Speech recognition of character sequences

1. A method of processing speech, the method comprising:

receiving a spoken utterance of a plurality of uttered characters;

determining an identified character sequence by determining corresponding identified characters for individual ones of the plurality of uttered characters;

selecting a plurality of known character sequences that potentially correspond to the identified character sequence; and

for each selected known character sequence, scoring such known character sequence, using a processor, based at least in part on a weighting of individual characters that comprise the known character sequence, wherein scoring the known character sequence comprises:

responsive to determining that a first character of the known character sequence matches a second identified character of the identified character sequence, selecting a value that corresponds to the first character of the known character sequence; and

adding the selected value to a cumulative score associated with the known character sequence.

2. The method of claim 1 , wherein the weighting is based at least in part on frequencies of utterance of the individual characters.

3. The method of claim 1 , wherein the selected value is pre-assigned to the first character in a character set.

4. The method of claim 1 , wherein:

no characters precede the first character in the known character sequence, and

one identified character precedes the second identified character in the identified character sequence.

5. The method of claim 1 , further comprising:

selecting the known character sequence having the highest cumulative score; and

communicating the selected known character sequence having the highest cumulative score to an application that receives recognized speech.

6. The method of claim 1 , wherein selecting the plurality of known character sequences comprises selecting character sequences from a limited set of character sequences.

7. A method of processing speech, the method comprising:

receiving a spoken utterance of a plurality of uttered characters;

determining an identified character sequence by determining corresponding identified characters for individual ones of the plurality of uttered characters;

selecting a plurality of known character sequences that potentially correspond to the identified character sequence; and

for each selected known character sequence, scoring such known character sequence, using a processor, based at least in part on a weighting of individual characters that comprise the known character sequence, wherein scoring the known character sequence comprises:

responsive to determining that a second character of the known character sequence matches a first identified character of the identified character sequence, selecting a value that corresponds to the second character of the known character sequence; and

adding the selected value to a cumulative score associated with the known character sequence.

8. The method of claim 7 , further comprising:

selecting the known character sequence having the highest cumulative score; and

communicating the selected known character sequence having the highest cumulative score to an application that receives recognized speech.

9. The method of claim 7 , wherein selecting the plurality of known character sequences comprises selecting character sequences from a limited set of character sequences.

10. The method of claim 7 , wherein:

no identified characters precede the first identified character in the identified character sequence, and

one character precedes the second character in the known character sequence.

11. The method of claim 7 , wherein the weighting is based at least in part on frequencies of utterance of the individual characters.

12. The method of claim 7 , wherein the selected value is pre-assigned to the second character in a character set.

13. A speech recognition system comprising:

a primary speech processor that processes an audio signal comprising a spoken utterance of a plurality of uttered characters, wherein the processing comprises determining an identified character sequence by determining corresponding identified characters for individual ones of the plurality of uttered characters; and

a character post-processor that selects a plurality of known character sequences that potentially correspond to the identified character sequence and, for each selected known character sequence, scores such known character sequence based at least in part on a weighting of individual characters that comprise the known character sequence, wherein the character post-processor selects a value that corresponds to a first character of the known character sequence in response to determining that the first character of the known character sequence matches a second identified character of the identified character sequence, and adds the selected value to a cumulative score associated with the known character sequence.

14. The system of claim 13 , wherein the weighting is based at least in part on frequencies of utterance of the individual characters.

15. The system of claim 13 , wherein the selected value is pre-assigned in a character set to the first character.

16. The system of claim 13 , wherein:

no characters precede the first character in the known character sequence, and

one identified character precedes the second identified character in the identified character sequence.

17. A speech recognition system comprising:

a primary speech processor that processes an audio signal comprising a spoken utterance of a plurality of uttered characters, wherein the processing comprises determining an identified character sequence by determining corresponding identified characters for individual ones of the plurality of uttered characters; and

a character post-processor that selects a plurality of known character sequences that potentially correspond to the identified character sequence and, for each selected known character sequence, scores such known character sequence based at least in part on a weighting of individual characters that comprise the known character sequence, wherein the character post-processor selects a value that corresponds to a second character of the known character sequence in response to determining that the second character of the known character sequence matches a first identified character of the identified character sequence, and adds the selected value to a cumulative score associated with the known character sequence.

18. The system of claim 17 , wherein:

no identified characters precede the first identified character in the identified character sequence, and

one character precedes the second character in the known character sequence.

19. The system of claim 17 , wherein the weighting is based at least in part on frequencies of utterance of the individual characters.

20. The system of claim 17 , wherein the selected value is pre-assigned in a character set to the second character.

21. A computer program product comprising:

a non-transitory computer readable storage medium having computer usable program code that, when executed, performs a method of processing speech, the method comprising:

receiving a spoken utterance of a plurality of uttered characters;

determining an identified character sequence by determining corresponding identified characters for individual ones of the plurality of uttered characters;

selecting a plurality of known character sequences that potentially correspond to the identified character sequence; and

for each selected known character sequence, scoring such known character sequence based at least in part on a weighting of individual characters that comprise the known character sequence, wherein scoring the known character sequence comprises:

responsive to determining that a first character of the known character sequence matches a second identified character of the identified character sequence, selecting a value that corresponds to the first character of the known character sequence; and

adding the selected value to a cumulative score associated with the known character sequence.

22. The computer program product of claim 21 , wherein the selected value is pre-assigned to the first character in a character set.

23. A computer program product comprising:

a non-transitory computer readable storage medium having computer usable program code that, when executed, performs a method of processing speech, the method comprising:

receiving a spoken utterance of a plurality of uttered characters;

determining an identified character sequence by determining corresponding identified characters for individual ones of the plurality of uttered characters;

selecting a plurality of known character sequences that potentially correspond to the identified character sequence; and

for each selected known character sequence, scoring such known character sequence based at least in part on a weighting of individual characters that comprise the known character sequence, wherein scoring the known character sequence comprises:

responsive to determining that a second character of the known character sequence matches a first identified character of the identified character sequence, selecting a value that corresponds to the second character of the known character sequence; and

adding the selected value to a cumulative score associated with the known character sequence.

24. The computer program product of claim 23 , wherein the selected value is pre-assigned to the second character in a character set.