Text entry at electronic communication device

1. A method of facilitating text entry at an electronic communication device, the method comprising:

receiving typed input at a text field from a keyboard of the electronic communication device;

receiving audio input at the electronic communication device;

performing text prediction using the typed input to obtain at least one text-predicted candidate word and an associated confidence value;

performing speech recognition using the audio input to obtain at least one speech-recognized candidate word and an associated confidence value;

selecting from the text-predicted and speech-recognized candidate words a candidate word having a highest associated confidence value, as a suggested candidate word; and, one of:

receiving a portion of the audio input corresponding to a particular speech-recognized candidate word before receiving a most recent portion of the typed input; and, determining the confidence value of the particular speech-recognized candidate word by referencing an amount of time that the particular speech-recognized candidate word is received before the most recent portion of the typed input, the confidence value of the particular speech-recognized candidate word decreasing as the amount of time increases; or,

receiving the portion of the audio input corresponding to the particular speech-recognized candidate word after receiving the most recent portion of the typed input and, determining the confidence value of the particular speech-recognized candidate word by referencing an amount of time that the particular speech-recognized candidate word is received after receiving the most recent portion of the typed input, the confidence value of the particular speech-recognized candidate word decreasing as the amount of time increases.

2. The method of claim 1 , further comprising obtaining the speech-recognized candidate word by performing a pre-selection from a plurality of speech-recognized candidate words based on at least a portion of the typed input.

3. The method of claim 2 , wherein the portion of the typed input comprises an initial character of a word.

4. The method of claim 1 , further comprising triggering the text prediction, the selecting, and the entering in response to receiving each character of the typed input.

5. The method of claim 1 , wherein the selecting comprises selecting from the text-predicted and speech-recognized candidate words a plurality of candidate words having highest associated confidence values, as suggested candidate words.

6. The method of claim 5 , further comprising displaying the suggested candidate words as user-selectable on a display of the electronic communication device.

7. The method of claim 6 , further comprising displaying at least two of the suggested candidate words superimposed on a virtual keyboard.

8. The method of claim 6 , further comprising receiving a user selection of one of the suggested candidate words.

9. The method of claim 1 , further comprising entering the suggested candidate word into a text buffer of the electronic communication device.

10. A non-transitory computer-readable medium storing a computer program, wherein execution of the computer program is for: facilitating text entry at an electronic communication device by:

receiving typed input at a text field from a keyboard of the electronic communication device;

receiving audio input at the electronic communication device;

performing text prediction using the typed input to obtain at least one text-predicted candidate word and an associated confidence value;

performing speech recognition using the audio input to obtain at least one speech-recognized candidate word and an associated confidence value;

selecting from the text-predicted and speech-recognized candidate words a candidate word having a highest associated confidence value, as a suggested candidate word; and, one of:

receive a portion of the audio input corresponding to a particular speech-recognized candidate word before receiving a most recent portion of the typed input; and determining the confidence value of the particular speech-recognized candidate word by referencing an amount of time that the particular speech-recognized candidate word is received before the most recent portion of the typed input, the confidence value of the particular speech-recognized candidate word decreasing as the amount of time increases; or,

receive the portion of the audio input corresponding to the particular speech-recognized candidate word after receiving the most recent portion of the typed input; and, determining the confidence value of the particular speech-recognized candidate word by referencing an amount of time that the particular speech-recognized candidate word is received after receiving the most recent portion of the typed input, the confidence value of the particular speech-recognized candidate word decreasing as the amount of time increases.

11. The non-transitory computer-readable medium of claim 10 , wherein execution of the computer program is further for: entering the suggested candidate word into a text buffer of the electronic communication device.

12. An electronic communication device comprising:

a display;

a microphone and connected analog-to-digital converter (ADC);

memory; and

a processor connected to the display, the ADC, and the memory, the processor configured to:

output a virtual keyboard to the display;

receive typed input from the keyboard, and perform text prediction using the typed input to obtain at least one text-predicted candidate word and an associated confidence value;

receive audio input from the ADC, and perform speech recognition using the audio input to obtain at least one speech-recognized candidate word and an associated confidence value;

select a candidate word having a highest confidence value from the text-predicted and speech-recognized candidate words, as a suggested candidate word; and, one of:

receiving a portion of the audio input corresponding to a particular speech-recognized candidate word before receiving a most recent portion of the typed input; and, determining the confidence value of the particular speech-recognized candidate word by referencing an amount of time that the particular speech-recognized candidate word is received before the most recent portion of the typed input, the confidence value of the particular speech-recognized candidate word decreasing as the amount of time increases; or,

receiving the portion of the audio input corresponding to the particular speech-recognized candidate word after receiving the most recent portion of the typed input; and, determining the confidence value of the particular speech-recognized candidate word by referencing an amount of time that the particular speech-recognized candidate word is received after receiving the most recent portion of the typed input, the confidence value of the particular speech-recognized candidate word decreasing as the amount of time increases.

13. The electronic communication device of claim 12 , wherein the processor is further configured to store the suggested candidate word in the memory.

14. A method of facilitating text entry at an electronic communication device, the method comprising:

receiving typed input from a virtual keyboard;

receiving a stream of digitized audio input;

performing text prediction on a most recent word or word portion of the typed input to obtain at least one text-predicted candidate word and an associated confidence value;

performing speech recognition on the audio input to obtain at least one speech-recognized candidate word and an associated confidence value, the confidence value of the speech-recognized candidate word being based at least in part on a recency of a respective portion of the audio input as compared to a time of receiving the word or word portion of the typed input;

selecting from the text-predicted and speech-recognized candidate words a candidate word, as a suggested candidate word, based on the associated confidence values; and, one of:

receiving a portion of the audio input corresponding to a particular speech-recognized candidate word before receiving a most recent portion of the typed input; and, determining the confidence value of the particular speech-recognized candidate word by referencing an amount of time that the particular speech-recognized candidate word is received before the most recent portion of the typed input, the confidence value of the particular speech-recognized candidate word decreasing as the amount of time increases; or,

receiving the portion of the audio input corresponding to the particular speech-recognized candidate word after receiving the most recent portion of the typed input; and, determining the confidence value of the particular speech-recognized candidate word by referencing an amount of time that the particular speech-recognized candidate word is received after receiving the most recent portion of the typed input, the confidence value of the particular speech-recognized candidate word decreasing as the amount of time increases.

15. The method of claim 14 , further comprising pre-selecting speech-recognized candidate words based on a match with the most recent word or word portion of the typed input.

16. The method of claim 14 , further comprising displaying the suggested candidate word superimposed on a virtual keyboard.

17. The method of claim 14 , comprising performing the speech recognition as a background process and performing the text prediction and the selecting in response to a key press at the virtual keyboard.

18. The method of claim 14 , further comprising storing the suggested candidate word in a memory of the electronic communication device.