Real-time transcription correction system

• US 6,567,503 B2
• Filed: 02/20/2001
• Issued: 05/20/2003
• Est. Priority Date: 09/08/1997
• Status: Expired due to Term

• Current Assignee: Ultratech Incorporated (Veeco Instruments Incorporated)
• Original Assignee: Ultratech Incorporated (Veeco Instruments Incorporated)
• Inventors: Vitek, Troy D., Colwell, Kevin R., Gritner, Kurt M., Engelke, Robert M., Turner, Jayne M., Frazier, Pamela A.
• Primary Examiner(s): Hoosain, Allan
• Application Number:
  US09/789,120
• Publication Number:
  US 20010005825A1
• Time in Patent Office: 819 Days
• Field of Search: 379/52, 379/88.01, 379/88.14, 379/93.05, 379/93.09, 379/93.15, 379/93.18, 379/93.27, 379/100.09, 379/88.16
• US Class Current: 379/52
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 1/271 controlled by voice recognition
• CPC Class Codes: H04M 1/724 User interfaces specially adapted for cordless or mobile telephones
• CPC Class Codes: H04M 11/066 Telephone sets adapted for data transmision
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2201/60 Medium conversion
• CPC Class Codes: H04M 3/42391 where the subscribers are hearing-impaired persons, e.g. telephone devices for the deaf

Abstract

An editing system for real-time remote transcription, such as may be used by deaf or hearing impaired individuals, displays transcribed text on a screen prior to transmission so that a human call assistant may identify words being held in a buffer by their spatial location on the screen to initiate a correction of those words either through speech or text entry.

Claims

1. An editing system for voice transcription comprising:

an input circuit receiving a voice signal including at least one spoken word from a remote source;

a speech engine generating input text corresponding to the voice signal, the input text including a text word corresponding to the spoken word;

a memory receiving the input text to store the same;

a display device viewable by a call assistant having a screen area displaying the input text stored in the memory in ordered locations over the screen area;

a word selection circuit providing for call assistant selection of at least one location on the screen corresponding to the text word;

an edit text input circuit receiving a replacement text word from the call assistant and replacing the text word in the memory associated with the selected location with the replacement text; and

output circuit transmitting the replacement text word stored in the memory to a remote user after a predetermined first delay.

2. The editing system of claim 1 wherein the display device operates to cease displaying the edited input text after at least a predetermined second delay after it has been transmitted by the output circuit.

3. The editing system of claim 1 wherein the display device displays the input text in lines ceases displaying entire lines after it has been transmitted by the output circuit whereby the remaining lines may be scrolled without horizontal displacement.

4. The editing system of claim 1 wherein the output circuit includes at least one input controlling the predetermined first delay according to a factor selected from the group consisting of:

skill of the call assistant, an absolute transcription error rate, a preferred transcription error rate of the remote user, a preferred reception speed by the remote user, a location of the replacement text word within a unit of the input text.

5. The editing system of claim 4 wherein the first delay is adjusted downward when the replacement text is at the beginning of a unit of input text.

6. The editing system of claim 4 wherein the input circuit receives a data signal from the remote user indicating at least one of the preferred transcription error rates of the remote user and the preferred reception speed of the remote user.

7. The editing system of claim 1 wherein the word selection circuit is selected from the group consisting of a touch screen circuit associated with the display, a cursor control device controlling a cursor visually represented on the display.

8. The editing system of claim 1 wherein the input circuit includes a microphone and an audio output device, and wherein the voice signal is output to the call assistant by the audio output device whereby the call assistant may repeat the output voice signal into the microphone for transmission to the speech engine.

9. The editing system of claim 1 wherein the output circuit also transmits the voice signal to the remote user.

10. The editing system of claim 1 wherein the output circuit transmits the voice signal a third predetermined delay after it is received by the input circuit.

11. The editing system of claim 1 wherein the input circuit further receives a second voice signal from the remote user and wherein the audio output device provides the second voice signal to the call assistant with modified audio qualities to distinguish it from the first voice signal.

12. The editing system of claim 1 wherein the edit text input circuit includes a connection selected from the group consisting of a keyboard, a speech engine, and a display screen menu.

