Methods and apparatus for providing speech recording and speech transcription services

• US 6,850,609 B1
• Filed: 10/23/1998
• Issued: 02/01/2005
• Est. Priority Date: 10/28/1997
• Status: Expired due to Fees

• Current Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Original Assignee: Verizon Services Corporation (Verizon Communications Inc.)
• Inventors: Schrage, James R.
• Primary Examiner(s): Tsang, Fan
• Assistant Examiner(s): PHAN, JOSEPH T
• Application Number:
  US09/178,295
• Time in Patent Office: 2,293 Days
• Field of Search: 379/88.11, 379/88.01, 379/88.26, 379/88.07, 379/88.13, 379/100.01, 379/158, 37920201-20601, 704/235, 704/231, 348/14.08, 348/14.09
• US Class Current: 379/202.01
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 2201/40 using speech recognition
• CPC Class Codes: H04M 2201/60 Medium conversion
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656
• CPC Class Codes: H04M 3/56 Arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities video conference systems H04N7/15

Abstract

Recording and automated transcription methods and apparatus suitable for use in a communication system such as a telephone system are described. In one embodiment, a telephone system has a conference bridge, a transcription system, and multiple telephone sets connected to a central office (CO) switch via communication channels. Each telephone set lets its user transmit speech on first and second channels simultaneously. The CO switch selectively connects the first channel from each telephone being used in a conference call to the conference bridge. The bridge interconnects the first channels to establish a telephone conference. The CO switch selectively connects the second channels to the transcription system, which records the teleconference participants in separate recordings. The separate recordings are each time stamped and identified with a user'"'"'s or communication unit ID. An automated speech-to-text (speech recognition) system transforms the recorded speech into textual data. A collator collates text segments generated from the speech obtained from different channels using the time stamps and the ID'"'"'s to form a master transcript of textual data. The present invention can be used by single or multiple users. A single user may use the system of the present invention as a dictation system. The system can be used for automatically generating a transcript of a multi-party telephone conference or meeting.

Claims

1. A transcription method comprising the steps of:

coupling a first audio source to an audio recording device using a first communication channel of a communications network, the first communication channel extending from the first audio source to said recording device;

coupling a second audio source to the audio recording device using a second communication channel of the communications network, the second communication channel extending from the second audio source to said recording device;

coupling the first audio source using a third communication channel to a conference bridge;

coupling the second audio source using a fourth communication channel to the conference bridge;

using the first communications channel in a uni-directional manner during a communications conference to communicate audio signals from the first audio source to said recording device;

using the second communications channel in a uni-directional manner during the communications conference to communicate audio signals from the second audio source to said recording device;

using the third communications channel in a bi-directional manner during the communications conference to communicate audio signals between said first audio source and said conference bridge;

using the fourth communications channel in a bi-directional manner during the communications conference to communicate audio signals between the second audio source and said conference bridge;

operating the recording device to generate a first audio recording of speech signals received from the first audio source;

performing a speech recognition operation on the first audio recording of speech signals to generate a first;

transcript therefrom;

delivering at least a portion of the generated first transcript; and

wherein the first and second communications channels are separate from each other such that the audio signals on the first and second channels do not mix.

2. The method of claim 1,

wherein the coupling step includes the step of using a telephone network to couple the audio source to the audio recording device.

3. The method of claim 1,

wherein the step of operating the recording device to generate a first audio recording includes the step of recording time stamp information with the audio being recorded in said first audio recording.

4. The method of claim 3, further comprising the step of:

operating the second recording device to generate a second recording of speech signals received from the second audio source;

performing a speech recognition operation on the recorded speech signals included in the second recording to generate a second transcript therefrom.

5. The method of claim 4,

wherein the step of operating the recording device to generate a second recording includes the step of recording time stamp information with the second recording.

6. The method of claim 5, further comprising the step of:

generating a composite transcript from the first and second transcripts.

7. The method of claim 6, wherein the step of generating a composite transcript includes the step of:

interleaving segments of text included in the first and second transcripts to generate the composite transcript.

