DESCRIPTION (COMPLETE) OCR NOT PREPARE
DUE TO PRINT PROBLEM

WHAT IS CLAIMED IS:
1. A computer-readable medium having computer-executable instructions for providing input data into a computer, the instructions comprising:
an audio capture module adapted to provide data
indicative of input speech; a voice search server adapted to receive the data from the audio capture module, the voice search server using the data to search a collection of phrases and identifying one or more phrases from the collection having a relation to the data; and a module for visually rendering the one or more phrases on the computer and receiving an indication from the user of a selected phrase.
2. The computer-readable medium of claim 1 wherein the voice search server is adapted to filter the data to remove at least one word not searched in the collection.
3. The computer-readable medium of claim 2 wherein the voice search server is adapted to remove at least one word indicative of a command.

4. The computer-readable medium of claim 1 wherein the voice search server is adapted to add alternatives for at least one word in the data.
5. The computer-readable medium of claim 1 wherein the voice search server includes a lattice generator adapted to form a phonetic lattice for the input speech and is adapted to use the data to search the collection by comparing the phonetic lattice for the input speech with phonetic lattices for the collection.
6. A method for providing input into a computer,
the method comprising:
receiving input speech from a user and providing data corresponding to the input speech;
using the data to search a collection of phrases and identifying one or more phrases from the collection having a relation to the data ;
visually rendering the one or more phrases to the user;
receiving an indication of selection from the user of one of the phrases; and
providing the selected phrase to an application.
7. The method of claim 6 wherein receiving an indication comprises operating a pointing device.

8. The method of claim 6 wherein receiving an
indication comprises receiving an audible indication.
9. The method of claim 6 wherein providing the selected phrase comprises inserting the selected phrase in a field of a form rendered on the computer.
10. The method of claim 6 and further comprising filtering the data to remove at least one word not searched in the collection.
11. The method of claim 10 wherein filtering comprises removing at least one word indicative of a command.
12. The method of claim 6 and further comprising adding alternatives for at least one word in the data.
13 . The method of claim 6 wherein providing data includes forming a phonetic lattice for the input speech and using the data to search the collection includes comparing the phonetic lattice for the input speech with phonetic lattices for the collection.
14. A mobile computing device comprising:
a store for storing a collection of phrases; an audio capture module adapted to provide data indicative of input speech;

a voice search server adapted to receive the data from the audio capture module, the voice search server using the data to search the collection of phrases and identifying one or more phrases from the collection having a relation to the data; and
a display/input module for visually rendering the one or more phrases on the computer and receiving an indication from the user of a selected phrase.
15. The mobile computing device of claim 14 wherein the voice search server is adapted to filter the data to remove at least one word not searched in the collection.
16. The mobile computing device of claim 15 wherein the voice search server is adapted to remove at least one word indicative of a command.
17. The mobile computing device of claim 14 wherein the voice search server is adapted to add alternatives for at least one word in the data.
18. The mobile computing device of claim 14 wherein the voice search server includes a lattice generator adapted to form a phonetic lattice for the input speech

and is adapted to use the data to search the collection by comparing the phonetic lattice for the input speech with phonetic lattices for the collection.