Continuous speech transcription performance indication

• US 8,543,396 B2
• Filed: 09/15/2012
• Issued: 09/24/2013
• 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: Terrell, James Richard II, White, Marc, Jablokov, Igor Roditis
• Primary Examiner(s): Abebe, Daniel D
• Application Number:
  US13/621,179
• Publication Number:
  US 20130018655A1
• Time in Patent Office: 374 Days
• Field of Search: 704/235, 704/251, 369/25.01
• 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

Audio data that includes speech may be transcribed to text by a speech recognition engine. One or more metrics associated with the audio data and/or the text may be determined. An indicator related to a metric may be provided for a portion of the audio data or the text for which the metric was determined. The indicator may be presented in a user-perceptible format.

Claims

1. A computer-implemented method, the computer-implemented method comprising:

under control of one or more computing devices configured with specific computer-executable instructions,

receiving audio data comprising speech;

transcribing the speech, using a speech recognition engine, to generate a transcription comprising first text;

determining a metric associated with the first text;

selecting, based at least in part on the metric, an indicator of the metric; and

causing presentation of the first text using the indicator of the metric.

2. The computer-implemented method of claim 1, wherein the metric corresponds to at least one of a level of background noise, a volume, or a confidence level of a portion of the transcription comprising the first text.

3. The computer-implemented method of claim 1, wherein the audio data was received from a client device, and wherein causing presentation of the first text using the indicator of the metric comprises transmitting the first text to the client device.

4. The computer-implemented method of claim 1 further comprising receiving a designation of a recipient device from a client device, wherein the audio data was received from the client device, and wherein causing presentation of the first text using the indicator of the metric comprises transmitting a message to the recipient device, the message comprising the first text.

5. The computer-implemented method of claim 1 wherein selecting the indicator of the metric comprises selecting a representation of the first text.

6. The computer-implemented method of claim 5, wherein the representation of the first text comprises at least one of a color of the first text, a grayscale level of the first text, a weight of the first text, an underlining of the first text, or a font size of the first text.

7. The computer-implemented method of claim 1, wherein the indicator of the metric comprises an audible indicator.

8. A system comprising:

an electronic data store configured to store one or more algorithms that, when executed, implement a speech recognition engine; and

a computing device in communication with the electronic data store, the computing device configured to;

receive audio data comprising speech;

transcribe the speech with the speech recognition engine to generate a transcription comprising first text;

determine a first metric associated with the first text;

select, based at least in part on the first metric, a representation of the first text;

cause presentation of the first text using the selected representation.

9. The system of claim 8, wherein the selected representation of the first text comprises at least one of a color of the first text, a grayscale level of the first text, a weight of the first text, an underlining of the first text, or a font size of the first text.

10. The system of claim 8, wherein the first metric comprises at least one of a level of background noise, a volume, or a confidence level of a portion of the transcription comprising the first text.

11. The system of claim 8, wherein the first text comprises at least one of a syllable, a word, a phrase, or a sentence.

12. The system of claim 8, wherein the audio data was received from a client device, and wherein the computing device is configured to cause presentation of the first text using the selected representation by transmitting the first text and information about the selected representation to the client device.

13. The system of claim 8, wherein the audio data was received from a client device, wherein the computing device is further configured to receive a designation of a recipient device from the client device, and wherein the computing device is configured to cause presentation of the first text using the selected representation by transmitting the first text and information about the selected representation to the recipient device.

14. The system of claim 8, wherein the computing device is further configured to determine a second metric associated with the first text, and wherein the representation of the first text is selected further based at least in part on the second metric.

15. A non-transitory computer-readable medium having stored thereon a computer-executable module configured to execute in one or more processors of a device, the computer-executable module being further configured to:

obtain text transcribed from audio data using a speech recognition engine, wherein the text comprises a first portion;

obtain information about a metric associated with the first portion of the text; and

cause presentation of the first portion of the text using the information about the metric.

16. The non-transitory computer-readable medium of claim 15, wherein the computer-executable module is further configured to receive a designation of a recipient device, and wherein the computer-executable module is configured to cause presentation of the first portion of the text using the information about the metric by transmitting, to the recipient device, a message comprising the first portion of the text and the information about the metric.

17. The non-transitory computer-readable medium of claim 15, wherein the computer-executable module is configured to obtain the text and the information about the metric by receiving a message comprising the first portion of the text and the information about the metric.

18. The non-transitory computer-readable medium of claim 15, wherein the speech recognition engine is included in the device, and wherein the computer-executable module is further configured to:

obtain the audio data;

obtain the text by using the speech recognition engine to transcribe the audio data; and

obtain the information about the metric associated with the first portion of the text by determining the information about the metric.

19. The non-transitory computer-readable medium of claim 15, wherein the information about the metric comprises formatting corresponding to the first portion of the text, wherein the formatting was generated using the metric.

20. The non-transitory computer-readable medium of claim 19, wherein the formatting corresponding to the first portion of the text comprises at least one of a color of the first portion of the text, a grayscale level of the first portion of the text, a weight of the first portion of the text, an underlining of the first portion of the text, or a font size of the first portion of the text.