Language-oriented user interfaces for voice activated services

• US 6,526,382 B1
• Filed: 12/07/1999
• Issued: 02/25/2003
• Est. Priority Date: 12/07/1999
• Status: Expired due to Term

• Current Assignee: Mavenir Systems Incorporated (Mavenir Group Holdings Ltd.)
• Original Assignee: Comverse Incorporated (Mavenir Group Holdings Ltd.)
• Inventors: Yuschik, Matthew John
• Primary Examiner(s): Dorvil, Richemond
• Application Number:
  US09/456,922
• Time in Patent Office: 1,176 Days
• Field of Search: 704/270, 704/275, 704/257, 704/231, 704/9, 704/251, 704/3
• US Class Current: 704/275
• 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 designing a voice activated user interface, the method comprising:

separately selecting a vocabulary set and a prompting syntax for the user interface based on semantics and syntax determined by results of first testing with subjects from a target community; and

jointly optimizing the vocabulary set and the prompting syntax based on results of second testing with subjects from the target community.

2. A method as recited in claim 1, wherein selecting the vocabulary set comprises selecting frequently used words for commands of a target service application based on frequencies of occurrence generated for the words from the first testing results.

3. A method as recited in claim 1, further comprising obtaining the first testing results by a procedure including:

posing task-oriented questions to the subjects and collecting responses therefor; and

generating a frequency distribution for the collected responses.

4. A method as recited in claim 1, wherein selecting the prompting syntax includes:

identifying an initial value for each of one or more syntax parameters from samples of spoken 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.

5. A method as recited in claim 1, further comprising obtaining the first testing results by a procedure including:

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

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

6. A method as recited in claim 1, further comprising obtaining the second testing results by a procedure including:

posing a task set for a subject to perform using the prompting syntax and the vocabulary set; and

collecting dialogue information for at least one of the prompting syntax and the vocabulary set when the subject performs the task set.

7. A method as recited in claim 1, wherein selecting the vocabulary set includes:

dividing user preferred words for the user interface into sub-vocabularies;

testing each sub-vocabulary for pairwise acoustic similarity among the words thereof; and

replacing a specified word of a sub-vocabulary with an alternative user-preferred word when the specified word is acoustically similar to another word in the sub-vocabulary.