Speech recognition repair using contextual information
First Claim
Patent Images
1. A method for transcribing speech, the method comprising:
- at an electronic device;
receiving a transcription of a spoken user request from a speech recognition system;
parsing the transcription into a plurality of tokens representing words in the spoken user request;
using a first interpreter, determining a first confidence level of a first alternative token for one of the plurality of tokens;
using a second interpreter, determining a second confidence level of a second alternative token for the one of the plurality of tokens; and
generating a repaired transcription by replacing the one of the plurality of tokens with the first alternative token or the second alternative token based on the first confidence level and the second confidence level.
1 Assignment
0 Petitions
Accused Products
Abstract
A speech control system that can recognize a spoken command and associated words (such as “call mom at home”) and can cause a selected application (such as a telephone dialer) to execute the command to cause a data processing system, such as a smartphone, to perform an operation based on the command (such as look up mom'"'"'s phone number at home and dial it to establish a telephone call). The speech control system can use a set of interpreters to repair recognized text from a speech recognition system, and results from the set can be merged into a final repaired transcription which is provided to the selected application.
-
Citations
20 Claims
-
1. A method for transcribing speech, the method comprising:
at an electronic device; receiving a transcription of a spoken user request from a speech recognition system; parsing the transcription into a plurality of tokens representing words in the spoken user request; using a first interpreter, determining a first confidence level of a first alternative token for one of the plurality of tokens; using a second interpreter, determining a second confidence level of a second alternative token for the one of the plurality of tokens; and generating a repaired transcription by replacing the one of the plurality of tokens with the first alternative token or the second alternative token based on the first confidence level and the second confidence level. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
9. A non-transitory computer-readable storage medium comprising computer-executable instructions for performing a method comprising:
-
receiving a transcription of a spoken user request from a speech recognition system; parsing the transcription into a plurality of tokens representing words in the spoken user request; using a first interpreter, determining a first confidence level of a first alternative token for one of the plurality of tokens; using a second interpreter, determining a second confidence level of a second alternative token for the one of the plurality of tokens; and generating a repaired transcription by replacing the one of the plurality of tokens with the first alternative token or the second alternative token based on the first confidence level and the second confidence level. - View Dependent Claims (10, 11, 12, 13, 14, 15)
-
-
16. A system for transcribing speech, the system comprising:
-
a memory; and a processor capable of executing a method comprising; receiving a transcription of a spoken user request from a speech recognition system; parsing the transcription into a plurality of tokens representing words in the spoken user request; using a first interpreter, determining a first confidence level of a first alternative token for one of the plurality of tokens; using a second interpreter, determining a second confidence level of a second alternative token for the one of the plurality of tokens; and generating a repaired transcription by replacing the one of the plurality of tokens with the first alternative token or the second alternative token based on the first confidence level and the second confidence level. - View Dependent Claims (17, 18, 19, 20)
-
Specification