by said master processor for generating the subsystem execution commands in response to an internal subsystem operation command received from said control subsystem, and

wherein said execution control program includes a plurality of execution program modules having different programmed priority levels, and means for assigning subsystem execution commands for tasks to be executed to said modules and for activating said subsystem execution commands according to the priorities of the respective modules.

2. A real-time speech processing development system according to claim 1, wherein said control program module of said control subsystem includes a speaker enrollment program for enrolling vocabulary speech samples of a speaker into said speech processing development system using said speech recognition control program.

3. A real-time speech processing development system according to claim 1, wherein said control program module of said control subsystem includes a speaker verification program for verifying a speaker based upon stored speech samples of the speaker using said speech recognition control program.

4. A real-time speech processing development system according to claim 1, wherein said control program module of said control subsystem includes a speaker monitoring program for passively monitoring the input speech of a claimed speaker as compared to stored speech samples of an identified speaker using said speech recognition control program.

5. A real-time speech processing development system according to claim 1, wherein said recognition system includes a common bus interconnecting said master processor, template matching processor, and speech signal processor.

6. A real-time speech processing development system according to claim 5, wherein said template matching processor includes a plurality of processor units interconnected in parallel with said common bus.

7. A real-time speech processing development system according to claim 1, wherein said interface includes a transmit buffer and a receive buffer for temporarily storing communication exchanges sent or received between said control subsystem and said recognition subsystem.

8. A real-time speech processing development system according to claim 1, wherein said execution control program includes, in order of decreasing priority, a subsystem initialization module, a frame-data acceptance module for receiving a frame of speech data processed by said speech signal processor, a transmit-communications module, a receive-communications module, a compute-template-values module for computationally comparing input frames of speech data with the stored templates, and a subsystem background module.

9. A real-time speech processing development system according to claim 1, wherein said speech signal input means is a microphone input.

10. A real-time speech processing development system according to claim 1, wherein said control subsystem includes said database storage being used for storing system data files, speaker data files, and template data files.

11. A real-time speech processing development system according to claim 10, wherein said control subsystem also executes the speech recognition control program in a non-real-time mode by downloading stored speaker data files as said speech signal input means to said recognition subsystem.