13. The editing system of claim 1 wherein the input circuit, the speech engine, the memory, the display device, the word selection circuit, the edit text input circuit, and the output circuit are implemented at least in part by a program executed on at least one electronic computer.

14. The editing system of claim 1 wherein the input circuit further includes a recording device recording the voice signal and having playback of the voice signal controllable by the call assistant to buffer the voice signal.

15. The editing system of claim 14 including a foot pedal and wherein the playback of the recording device is controlled by the foot pedal.

16. The editing system of claim 14 wherein the word selection circuit and edit text input circuit communicates with the recording device to cause a ceasing of playback of the recording device when the word selection circuit is activated prior to a replacement text being entered into the edit text input circuit.

17. The editing system of claim 14 wherein the display device further includes an indication of the amount of voice signal buffered by the recording device between a recording and playback point.

18. The editing system of claim 14 wherein the recording device further includes a silence compression circuit operating on the recorded voice signal prior to playback to reduce the length of silences in the voice signal.

19. The editing system of claim 18 wherein the silence compression circuit reduces the length of silences as a function of the duration of the voice signal buffered by the recording device.

20. The editing system of claim 19 wherein the silence compression circuit detects silence as any voice signal beneath a predetermined squelch level for a predetermined continuous period and replaces the detected silence with a predetermined silence replacement time.

21. The editing system of claim 1 wherein the input and output circuits communicate with at least one of the remote source and remote users through media selected from the group consisting of voice grade telephone lines, high speed data lines, and radio.

22. The editing system of claim 1 further including an auxiliary text input circuit activated by the call assistant to insert predefined text into the memory.

23. The editing system of claim 22 wherein the predefined text strings are selected from the group consisting of call progress text, conversation text, and initial word text.

24. The editing system of claim 23 wherein the initial words macros are selected from the group consisting of:

“

okay”

, “

but”

, “

hello”

, “

oh”

, “

yes”

, “

um”

, “

so”

, “

well”

, “

no”

, and “

bye”

.

25. The editing system of claim 22 wherein the auxiliary text input circuit is activated via virtual buttons on the display device.

26. The editing system of claim 1 further including an auxiliary number input circuit activated by the call assistant to cause the transmission of call assistant selected DTMF tones to the remote user by the output circuit.

27. A method of transcribing voice comprising:

(a) receiving a voice signal from a first user including at least one spoken word;

(b) generating input text corresponding to the voice signal using a speech engine, the input text including a text word corresponding to the spoken word;

(c) storing the input text in a memory;

(d) displaying on a display device viewable by a call assistant and having a screen area, the input text stored in the memory in ordered spatial locations over the screen area;

(e) selecting by a call assistant using a word selection circuit, at least one location on the screen corresponding to the text work;

(f) via an edit text input circuit receiving a replacement text word from the call assistant and replacing the text word in the memory associated with the selected location with the replacement text; and

(e) transmitting via an output circuit the replacement text word stored in the memory to a remote user after a predetermined first delay.

28. The method of claim 27 wherein the remote user is in the same location as the first user.

29. The method of claim 27 wherein the remote user is in a different location that the first user.

30. A voice transcription system comprising:

an input circuit receiving a voice signal including at least one spoken word from a remote source and providing the spoken word to a call assistant;

a keyboard operable by a call assistant providing for the input of text by the call assistant corresponding to the voice signal, the input text including a text word corresponding to the spoken word;

output circuit transmitting the input text to a remote user;

wherein the input circuit further includes a recording device recording the voice signal and having playback of the voice signal controllable by the call assistant to buffer the voice signal;

wherein the recording device further includes a silence compression circuit operating on the recorded voice signal prior to playback to reduce the length of silences in the voice signal.

31. The voice transcription system of claim 30 including a foot pedal and wherein the playback of the recording device is controlled by the foot pedal.

32. The voice transcription system of claim 30 further including a display device providing an indication of the amount of voice signal buffered by the recording device between a recording and playback point.

33. The voice transcription system of claim 30 wherein the silence compression circuit reduces the length of silences as a function of the duration of the voice signal buffered by the recording device.

34. The voice transcription system of claim 33 wherein the silence compression circuit detects silence as any voice signal beneath a predetermined squelch level for a predetermined continuous period and replaces the detected silence with a predetermined silence replacement time.