Semiautomated relay method and apparatus
A method to transcribe communications includes the steps of obtaining a plurality of hypothesis transcriptions of a voice signal generated by a speech recognition system, determining consistent words that are included in at least first and second of the plurality of hypothesis transcriptions, in response to determining the consistent words, providing the consistent words to a device for presentation of the consistent words to an assisted user, and presenting the consistent words via a display screen on the device, wherein a rate of the presentation of the words on the display screen is variable.
1. A method comprising:
obtaining, at a system, a first rating of a first transcription of a voice signal from a first hearing user (HU) device during a first communication session involving an assisted user (AU) using an AU device and the first HU device, the first rating indicating feedback from the AU device regarding the first transcription and the first transcription obtained using a first transcription generation technique;
after termination of the first communication session, obtaining, at the system, at least a second rating of a second transcription of a voice signal from a second HU device during a second communication session involving the AU device and the second HU device, where the second HU device is different from the first HU device, the second rating indicating feedback from the AU device regarding the second transcription and the second transcription obtained using the first transcription generation technique;
selecting, using at least the first and second ratings, a second transcription generation technique for a third communication session involving the AU device and a third HU device that is different from the first HU device and the second HU device, the second transcription generation technique selected to generate a third transcription of a voice signal from the third HU device; and
obtaining, during the third communication session, the third transcription that is generated using the second transcription generation technique.
2. The method of claim 1 , wherein the first transcription generation technique includes an automatic speech recognition system that receives an HU voice signal and generates a transcription of the HU voice signal independent of any re-voicing by a call assistant.
3. The method of claim 2 , wherein the second transcription generation technique includes using a re-voicing speech recognition system to generate the third transcription, wherein the re-voicing speech recognition system includes an automatic speech recognition system that receives a re-voicing of the HU voice signal by a call assistant and captions the re-voiced signal to generate the third transcription.
4. The method of claim 1 , wherein the second transcription generation technique includes using a re-voicing speech recognition system to generate the third transcription, wherein the re-voicing speech recognition system includes an automatic speech recognition system that receives a re-voicing of the HU voice signal by a call assistant and captions the re-voiced signal to generate the third transcription.
5. The method of claim 1 wherein the first transcription generation technique includes using a re-voicing speech recognition system to generate the first transcription and the second transcription, wherein the re-voicing speech recognition system includes an automatic speech recognition system that receives a re-voicing of the HU voice signal by a call assistant and captions the re-voiced signal to generate the third transcription.
6. The method of claim 1 , wherein obtaining the first rating includes:
presenting a request for the first rating on the AU device after termination of the first communication session; and
obtaining the first rating from the AU device based on a response to the request.
7. The method of claim 6 , wherein obtaining the second rating includes:
presenting a second request for the second rating on the AU device after termination of the second communication session; and
obtaining the second rating from the AU device based on a response to the second request.
8. The method of claim 1 , wherein selecting the second transcription generation technique includes:
determining a number of ratings of a plurality of ratings from the AU device, which include the first rating and the second rating, that meet a poor rating threshold; and
selecting the second transcription generation technique based on the number of ratings satisfying a number threshold.
9. The method of claim 1 wherein the AU device includes a processor and wherein the first transcription generation technique includes an automatic speech recognition technique run by the AU device processor.
10. The method of claim 9 also for use with a remote relay that is independent of the AU device and the HU device and wherein the second transcription generation technique includes transcribing at the remote relay.
11. The method of claim 10 wherein the second transcription process includes a re-voicing of the third voice signal at the remote relay, wherein the re-voicing includes an automatic speech recognition system that receives a re-voicing of the third voice signal by a call assistant.
12. The method of claim 1 further including presenting the first transcription via an AU device display and presenting the second transcription via the AU device display.
13. The method of claim 12 further including presenting the third transcription via the AU device display.
14. At least one non-transitory computer-readable media configured to store one or more instructions that in response to being executed by at least one computing system cause performance of the method of claim 1 .
15. The method of claim 1 further including obtaining, at a system, at least a third rating of a fourth transcription of a voice signal from a fourth HU device during a fourth communication session involving the AU using the AU device and the fourth HU device, the third rating indicating feedback from the AU device regarding the fourth transcription and the fourth transcription obtained using the second transcription generation technique, the step of selecting including selecting, using at least the first, second and third ratings, the second transcription generation technique for the third communication session.
