Enhanced interface for use with speech recognition
View Patent ↗Improved methods of presenting speech prompts to a user as part of an automated system that employs speech recognition or other voice input are described. The invention improves the user interface by providing in combination with at least one user prompt seeking a voice response, an enhanced user keyword prompt intended to facilitate the user selecting a keyword to speak in response to the user prompt. The enhanced keyword prompts may be the same words as those a user can speak as a reply to the user prompt but presented using a different audio presentation method, e.g., speech rate, audio level, or speaker voice, than used for the user prompt. In some cases, the user keyword prompts are different words from the expected user response keywords, or portions of words, e.g., truncated versions of keywords.
1. A voice interface method comprising:
operating a device including a processor to generate a user prompt to solicit input from a user, and
prior to receiving a user response to said user prompt, generating an audible keyword prompt indicating at least some keywords that may be included by a user in a response to said user prompt, the audible keyword prompt including speech that has overlapping words, wherein said overlapping words comprise two or more voice keyword prompts that are mixed together to be at least partially overlapped.
2. The method of claim 1 , wherein said user prompt is an audible prompt.
3. The method of claim 1 , wherein said audible keyword prompt includes keywords that may be spoken by the user as part of a response to said user prompt.
4. The method of claim 3 , further comprising:
playing said audible keyword prompt to the user;
monitoring, following said playing of said audible keyword prompt for keywords spoken by the user in response to said user prompt until a time out is reached; and
responding to keywords spoken by said user which are detected by said monitoring.
5. The method of claim 1 , wherein said step of generating an audible keyword prompt includes generating speech that has includes at least one keyword that is not fully pronounced.
6. The method of claim 1 , wherein the step of generating an audible keyword prompt includes:
combining speech corresponding to different speakers to form said audible keyword prompt.
7. The method of claim 5 , wherein said step of combining speech corresponding to different speakers includes overlapping the speech of different people, the overlapped speech of at least two different people corresponding to different keywords.
8. The method of claim 1 , wherein the step of generating an audible keyword prompt includes synthesizing speech.
9. The method of claim 2 , wherein
operating a device including a processor to generate an audible user prompt includes presenting speech at a first rate; and
generating an audible keyword prompt includes generating speech at a second rate that is different from said first rate.
10. The method of claim 2 , wherein
generating an audible user prompt includes presenting speech at a first volume level; and
generating an audible keyword prompt includes generating speech at a second volume level that is lower than said first volume level.
11. An apparatus comprising:
a processor configured to control said apparatus to:
generate a user prompt to solicit input from a user, and
generate an audible keyword prompt indicating at least some keywords that may be included by a user in a response to said user prompt, the audible keyword prompt including speech that has overlapping words, wherein said overlapping words comprise two or more voice keyword prompts that are mixed together to be at least partially overlapped.
12. The apparatus of claim 11 , wherein said user prompt is an audible prompt.
13. The apparatus of claim 12 , wherein said audible keyword prompt includes keywords that may be spoken by the user as part of a response to said user prompt.
14. The apparatus of claim 13 , further comprising:
an input device configured to receive keywords spoken by the user in response to said user prompt.
15. The apparatus of claim 11 , wherein said processor is configured to control said apparatus to include at least one keyword that is not fully pronounced in said audible keyword prompt.
16. The apparatus of claim 11 , wherein said processor is configured to control said apparatus to:
combine speech corresponding to different speakers to form said audible keyword prompt.
17. The apparatus of claim 16 , wherein said processor is configured, as part of combining speech corresponding to different speakers, to include overlapping speech of different people, the overlapped speech of at least two different people corresponding to different keywords.
18. The apparatus of claim 11 ,
further comprising a speech synthesizer; and
wherein the processor is configured to control said speech synthesizer to generate said audible keyword prompt.
19. The apparatus of claim 12 , where said audible user prompt includes speech, the apparatus further comprising:
an output device configured to output said speech in said audible user prompt at a first rate and to output speech in said audible keyword prompt at a second rate that is different from said first rate.
20. A non-transitory computer readable medium comprising machine executable instructions which, when executed by a processor, cause said processor to:
generate a user prompt to solicit input from a user, and
generate an audible keyword prompt indicating at least some keywords that may be included by a user in a response to said user prompt, the audible keyword prompt including speech that has overlapping words, wherein said overlapping words comprise two or more voice keyword prompts that are mixed together to be at least partially overlapped.