8. The method of claim 7, wherein the step of interleaving segments of text is performed as a function of the recorded time stamp information.

9. The method of claim 7, wherein the step of generating a composite transcript further includes the step of:

inserting before each interleaved segment of text, an identifier indicating the source of the text.

10. The method of claim 1, wherein the first audio source is a first multi-line telephone and said second audio source is a second telephone;

wherein coupling the first audio source using a third communications channel to a conference bridge includes placing a telephone call to said conference bride from said first telephone; and

wherein coupling the first audio source using a first communication channel to the recording device includes placing a telephone call to said recording device from said first telephone.

11. The method of claim 10, further comprising the steps of:

generating a second recording of speech signals received from the second audio device;

performing a speech recognition operation on the recorded speech signals to generate a second transcript therefrom.

12. The method of claim 11, further comprising the step of:

generating a composite transcript from the first and second transcripts.

13. The method of claim 12,

wherein the step of delivering at least a portion of the generated first transcript includes the step of transmitting the composite transcript to a transcript service subscriber.

14. The method of claim 12,

wherein the step of delivering at least a portion of the generated first transcript includes the step of transmitting the composite transcript to a transcript service subscriber through the use of one of an E-mail message, an Internet communication, and a facsimile transmission.

15. The method of claim 1, wherein performing a speech recognition operation on the recorded audio speech signals includes:

performing multiple speech recognition passes on said recorded audio speech signals.

16. A method of processing audio signals, comprising the steps of:

coupling a first audio source to an audio recording device using a first communication channel, the first communication channel extending between said first audio source and said audio recording device;

coupling the first audio source to a conference bridge using a second communication channel;

coupling a second audio source to the recording device using a third communication channel, the third communication channel extending between said second audio source and said recording device;

coupling the second audio source to the conference bridge using a fourth communication channel, said first, and third communication channels being separate from each other such that audio signals on the first and third communications channels do not mix;

using the first communications channel in a bi-directional manner during a communications conference to communicate audio signals from the first audio source to said recording device;

using the second communications channel in a bi-directional manner during said communications conference communicate audio signals from the second audio source to said recording device;

using the third communications channel in a uni-directional manner during said communications conference to communicate audio signals between said first audio source and said conference bridge; and

using the fourth communications channel during said communications conference in a bi-directional manner to communicate audio signals between the second audio source and said conference bridge.

17. The method of claim 16, further comprising the step of:

operating the conference bridge to bridge the second and third communication channels.

18. The method of claim 17, further comprising the step of:

operating the recording device to generate a first recording of audio received from the first audio source an to generate a second recording of audio received from the second audio source.

19. The method of claim 18, further comprising the steps of:

generating a first transcript from the first recording using a speech recognizer; and

generating a second transcript from the second recording using the speech recognizer.

20. The method of claim 19, further comprising the step of generating a composite transcript from the first and second recordings.

21. The method of claim 18, wherein said first and second audio recordings are generated simultaneously, the method further comprising the steps of:

operating speech recognizer to sequentially process the first and second audio recordings; and

generating a transcript from the output of said speech recognizer.

22. A communication system with conferencing and transcribing services comprising:

a conference bridge;

speech transcript means having a plurality of inputs for converting speech signals received on said inputs into textual data without mixing the audio signals received on said plurality of inputs;

a plurality of paired first and second communication channels, each first communications channel serving as a bi-directional communications channel, each of said second communications channels serving as a uni-directional communications channel; and

switch means connected to said first and second communication channels for selectively connecting a number of said first communication channels to the conference bridge to thereby provide a bridged set of communications channels, and for connecting corresponding second communication channels to different inputs of said speech transcript means, said switch means connecting the second communication channels to said transcript means without mixing the audio from said second communications channels.

23. The system of claim 22, wherein said speech transcript means includes a recorder means, having a speech recording circuit for making a set of separate recordings of said speech signals transmitted on said different ones of said corresponding second communication channels in parallel.

24. The system of claim 23,

wherein said speech transcript means includes a speech-to-text system;

and

wherein said recorder means includes means for inserting into recordings time stamp information.