System and method for spelling recognition using speech and non-speech input
View Patent ↗A system and method for non-speech input or keypad-aided word and spelling recognition is disclosed. The method includes generating an unweighted grammar, selecting a database of words, generating a weighted grammar using the unweighted grammar and a statistical letter model trained on the database of words, receiving speech from a user after receiving the non-speech input and after generating the weighted grammar, and performing automatic speech recognition on the speech and non-speech input using the weighted grammar. If a confidence is below a predetermined level, then the method includes receiving non-speech input from the user, disambiguating possible spellings by generating a letter lattice based on a user input modality, and constraining the letter lattice and generating a new letter string of possible word spellings until a letter string is correctly recognized.
1. A method comprising:
receiving, via a processor, a speech input;
constructing an unweighted grammar permitting all letter sequences that map to the speech input;
generating keypad constraints using the unweighted grammar and a weighted statistical letter model trained on a database of words;
receiving non-speech input constrained by the keypad constraints; and
recognizing the speech input and the non-speech input using the unweighted grammar and the weighted statistical letter model.
2. The method of claim 1 , wherein the database of words is a domain of words related to the non-speech input.
3. The method of claim 1 , wherein the weighted statistical letter model is an N-gram letter model.
4. The method of claim 3 , wherein the N-gram letter model is unsmoothed.
5. The method of claim 1 , further comprising:
generating a final letter string based on the database of words.
6. The method of claim 5 , wherein generating the final letter string based on the database of words further comprises using a finite state network that accepts only valid letter strings.
7. The method of claim 1 , wherein the non-speech input comprises a portion of a word.
8. The method of claim 1 , further comprising:
if an automated speech recognition confidence is below a predetermined level, prompting the user to enter a first three or less letters of the speech input by using a keypad to yield the non-speech input.
9. A system comprising:
a processor;
a non-transitory computer-readable storage medium having stored therein instructions which, when executed by the processor, cause the processor to perform a method comprising:
constructing an unweighted grammar permitting all letter sequences that map to speech input;
generating keypad constraints using the unweighted grammar and a weighted statistical letter model trained on a database of words;
receiving non-speech input constrained by the keypad constraints; and
recognizing the speech input and the non-speech input using the unweighted grammar and the weighted statistical letter model.
10. The system of claim 9 , wherein the database of words is a domain of words related to the non-speech input.
11. The system of claim 9 , wherein the weighted statistical letter model is an N-gram letter model.
12. The system of claim 11 , wherein the N-gram letter model is unsmoothed.
13. The system of claim 9 , the non-transitory computer-readable storage medium having stored therein further instructions which, when executed by the processor, cause the processor to perform a method further comprising:
generating a final letter string based on the database of words.
14. The system of claim 13 , wherein the final letter string is generated based on the database of words via a finite state network that accepts only valid letter strings.
15. A non-transitory computer-readable storage medium storing instructions which, when executed by a computing device, cause the computing device to perform a method comprising:
receiving a speech input;
constructing an unweighted grammar permitting all letter sequences that map to the speech input;
generating keypad constraints using the unweighted grammar and a weighted statistical letter model trained on a database of words;
receiving non-speech input constrained by the keypad constraints; and
recognizing the speech input and the non-speech input using the unweighted grammar and the weighted statistical letter model.
16. The non-transitory computer-readable storage medium of claim 15 , wherein the database of words is a domain of words related to the non-speech input.
17. The non-transitory computer-readable storage medium of claim 15 , wherein the weighted statistical letter model is an N-gram letter model.
18. The non-transitory computer-readable storage medium of claim 17 , wherein the N-gram letter model is unsmoothed.
19. The non-transitory computer-readable storage medium of claim 15 , the instructions further comprising:
controlling the processor to generate a final letter string based on the database of words.
20. The non-transitory computer-readable storage medium of claim 19 , wherein the final letter string based on the database of words further comprises using a finite state network that accepts only valid letter strings.