System and method for enhancing voice-enabled search based on automated demographic identification
View Patent ↗Disclosed herein are systems, methods, and non-transitory computer-readable storage media for approximating responses to a user speech query in voice-enabled search based on metadata that include demographic features of the speaker. A system practicing the method recognizes received speech from a speaker to generate recognized speech, identifies metadata about the speaker from the received speech, and feeds the recognized speech and the metadata to a question-answering engine. Identifying the metadata about the speaker is based on voice characteristics of the received speech. The demographic features can include age, gender, socio-economic group, nationality, and/or region. The metadata identified about the speaker from the received speech can be combined with or override self-reported speaker demographic information.
1. A method performed by a speech recognition system, the method comprising:
receiving recognized speech;
identifying information about a speaker of the recognized speech from the recognized speech;
generating confidence scores indicating degrees of certainty of the identified information; and
submitting the recognized speech, the information, and the confidence scores to a question-answering engine integrated with the speech recognition system, which outputs a response associated with the recognized speech using the recognized speech, the information, and the confidence scores.
2. The method of claim 1 , wherein the information comprises demographic features.
3. The method of claim 2 , wherein the demographic features comprise one of age, gender, socio-economic group, nationality, and origin.
4. The method of claim 1 , wherein identifying of the information is based on voice characteristics of the recognized speech.
5. The method of claim 1 , further comprising storing the information for future use.
6. The method of claim 5 , wherein the storing of the information is performed in accordance with a privacy policy.
7. The method of claim 1 , wherein the response comprises audible speech.
8. A speech recognition system comprising:
a processor; and
a computer-readable storage medium having instruction stored which, when executed by the processor, result in the processor performing operations comprising:
receiving recognized speech;
identifying information about a speaker of the recognized speech from the recognized speech;
generating confidence scores indicating degrees of certainty of the identified information; and
submitting the recognized speech, the information, and the confidence scores to a question-answering engine integrated with the speech recognition system, which outputs a response associated with the recognized speech using the recognized speech, the information, and the confidence scores.
9. The system of claim 8 , wherein the information comprises demographic features.
10. The system of claim 9 , wherein the demographic features comprise one of age, gender, socio-economic group, nationality, and origin.
11. The system of claim 8 , wherein identifying of the information is based on voice characteristics of the recognized speech.
12. The system of claim 8 , the computer-readable storage medium having additional instructions which result in the operations further comprising storing the information for future use.
13. The system of claim 12 , wherein the storing of the information is performed in accordance with a privacy policy.
14. A non-transitory computer-readable storage medium having instruction stored which, when executed by a computing device, result in the computing device performing operations comprising:
receiving recognized speech at a speech recognition system;
identifying information about a speaker of the recognized speech from the recognized speech;
generating confidence scores indicating degrees of certainty of the identified information; and
submitting the recognized speech, the information, and the confidence scores to a question-answering engine integrated with the speech recognition system, which outputs a response associated with the recognized speech using the recognized speech, the information, and the confidence scores.
15. The non-transitory computer-readable storage medium of claim 14 , wherein the information comprises demographic features.
16. The non-transitory computer-readable storage medium of claim 15 , wherein the demographic features comprise one of age, gender, socio-economic group, nationality, and origin.
17. The non-transitory computer-readable storage medium of claim 14 , wherein identifying of the information is based on voice characteristics of the recognized speech.