CONTINUOUS SPEECH TRANSCRIPTION PERFORMANCE INDICATION

• US 20090055175A1
• Filed: 08/22/2008
• Published: 02/26/2009
• Est. Priority Date: 08/22/2007
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Canyon IP Holdings LLC (Intellectual Ventures LLC)
• Inventors: White, Marc, Jablokov, Igor Roditis, Terrell, James Richard II
• Granted Patent: US 8,510,109 B2
• Time in Patent Office: Days
• US Class Current: 704/235
• CPC Class Codes: G10L 15/01 Assessment or evaluation of speech recognition systems
• 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: G10L 2015/221 Announcement of recognition results

Abstract

A method of providing speech transcription performance indication includes receiving, at a user device data representing text transcribed from an audio stream by an ASR system, and data representing a metric associated with the audio stream; displaying, via the user device, said text; and via the user device, providing, in user-perceptible form, an indicator of said metric. Another method includes displaying, by a user device, text transcribed from an audio stream by an ASR system; and via the user device, providing, in user-perceptible form, an indicator of a level of background noise of the audio stream. Another method includes receiving data representing an audio stream; converting said data representing an audio stream to text via an ASR system; determining a metric associated with the audio stream; transmitting data representing said text to a user device; and transmitting data representing said metric to the user device.

Claims

1. A method of providing speech transcription performance indication, comprising:

(a) displaying, by a user device, text transcribed from an audio stream by an ASR system; and

(b) via the user device, providing, in user-perceptible form, an indicator of a level of background noise of the audio stream.

2. The method of claim 1, further comprising the step of:

(c) before the displaying step, receiving, by the user device, the transcribed text from the ASR system.

3. A method of providing speech transcription performance indication, comprising:

(a) receiving, at a user device

(i) data representing text transcribed from an audio stream by an ASR system, and

(ii) data representing a metric associated with the audio stream;

(b) displaying, via the user device, said text; and

(c) via the user device, providing, in user-perceptible form, an indicator of said metric.

4. The method of claim 3, wherein said transcribed text was converted at a server from data representing said audio stream transmitted to the server from a transmitting device

5. The method of claim 4, wherein said transcribed text was confirmed by a user of said transmitting device prior to said receiving step.

6. The method of claim 3, wherein said transcribed text was confirmed prior to said receiving step.

7. The method of claim 3, wherein said text comprises a word and said metric is a metric of said word.

8. The method of claim 3, wherein said text comprises a plurality of words and said metric is one of a plurality of metrics represented by data received at the user device and provided via the user device, each of said plurality of metrics being a metric of a distinct one of said plurality of words.

9. The method of claim 3, wherein said text comprises a syllable and said metric is a metric of said syllable.

10. The method of claim 3, wherein said text comprises a plurality of syllables and said metric is one of a plurality of metrics represented by data received at the user device and provided via the user device, each of said plurality of metrics being a metric of a distinct one of said plurality of syllables.

11. The method of claim 3, wherein said text comprises a phrase and said metric is a metric of said phrase.

12. The method of claim 3, wherein said text comprises a plurality of phrases and said metric is one of a plurality of metrics represented by data received at the user device and provided via the user device, each of said plurality of metrics being a metric of a distinct one of said plurality of phrases.

13. The method of claim 3, wherein said text comprises a sentence and said metric is a metric of said sentence.

14. The method of claim 3, wherein said text comprises a plurality of sentences and said metric is one of a plurality of metrics represented by data received at the user device and provided via the user device, each of said plurality of metrics being a metric of a distinct one of said plurality of sentences.

15. The method of claim 3, wherein said text comprises a plurality of units and said metric is one of a plurality of metrics represented by data received at the user device and provided via the user device, each of said plurality of metrics being a metric of one of said plurality of units, and each of said units being either a word, a sentence, a phrase, or a syllable.

16. The method of claim 3, wherein said user device is a mobile phone.

17. The method of claim 16, wherein said data representing transcribed text and said data representing said metric are received in the same manner as data representing a text message.

18. The method of claim 16, wherein said text is displayed as a text message.

19. The method of claim 3, wherein said user device is a computer.

20. The method of claim 19, wherein said data representing transcribed text and said data representing said metric are received in the same manner as data representing an instant message.

21. The method of claim 19, wherein said text is displayed as an instant message.

22. The method of claim 19, wherein said data representing transcribed text and said data representing said metric are received in the same manner as data representing an email.

23. The method of claim 19, wherein said text is displayed as an email.

24. The method of claim 3, wherein said metric associated with the audio stream comprises a volume of the audio stream.

25. The method of claim 3, wherein said metric associated with the audio stream comprises background noise of the audio stream.

26. The method of claim 3, wherein said metric associated with the audio stream comprises a confidence level of the audio stream.

27. The method of claim 3, wherein said indicator comprises a font color.

28. The method of claim 3, wherein said indicator comprises a font weight.

29. The method of claim 3, wherein said indicator comprises a font size.

30. The method of claim 3, wherein said indicator comprises underlining.

31. The method of claim 3, wherein said indicator comprises an audible indicator.

32. A method of providing speech transcription performance indication, comprising:

(a) receiving data representing an audio stream;

(b) converting said data representing an audio stream to text via an ASR system;

(c) determining a metric associated with the audio stream;

(d) transmitting data representing said text to a user device; and

(e) transmitting data representing said metric to the user device.