Method and apparatus for response using voice matching user category

Patent metadata

Field	Value
Publication number	US-11475897-B2
Application number	US-201916505648-A
Country	US
Kind code	B2
Filing date	Jul 8, 2019
Priority date	Aug 30, 2018
Publication date	Oct 18, 2022
Grant date	Oct 18, 2022

Abstract

A response method and an apparatus thereof are provided. The method includes: receiving voice information sent through a client by a user; determining, based on the voice information, a user category to which the user belongs; and using voice matching the user category to respond to the voice information. Accordingly, response voice matches the user category of the user, which implements that the response is performed using the response voice targeted for the user category, and thus, the user experience may be improved.

First claim

What is claimed is:

1. A response method, wherein the method comprises:
receiving voice information sent through a client by a user;
determining, based on the voice information, an output user category to which the user belongs, wherein voices and voice parameters matching user categories are pre-stored, the voice parameters comprising at least one of a sound spectrum, a fundamental frequency, a pitch, or a sound intensity; and
using a voice matching the output user category to respond to the voice information, wherein the using the voice matching the output user category to respond to the voice information comprises:
determining that the voice information includes a polite term, and
playing a preset polite term expressing thanks by using the voice, in response to determining the voice information including the polite term, wherein the using the voice matching the output user category to respond to the voice information comprises:
analyzing semantics of the voice information;
acquiring a plurality of pieces of chat information from the Internet;
determining, from the plurality of pieces of chat information, conversation information including semantics identical to the semantics of the voice information;
extracting a response from the conversation information; and
playing the response using the voice.

2. The method according to claim 1 , wherein the determining, based on the voice information, an output user category to which the user belongs comprises:
inputting the voice information into a pre-trained user category recognition model, and determining the output user category to which the user belongs according to an output of the user category recognition model.

3. The method according to claim 1 , wherein the using voice matching the user category to respond to the voice information comprises:
analyzing semantics of the voice information;
determining response information matching the semantics; and
playing the response information using the voice.

4. The method according to claim 1 , wherein the output user category refers to a child user, and the method further comprises:
pushing multimedia information matching the child user to the user.

5. A response apparatus, wherein the apparatus comprises:
at least one processor; and
a memory storing instructions, wherein the instructions when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising:
receiving voice information sent through a client by a user;
determining, based on the voice information, an output user category to which the user belongs, wherein voices and voice parameters matching user categories are pre-stored, the voice parameters comprising at least one of a sound spectrum, a fundamental frequency, a pitch, or a sound intensity; and
using a voice matching the output user category to respond to the voice information, wherein the using the voice matching the output user category to respond to the voice information comprises:
determining that the voice information includes a polite term, and
playing a preset polite term expressing thanks by using the voice, in response to determining the voice information including the polite term, wherein the using the voice matching the output user category to respond to the voice information comprises:
analyzing semantics of the voice information;
acquiring a plurality of pieces of chat information from the Internet;
determining, from the plurality of pieces of chat information, conversation information including semantics identical to the semantics of the voice information;
extracting a response from the conversation information; and
playing the response using the voice.

6. The apparatus according to claim 5 , wherein the determining, based on the voice information, an output user category to which the user belongs comprises:
inputting the voice information into a pre-trained user category recognition model, and determine the output user category to which the user belongs according to an output of the user category recognition model.

7. The apparatus according to claim 5 , wherein the using voice matching the user category to respond to the voice information comprises:
analyzing semantics of the voice information;
determining response information matching the semantics; and
playing the response information using the voice.

8. The apparatus according to claim 5 , wherein the output user category refers to a child user, and the operations further comprise:
pushing multimedia information matching the child user to the user.

9. A non-transitory computer readable medium, storing a computer program, wherein the program, when executed by a processor, causes the processor to perform operations, wherein the operations comprise:
receiving voice information sent through a client by a user;
determining, based on the voice information, an output user category to which the user belongs, wherein voices and voice parameters matching user categories are pre-stored, the voice parameters comprising at least one of a sound spectrum, a fundamental frequency, a pitch, or a sound intensity; and
using a voice matching the output user category to respond to the voice information, wherein the using the voice matching the output user category to respond to the voice information comprises:
determining that the voice information includes a polite term, and
playing a preset polite term expressing thanks by using the voice, in response to determining the voice information including the polite term, wherein the using the voice matching the output user category to respond to the voice information comprises:
analyzing semantics of the voice information;
acquiring a plurality of pieces of chat information from the Internet;
determining, from the plurality of pieces of chat information, conversation information including semantics identical to the semantics of the voice information;
extracting a response from the conversation information; and
playing the response using the voice.

10. The method according to claim 1 , wherein the output voice parameter includes the sound spectrum, the fundamental frequency, the pitch, and the sound intensity, matching the output user category.

11. The method according to claim 1 , wherein an interval corresponding to an acoustic characteristic having a commonality for a plurality of users in a given age range is acquired in advance by performing statistics, wherein the determining comprising: extracting a characteristic value of an acoustic characteristic of a user, determining that the interval includes the characteristic value, and determining the user category to which the user belongs based on the given age range, wherein the acoustic characteristic includes a time length, a fundamental frequency, energy, a formant frequency, wideband, a frequency perturbation, an amplitude perturbation, a zero-crossing rate, and a Mel frequency cepstral parameter.

12. The method according to claim 1 , wherein the using comprises: determining an output voice and an output voice parameter matching the output user category from the voices and the voice parameters matching user categories, and outputting the output voice with the output voice parameter, wherein the output voice parameter includes a sound spectrum, a fundamental frequency, a pitch, and a sound intensity, matching the output user category, and the output voice with the output voice parameter sounds identical or similar to a true voice of the user of the output user category.

Assignees

• Baidu online network technology beijing co ltd

Inventors

• Wang Wenyu

Classifications

• G06F3/167 Primary

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title

• G10L13/04

  Details of speech synthesis systems, e.g. synthesiser structure or memory management · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G10L13/00

  Speech synthesis; Text to speech systems · CPC title

• G10L17/00 Primary

  Speaker identification or verification techniques · CPC title