Multimodal voice dialing digital key telephone with dialog manager
First Claim
1. A multimodal telephone comprising:
- a telephone unit having a microphone and speaker for supporting voice communication by a user;
a visual display device disposed on said telephone unit, the display adapted for displaying a plurality of different command prompts to the user;
at least one programmable function key for enabling entry of keyed commands, said function key disposed on said telephone unit adjacent said visual display such that at least a portion of said command prompts are displayed approximately adjacent said function key;
a speech module disposed within said telephone unit, the speech module including a speech recognizer and a speech generator, the speech module being coupled to said telephone unit so that said speech recognizer is responsive to voiced commands entered through said microphone and said speech synthesizer provides audible prompts through said speaker;
a dialog manager coupled to said visual display, to said function key and to said speech module, said dialog manager defining a set of linked control function states each state associated with a respective one of said command prompts and at least a portion of said set of linked control function states being further associated with a respective one of said audible prompts;
said dialog manager being responsive to said voiced commands and to said function key to traverse said set of linked control function states to select one of said set of linked control function states as an active state;
said dialog manager being operative to maintain synchronism between said command prompts and said audible prompts such that the control function states linked to said active state are displayed as a command prompts and the user has the option to move from said active state to one of said control function states linked to said active state by either voiced command or keyed command; and
wherein said dialog manager stores a dialog context and wherein said speech recognizer selects a plurality of word candidates in response to voiced commands and uses said dialog context to select among said plurality of word candidates.
5 Assignments
0 Petitions
Accused Products
Abstract
The multimodal telephone prompts the user using both a visual display and synthesized voice. It receives user input via keypad and programmable soft keys associated with the display, and also through user-spoken commands. The voice module includes a two stage speech recognizer that models speech in terms of high similarity values. A dialog manager associated with the voice module maintains the visual and verbal systems in synchronism with one another. The dialog manager administers a state machine that records the dialog context. The dialog context is used to ensure that the appropriate visual prompts are displayed--showing what commands are possible at any given point in the dialog. The speech recognizer also uses the dialog context to select the recognized word candidate that is appropriate to the current context.
-
Citations
13 Claims
-
1. A multimodal telephone comprising:
-
a telephone unit having a microphone and speaker for supporting voice communication by a user; a visual display device disposed on said telephone unit, the display adapted for displaying a plurality of different command prompts to the user; at least one programmable function key for enabling entry of keyed commands, said function key disposed on said telephone unit adjacent said visual display such that at least a portion of said command prompts are displayed approximately adjacent said function key; a speech module disposed within said telephone unit, the speech module including a speech recognizer and a speech generator, the speech module being coupled to said telephone unit so that said speech recognizer is responsive to voiced commands entered through said microphone and said speech synthesizer provides audible prompts through said speaker; a dialog manager coupled to said visual display, to said function key and to said speech module, said dialog manager defining a set of linked control function states each state associated with a respective one of said command prompts and at least a portion of said set of linked control function states being further associated with a respective one of said audible prompts; said dialog manager being responsive to said voiced commands and to said function key to traverse said set of linked control function states to select one of said set of linked control function states as an active state; said dialog manager being operative to maintain synchronism between said command prompts and said audible prompts such that the control function states linked to said active state are displayed as a command prompts and the user has the option to move from said active state to one of said control function states linked to said active state by either voiced command or keyed command; and wherein said dialog manager stores a dialog context and wherein said speech recognizer selects a plurality of word candidates in response to voiced commands and uses said dialog context to select among said plurality of word candidates. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12)
-
-
13. A multimodal telephone comprising:
-
a telephone unit having a microphone for supporting voice communication by a user; a speech module coupled to said telephone unit, the speech module including a speech recognizer that is responsive to voiced commands entered through said microphone; a dialog manager coupled to said speech module that stores a dialog context and wherein said speech recognizer selects a plurality of word candidates in response to said voiced commands and uses said dialog context to select among said plurality of word candidates.
-
Specification