Apparatus, method, and program for supporting speech interface design
View Patent ↗For design of a speech interface accepting speech control options, speech samples are stored on a computer-readable medium. A similarity calculating unit calculates a certain indication of similarity of first and second sets of ones of the speech samples, the first set of speech samples being associated with a first speech control option and the second set of speech samples being associated with a second speech control option. A display unit displays the similarity indication. In another aspect, word vectors are generated for the respective speech sample sets, indicating frequencies of occurrence of respective words in the respective speech sample sets. The similarity calculating unit calculates the similarity indication responsive to the word vectors of the respective speech sample sets. In another aspect, a perplexity indication is calculated for respective speech sample sets responsive to language models for the respective speech sample sets.
1. A method for creating a speech interface of a system with a computer, the method comprising:
accessing, with the computer, a database that includes speech samples associated with any of a plurality of speech controls to the system;
calculating a similarity indication between a first set of speech samples associated with a first attribute and a second set of speech samples associated with a second attribute;
displaying the similarity indication between the first set and the second set;
receiving analytical results of the displayed similarity indication and generating an electronic report of the analytical results;
generating a language model regarding the first set based upon the speech samples included in the first set; and
calculating a perplexity regarding the first set using the language model regarding the first set;
wherein displaying the similarity indication includes displaying a graph where points corresponding to each of the plurality of speech controls are plotted so as to express the similarity indication and a circle is drawn, wherein the circle has one of the points as a center and indicates the perplexity for the speech control corresponding to the one of the points.
2. The method according to claim 1 , wherein preparing the electronic report includes a step of including an image of the graph in the electronic report.
3. A first system for creating a speech interface of a second system with a computer, the first system comprising at least one host computer configured to create a speech interface of the second system, the at least one host computer programmed to:
access a database that includes speech samples associated with any of a plurality of speech controls to the second system;
calculate a similarity indication between a first set of speech samples associated with a first attribute and a second set of speech samples associated with a second attribute;
display the similarity indication between the first set and the second set;
receive analytical results of the displayed similarity indication and generate an electronic report of the analytical results;
generate a language model regarding the first set based upon the speech samples included in the first set; and
calculate a perplexity regarding the first set using the language model regarding the first set;
wherein displaying the similarity indication includes displaying a graph where points corresponding to each of the plurality of speech controls are plotted so as to express the similarity indication and a circle is drawn, wherein the circle has one of the points as a center and indicates the perplexity for the speech control corresponding to the one of the points.
4. The first system according to claim 3 , wherein preparing the electronic report includes preparing an image of the graph in the electronic report.
5. At least one computer readable medium storing program code that, when executed by at least one processor, performs a method for creating a speech interface, the method comprising:
accessing, with a computer, a database that includes speech samples associated with any of a plurality of speech controls to a system;
calculating a similarity indication between a first set of speech samples associated with a first attribute and a second set of speech samples associated with a second attribute;
displaying the similarity indication between the first set and the second set;
receiving analytical results of the displayed similarity indication and generating an electronic report of the analytical results;
generating a language model regarding the first set based upon the speech samples included in the first set; and
calculating a perplexity regarding the first set using the language model regarding the first set;
wherein displaying the similarity indication includes displaying a graph where points corresponding to each of the plurality of speech controls are plotted so as to express the similarity indication and a circle is drawn, wherein the circle has one of the points as a center and indicates the perplexity for the speech control corresponding to the one of the points.
6. The at least one computer readable medium according to claim 5 , wherein the step of preparing the electronic report includes preparing an image of the graph in the electronic report.