Semiautomated relay method and apparatus

Patent metadata

Field	Value
Publication number	US-2020404097-A1
Application number	US-201916537196-A
Country	US
Kind code	A1
Filing date	Aug 9, 2019
Priority date	Feb 28, 2014
Publication date	Dec 24, 2020
Grant date	—

Abstract

A method and system to transcribe communications the method comprising the steps of obtaining an audio message originating at a first device during a voice communication session between the first device and a second device, providing the audio message to a first speech recognition system to generate a first transcript of the audio message, directing the first transcript to the second device, in response to obtaining an indication that indicates a quality of the first transcript is below a quality threshold, using a second speech recognition system to generate a second transcript based on the audio message while continuing to provide the audio data to the first speech recognition system to generate the first transcript and, in response to occurrence of an event that indicates the second transcript is to be directed to the second device, directing the second transcript to the second device instead of directing the first transcript.

First claim

1 . A method to transcribe communications, the method comprising:
obtaining an audio message originating at a first device during a voice communication session between the first device and a second device; providing the audio message to a first automated speech recognition system that works independent of human interaction to generate a first transcript of the audio message; directing the first transcript to the second device; in response to obtaining an indication that indicates a quality of the first transcript is below a quality threshold and while continuing to provide the audio message to the first automated speech recognition system to generate the first transcript, the method including: providing the audio message to a second speech recognition system; broadcasting, by the second speech recognition system, audio based on the audio message to a call assistant; obtaining, by the second speech recognition system, a second audio message based on a re-voicing of the broadcast audio; and generating, by the second speech recognition system a second transcript using the second audio message; and in response to occurrence of an event, directing the second transcript to the second device instead of directing the first transcript to the second device and ceasing providing the audio message to the first automated speech recognition system.

2 . The method of claim 1 further comprising:
obtaining a confidence score of the first transcript from the first automated speech recognition system; and
using the confidence score to assess transcription accuracy and generate the indication that indicates quality.

3 . The method of claim 1 wherein the indication that indicates quality is obtained from the second device.

4 . The method of claim 1 wherein the event includes the second transcript including at least one captioned word based on the second audio message.

5 . At least one memory device storing at least one software program including instructions that when executed by at least one processor cause or direct a system to perform the method of claim 1 .

6 . A method to transcribe communications, the method comprising:
obtaining an audio message originating at a first device during a voice communication session between the first device and a second device; providing the audio message to a first speech recognition system to generate a first transcript of the audio message; directing the first transcript to the second device; in response to obtaining an indication that indicates a quality of the first transcript is below a quality threshold, providing the audio message to a second speech recognition system to generate a second transcript based on the audio message while continuing to provide the audio message to the first speech recognition system to generate the first transcript and continuing to direct the first transcript to the second device; and in response to occurrence of an event that indicates the second transcript is to be directed to the second device instead of the first transcript, directing the second transcript to the second device instead of directing the first transcript.

7 . The method of claim 6 wherein the first speech recognition system and the second speech recognition system are automated speech recognition systems that work independent of human interaction.

8 . The method of claim 6 wherein the first speech recognition system is an automated speech recognition system that works independent of human interaction and the generation of the second transcript by the second speech recognition system includes:
(i) broadcasting the audio message; and
(ii) obtaining a second audio message based on a re-voicing of the broadcast audio message, wherein the second transcript is generated based on the second audio message.

9 . The method of claim 6 further comprising obtaining a confidence score of the first transcript from the first speech recognition system and obtaining the indication of quality based on a comparison of the confidence score to the quality threshold.

10 . The method of claim 6 wherein the quality indication is obtained from the second device.

11 . The method of claim 6 wherein the event includes the second transcript including at least one captioned word based on the audio message.

12 . The method of claim 6 further including, in response to the event, ceasing providing the audio message to the first speech recognition system.

13 . The method of claim 6 wherein the event includes passage of a short delay.

14 . A system to transcribe communications, the system comprising:
at least one processor; and at least one memory device linked to the processor and storing at least one software program including instructions that when executed by at least one processor cause or direct a system to perform operations comprising: obtaining an audio message originating at a first device during a voice communication session between the first device and a second device; providing the audio message to a first automated speech recognition system to generate a first transcript of the audio message; directing the first transcription to the second device; in response to obtaining an indication that indicates a quality of the first transcript is below a quality threshold, provide the audio message to a second speech recognition system to generate a second transcript based on the audio message while continuing to provide the audio message to the first speech recognition system to generate the first transcript and continuing to direct the first transcript to the second device; and in response to an event that indicates the second transcript is to be directed to the second device instead of the first transcript where the event occurs after the audio message is provided to the second speech recognition system, direct the second transcript to the second device instead of the first transcript.

15 . The system of claim 14 , wherein the first speech recognition system and the second speech recognition system are automated speech recognition systems that work independent of human interaction.

16 . The system of claim 14 , wherein the first speech recognition system is an automated speech recognition system that works independent of human interaction and the generation of the second transcript by the second speech recognition system includes operations comprising:
broadcast audio based on the audio message; and obtain a second audio message based on a re-voicing of the broadcast audio, wherein the second transcript is generated based on the second audio message.

17 . The system of claim 14 , wherein the operations further comprise:
obtaining a confidence score of the first transcript from the first speech recognition system; and obtaining the quality indication based on a comparison of the confidence score to the quality threshold.

18 . The system of claim 14 , wherein the quality indication is obtained from the second device.

19 . The system of claim 14 wherein the event includes the second transcript including at least one captioned word based on the audio message.

20 . The system of claim 14 , wherein the operations further comprise in response to occurrence of the event, ceasing providing the audio message to the first speech recognition system.

21 . The method of claim 6 wherein the second device includes an input device for indicating that a user of the second device desires a call assistant to assist in transcription, the method generating

Assignees

• Ultratec Inc

Inventors

• Engelke Robert M
• Colwell Kevin R
• Engelke Christopher

Classifications

• H04W4/06

  Selective distribution of broadcast services, e.g. multimedia broadcast multicast service [MBMS]; Services to user groups; One-way selective calling services · CPC title

• G10L25/48

  specially adapted for particular use · CPC title

• H04M1/72478

  for hearing-impaired users · CPC title

• G10L15/26

  Speech to text systems (G10L15/08 takes precedence) · CPC title

• H04M2201/18

  Comparators · CPC title