Automatically adapting user guidance in automated speech recognition
View Patent ↗A speech recognition method includes receiving input speech from a user, processing the input speech to obtain at least one parameter value, and determining an experience level of the user using the parameter value(s). The method can also include prompting the user based upon the determined experience level of the user to assist the user in delivering speech commands.
1. A speech recognition method comprising the steps of:
(a) receiving input speech from a user;
(b) processing said input speech to obtain at least one parameter value; and
(c) determining the user's level of experience with using automatic speech recognition, using the at least one parameter value.
2. The speech recognition method of claim 1 , wherein step (c) further comprises calculating a score using said at least one parameter value.
3. The speech recognition method of claim 2 , wherein step (c) further comprises calculating said score from a sum of said at least one parameter value.
4. The speech recognition method of claim 3 , wherein said sum is a weighted sum of said at least one parameter value.
5. The speech recognition method of claim 1 , wherein step (c) further comprises comparing said at least one parameter value to at least one threshold value.
6. The speech recognition method of claim 1 , further comprising the step of maintaining a history of usage of automatic speech recognition by the user for determining said user's level of experience.
7. The speech recognition method of claim 1 , wherein step (c) further comprises determining said user's level of experience from at least one or more predetermined levels of experience including a novice user level.
8. The speech recognition method of claim 1 , further comprising the step of setting a voice recognition window based upon the determined user's level of experience, including setting the window to be shorter for expert users and longer for novice users.
9. The speech recognition method of claim 1 , wherein said at least one parameter value includes at least one of: speech volume, vocal pitch, vocal speed, energy profiles, steadiness, or intonation.
10. A speech recognition method for a speech recognition system comprising the steps of:
(a) receiving input speech from a user;
(b) processing said input speech to obtain at least one parameter value;
(c) determining the user's level of experience with using automatic speech recognition, using the at least one parameter value; and
(d) adjusting an amount of prompting provided to the user based upon said user's level of experience to assist the user in delivering speech commands to the system wherein the adjusting includes providing users having less experience with automatic speech recognition with prompting that is more detailed than that provided for users having more experience with automatic speech recognition.
11. The speech recognition method of claim 10 , wherein step (d) further comprises providing the user with commands recognized by the system depending on the user's level of experience with using automatic speech recognition.
12. The speech recognition method of claim 10 , wherein step (d) further comprises providing the user with instructions to guide the user depending on the user's level of experience with using automatic speech recognition.
13. The speech recognition method of claim 10 , further comprising the step of suggesting commands to the user during dead time.
14. The speech recognition method of claim 10 , further comprising the step of setting a voice recognition window based upon the determined user's level of experience.
15. The speech recognition method of claim 10 , wherein step (d) includes providing at least one of confirmation responses to user commands, instructions to guide the user to complete a request for an action, or playing an automated help message.
16. The speech recognition method of claim 10 wherein step (c) further comprises calculating a score from a weighted sum of said at least one parameter value.
17. The speech recognition method of claim 10 , wherein step (b) further comprises comparing said at least one parameter value to at least one threshold value, wherein said at least one parameter is speech volume, and when said speech volume value is below said at least one threshold value, the user's level of experience with automatic speech recognition is determined to be at a novice user level.
18. The speech recognition method of claim 10 , further comprising the step of maintaining a history of usage of automatic speech recognition by the user for determining said user's level of experience.
19. The speech recognition method of claim 10 , further comprising the step of determining the user's experience level with a group of commands.
20. A communications system located on a vehicle, comprising:
a speech receiving device to receive speech from a user;
an acoustic interface to digitize the speech into acoustic data;
a memory for storing the acoustic data; and
a processor for processing the acoustic data;
said speech receiving device, said memory, and said processor providing automated speech recognition for the acoustic data;
wherein said processor processes said acoustic data to obtain at least one parameter value, determines the user's level of experience with using automatic speech recognition from at least one of said parameter values, and adjusts an amount of prompting provided to the user based upon said user's level of experience to assist the user in delivering speech commands to the system.
21. The speech recognition method of claim 1 , wherein said at least one parameter value includes intonation, and further wherein an intonation parameter value indicating that the user gave a command in the form of a question is indicative that the user's level of experience is relatively low, whereas an intonation parameter value indicating a firm command is indicative that user's level of experience is relatively high.
22. The speech recognition method of claim 1 , wherein the user's level of experience is determined to be high when the user's input speech includes only commands without extra words.
23. The speech recognition method of claim 1 , further comprising the step of determining the user's experience level with different groups of commands.
24. The speech recognition method of claim 1 , further comprising the step of maintaining a history of usage of automatic speech recognition by the user for determining said user's level of experience, and wherein step (d) includes tracking the number of times a command is given by the user as said at least one parameter value.
25. The speech recognition method of claim 24 , further comprising the step of adjusting the amount of prompting provided to the user, if it is determined that the user has given the command for the first time.
26. The speech recognition method of claim 1 , further comprising the steps of:
identifying individual users of automatic speech recognition; and
maintaining histories for the users, including the users' levels of experience with automatic speech recognition commands.