Language-oriented user interfaces for voice activated services

• US 20030046088A1
• Filed: 08/13/2002
• Published: 03/06/2003
• Est. Priority Date: 12/07/1999
• Status: Active Grant

• Current Assignee: Mavenir Systems Incorporated (Mavenir Group Holdings Ltd.)
• Original Assignee: Comverse Network Systems, Inc. (Verint Systems Incorporated)
• Inventors: Yuschik, Matthew John
• Granted Patent: US 6,598,022 B2
• Time in Patent Office: Days
• US Class Current: 704/276
• CPC Class Codes: G10L 15/065 Adaptation
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding

Abstract

A comprehensive system is provided for designing a voice activated user interface (VA UI) having a semantic and syntactic structure adapted to the culture and conventions of spoken language for the intended users. The system decouples the content dimension of speech (semantics) and the manner-of-speaking dimension (syntax) in a systematic way. By decoupling these dimensions, the VA UI can be optimized with respect to each dimension independently and jointly. The approach is general across languages and encompasses universal variables of language and culture. Also provided are voice activated user interfaces with semantic and syntactic structures so adapted, as well as a prompting grammar and error handling methods adapted to such user interfaces.

Claims

1. A method for defining a temporal prompting syntax for a voice actuated user interface, the method comprising:

identifying an initial value for each of one or more syntax parameters from samples of dialogue in a conversational language of a target community; and

specifying an initial temporal syntax for the user interface based on the one or more identified initial values.

2. A method as recited in claim 1, further comprising collecting further samples of dialogue by a procedure including:

posing a task set for a subject to perform using the initial temporal syntax and a selected vocabulary set; and

collecting dialogue information for the initial temporal syntax and the selected vocabulary set when the subject performs the task set.

3. A method as recited in claim 1, wherein the one or more syntax parameters includes at least one of a pace, a pause duration, an intonational cue location, and a command options chunk size.

4. A method as recited in claim 1, wherein identifying the one or more syntax parameter initial values includes:

posing a task set for a subject to perform using test prompts; and

collecting dialogue information for the test prompts when the subject performs the task set.

15. A method as recited in claim 3, wherein the pause duration is selected from a duration of an interchunk pause, a duration of an intrachunk pause, and a duration of a carrier phrase pause.

5. A method for optimizing a prompting syntax of a voice actuated user interface, the method comprising:

testing performance of tasks by subjects from a target community using the interface implemented with a command vocabulary and a temporal syntax each selected for the target community; and

modifying the temporal syntax based on results of the testing.

6. A method as recited in claim 5, wherein the performance testing includes:

posing a task set for a subject to perform using the interface; and

collecting dialogue information for the interface when the subject performs the task set.

7. A method as recited in claim 5, further comprising selecting the temporal syntax based on samples of dialogues with users using test prompts.

8. A method as recited in claim 7, wherein the sampled dialogues are dialogues in a conversational language of the target community.

9. A method as recited in claim 5, wherein modifying the temporal syntax includes changing at least one of a pace, a pause duration, an intonational cue, and a prompt chunk size of the temporal syntax.

10. A method as recited in claim 5, wherein the results of the performance testing include a performance indicator selected from a task duration, a throughput rate, and a count of correction words said during performance of the tasks.

11. A method for defining a prompting syntax for a voice activated user interface, the method comprising:

specifying an initial temporal syntax for the user interface based on initial syntax parameter values identified through dialogue analysis; and

modifying the initial temporal syntax based on results of testing user performance with the user interface using a selected command vocabulary with the initial temporal syntax.

12. A method as recited in claim 11, wherein the performance testing includes:

posing a task set for a subject to perform using the interface; and

collecting dialogue information for the interface when the subject performs the task set.

13. A method as recited in claim 11, further comprising selecting the initial syntax parameter values based on samples of dialogues with users using test prompts.

14. A method as recited in claim 13, wherein the sampled dialogues are dialogues in a conversational language of the target community.