16. The method of claim 1 wherein each of the steps of obtaining the first rating and obtaining the second rating includes presenting a plurality of rating options via the AU device that are selectable by the AU for indicating satisfaction level of an associated transcription.
17. The method of claim 16 wherein the step of presenting a plurality of rating options includes presenting only two options including a “good” option and a “poor” option.
18. The method of claim 16 wherein the AU device includes a touch sensitive display screen, the method further including presenting the first transcription via the display screen and presenting the second transcription via the display screen, the step of presenting a plurality of rating options including presenting the rating options via the display screen, each option selectable via touch.
19. A method comprising:
at the end of each of a series of consecutive communication sessions, each involving an assisted user (AU) device and at least one hearing user (HU) device, obtaining at a system a satisfaction rating from the AU device of an associated transcription using a first transcription generation technique of an HU voice signal captured during the session;
selecting, using the satisfaction ratings, a second transcription generation technique for a next communication session involving the AU device and at least one next HU device, the second transcription generation technique selected to generate a next transcription of voice signal captured by the at least one next HU device; and
obtaining, during the next communication session, the next transcription that is generated using the second transcription generation technique.
20. The method of claim 19 , wherein the first transcription generation technique includes an automatic speech recognition system that receives an HU voice signal and generates a transcription of the HU voice signal independent of any re-voicing by a call assistant.
21. The method of claim 20 , wherein the second transcription generation technique includes using a re-voicing speech recognition system to generate the next transcription, wherein the re-voicing speech recognition system includes an automatic speech recognition system that receives a re-voicing of the HU voice signal by a call assistant and captions the re-voiced signal to generate the next transcription.
22. The method of claim 19 , wherein the second transcription generation technique includes using a re-voicing speech recognition system to generate the next transcription, wherein the re-voicing speech recognition system includes an automatic speech recognition system that receives a re-voicing of the HU voice signal by a call assistant and captions the re-voiced signal to generate the next transcription.
23. The method of claim 19 , wherein obtaining the rating includes:
presenting a request for the rating on the AU device after termination of an associated communication session; and
obtaining the rating from the AU device based on a response to the request.
24. The method of claim 19 wherein the series of communication sessions includes at least first and second communication sessions.
25. The method of claim 24 wherein the first communication session is between the AU device and a first HU device, the second communication session is between the AU device and a second HU device, and the next communication session is between the AU device and a third HU device.
26. A system comprising:
one or more processors; and
one or more computer-readable media configured to store instructions that in response to being executed by the one or more processors cause the system to perform operations, the operations comprising:
at the end of each of a series of consecutive communication sessions, each involving an assisted user (AU) device and at least one hearing user (HU) device, obtaining at a system a satisfaction rating from the AU device of an associated transcription using a first transcription generation technique of an HU voice signal captured during the session;
selecting, using the satisfaction ratings, a second transcription generation technique for a next communication session involving the AU device and at least one next HU device, the second transcription generation technique selected to generate a next transcription of voice signal captured by the at least one next HU device; and
obtaining, during the next communication session, the next transcription that is generated using the second transcription generation technique.
27. The system of claim 26 , wherein the first transcription generation technique includes an automatic speech recognition system that receives an HU voice signal and generates a transcription of the HU voice signal independent of any re-voicing by a call assistant.
28. The system of claim 27 , wherein the second transcription generation technique includes using a re-voicing speech recognition system to generate the next transcription, wherein the re-voicing speech recognition system includes an automatic speech recognition system that receives a re-voicing of the HU voice signal by a call assistant and captions the re-voiced signal to generate the next transcription.
29. The system of claim 26 , wherein the second transcription generation technique includes using a re-voicing speech recognition system to generate the next transcription, wherein the re-voicing speech recognition system includes an automatic speech recognition system that receives a re-voicing of the HU voice signal by a call assistant and captions the re-voiced signal to generate the next transcription.
30. The system of claim 26 , wherein obtaining the rating includes:
presenting a request for the rating on the AU device after termination of an associated communication session; and
obtaining the rating from the AU device based on a response to the request.
31. The system of claim 26 wherein the series of communication sessions includes at least first and second communication sessions.
32. The system of claim 31 wherein the first communication session is between the AU device and a first HU device, the second communication session is between the AU device and a second HU device, and the next communication session is between the AU device and a third HU device.