Visual confirmation of voice recognized text input

• US 8,606,577 B1
• Filed: 01/03/2013
• Issued: 12/10/2013
• Est. Priority Date: 06/25/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Faaborg, Alexander, Duarte, Matias Gonzalo, Shiplacoff, Daniel Marc Gatan, Cohen, Richard Zarek, Zanolin, Luca, Pietryka, Pawel, Hodgson, Peter John, Penha, Henrique, Stewart, Andrew, Ng, Peter, Bringert, Bjorn Erik, Tickner, Simon
• Primary Examiner(s): Godbold, Douglas
• Application Number:
  US13/733,715
• Publication Number:
  US 20130346076A1
• Time in Patent Office: 341 Days
• Field of Search: 704/231, 704/235
• US Class Current: 704/235
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A computing device receives an audio input from a user. The computing device determines a series of words from the audio input. The computing device outputs, for display, one or more substituted symbols. The one or more substituted symbols correspond to at least a portion of the series of words. In response to determining that receipt of the audio input has completed, the computing device outputs, for display, alphanumeric characters comprising the series of words in place of the one or more substituted symbols.

Claims

1. A method comprising:

receiving, at a computing device, an audio input;

determining, by the computing device, a series of words based on the audio input, the series of words including one or more alphanumeric characters;

outputting, by the computing device, for display, one or more substituted symbols, wherein the one or more substituted symbols correspond to at least a portion of the series of words, and wherein each of the one or more substituted symbols corresponds to an individual respective alphanumeric character of the one or more alphanumeric characters; and

responsive to determining that receipt of the audio input has completed, outputting, by the computing device, for display, the one or more alphanumeric characters in place of the one or more substituted symbols.

2. The method of claim 1, wherein outputting the one or more substituted symbols occurs during receipt of the audio input.

3. The method of claim 1, further comprising:

determining, by the computing device and based at least in part on the audio input, a waveform having a shape, wherein each word from the series of words corresponds to a portion of the waveform, and wherein a shape of each substituted symbol from the one or more substituted symbols reflects the shape of each portion of the waveform that corresponds to each word from the series of words.

4. The method of claim 1, wherein determining the series of words further comprises:

transmitting, by the computing device, to a remote computing device, the audio input; and

receiving, by the computing device, from the remote computing device, the series of words based on the audio input.

5. The method of claim 1, further comprising:

receiving, by the computing device, an indication of a user input; and

configuring, by the computing device and based at least in part on the indication of the user input, the computing device to output substituted symbols instead of alphanumeric characters.

6. The method of claim 1, wherein determining that receipt of the audio input has completed comprises:

receiving, by the computing device, an indication of a gesture input detected at a presence-sensitive screen.

7. The method of claim 1, wherein determining that receipt of the audio input has completed comprises:

determining, by the computing device, an amount of time during which speech has not been detected; and

responsive to determining that the amount of time satisfies a threshold, determining, by the computing device, that receipt of the audio input has completed.

8. The method of claim 1, further comprising:

determining, by the computing device, that a period of time has elapsed since the computing device began receiving the audio input; and

responsive to determining that the period of time satisfies a threshold, outputting, by the computing device, for display, at least a portion of the one or more alphanumeric characters in place of at least a portion of the one or more substituted symbols.

9. The method of claim 1, wherein each substituted symbol from the one or more substituted symbols corresponds to a different alphanumeric character in the series of words.

10. The method of claim 1, wherein each of the one or more alphanumeric characters is either an uppercase or a lowercase alphanumeric character, and wherein each substituted symbol from the one or more substituted symbols that corresponds to an uppercase alphanumeric character is different than each substituted symbol from the one or more substituted symbols that corresponds to a lowercase alphanumeric character.

11. The method of claim 10, wherein each substituted symbol from the one or more substituted symbols has a dimension, the dimension including at least one of a length, a height, a width, and a radius, and wherein the dimension of each substituted symbol from the one or more substituted symbols that corresponds to an uppercase alphanumeric character exceeds the dimension of each substituted symbol from the one or more substituted symbols that corresponds to a lowercase alphanumeric character.

12. The method of claim 10, wherein each substituted symbol from the one or more substituted symbols that corresponds to an uppercase alphanumeric character is represented by at least two substituted symbols from the one or more substituted symbols that correspond to a lowercase alphanumeric character.

13. The method of claim 1, wherein each substituted symbol from the one or more substituted symbols is a rectangular shape, a circular shape, a star shape, an asterisk, or a line segment.

14. The method of claim 1, further comprising:

responsive to determining a first word based on a first segment of the audio input, determining, by the computing device, based on a second segment of the audio input, a second word to replace the first word; and

responsive to determining the second word, replacing, by the computing device, at least one substituted symbol that corresponds to the first word with at least one different substituted symbol that corresponds to the second word.

15. The method of claim 14, wherein the at least one substituted symbol that corresponds to the first word comprise a first color and the at least one different substituted symbol that corresponds to the second word comprise a second color different from the first color.

16. The method of claim 14, wherein replacing the at least one substituted symbol that correspond to the first word with the at least one different substituted symbol that correspond to the second word occurs while the computing device is receiving the audio input.

17. The method of claim 1, wherein the audio input comprises a first segment and a second segment received after the first segment, the method further comprising:

determining, by the computing device and based on the second segment of the audio input, one or more words;

determining, by the computing device and based at least in part on the one or more words, a probability of a first word based on the first segment of the audio input and a probability of a second word based on the first segment of the audio input; and

responsive to determining that the probability of the second word exceeds the probability of the first word, outputting, by the computing device, for display, a different group of substituted symbols that correspond to alphanumeric symbols of the second word in place of the one or more substituted symbols that correspond to the one or more alphanumeric symbols of the first word.

18. The method of claim 17, wherein the probability of the first word is based on a language model probability that the first word is positioned in a sequence of words including the series of words, and the probability of the second word is based on a language model probability that the second word is positioned in a sequence of words including the series of words.

19. A computer-readable storage medium comprising instructions that, when executed, cause at least one processor of a computing device to:

receive an audio input;

determine a series of words based on the audio input, the series of words including one or more alphanumeric characters;

output for display, one or more substituted symbols, wherein the one or more substituted symbols correspond to at least a portion of the series of words, and wherein each of the one or more substituted symbols corresponds to an individual respective alphanumeric character of the one or more alphanumeric characters; and

responsive to determining that receipt of the audio input has completed, output for display the one or more alphanumeric characters in place of the one or more substituted symbols.

20. A computing device comprising one or more processors, the one or more processors being configured to:

receive an audio input;

determine a series of words based on the audio input, the series of words including one or more alphanumeric characters;

output for display, one or more substituted symbols, wherein the one or more substituted symbols correspond to at least a portion of the series of words, and wherein each of the one or more substituted symbols corresponds to a respective alphanumeric character of the one or more alphanumeric characters; and

responsive to determining that receipt of the audio input has completed, output for display the one or more alphanumeric characters in place of the one or more substituted symbols.