Methods and systems for adapting a speech system based on user characteristics
View Patent ↗Methods and systems are provided for adapting a speech system. In one example a method includes: logging speech data from the speech system; detecting a user characteristic from the speech data; and selectively updating a language model based on the user characteristic.
1. A method of adapting a speech system, comprising:
logging speech data from the speech system;
processing the speech data, by a plurality of characteristic detector modules, to detect a plurality of user characteristics from the speech data, the plurality of characteristic detector modules each map the speech data into at least one category associated with at least one user characteristic of the plurality of user characteristics, the user characteristics comprise characteristics that are specific to behavior of a user of a vehicle when saying a command to an automated system;
tracking a frequency of each of the plurality of user characteristics; and
when the frequency of at least one of the plurality of user characteristics reaches a certain frequency, selecting a language model associated with the user of the vehicle, and updating the language model based on the categories of the plurality of the user characteristics.
2. The method of claim 1 wherein the speech data comprises a spoken command uttered by a user when interacting with the speech system and a performance of the spoken command.
3. The method of claim 1 wherein the updating the language model comprises generating a new language model based on the plurality of user characteristics.
4. The method of claim 1 wherein the updating the language model comprises combining a plurality of language models associated with the plurality of user characteristics with at least one other language model.
5. The method of claim 1 wherein the user characteristics comprise at least one of a verbosity detected by a percentage of decoration or non-functional words, an information distribution detected by a delivery method of information, and a domain distribution detected by a domain historic behavior.
6. The method of claim 1 wherein the user characteristics comprise at least one of a politeness, and a formality level.
7. The method of claim 1 wherein the user characteristics comprise at least one of an age, a dialect, and a gender.
8. A system for adapting a speech system, comprising:
a computer readable medium comprising:
a first module that, by a processor, logs speech data from the speech system;
a second module that, by a processor, processes the speech data to detect by a plurality of characteristic detector modules a plurality of user characteristics from the speech data, the plurality of characteristic detector modules each map the speech data into at least one category associated with at least one user characteristic of the plurality of user characteristics, and track a frequency of each of the plurality of user characteristics, the user characteristics comprise characteristics that are specific to behavior of a user of a vehicle when saying a command to an automated system; and
a third module that, by a processor, when the frequency of at least one of the plurality of user characteristics reaches a certain frequency, selects a language model associated with the user of the vehicle, and updates the language model based on the categories of the plurality of the user characteristics.
9. The system of claim 8 wherein the speech data comprises a spoken command uttered by a user when interacting with the speech system and a performance of the spoken command.
10. The system of claim 8 wherein the third module updates the language model by generating a new language model based on the plurality of user characteristics.
11. The system of claim 8 wherein the third module updates the language model by combining a plurality of language models associated with the plurality of user characteristics with at least one other language model.
12. The system of claim 8 wherein the plurality of user characteristics comprise at least one of a verbosity, an information distribution, and a domain distribution.
13. The system of claim 8 wherein the plurality of user characteristics comprise at least one of a politeness, and a formality level.
14. The system of claim 8 wherein the plurality of user characteristics comprise at least one of an age, a dialect, and a gender.