GENERATING RESPONSE IN CONVERSATION - MICROSOFT TECHNOLOGY LICENSING LLC

Title:

GENERATING RESPONSE IN CONVERSATION

Document Type and Number:

WIPO Patent Application WO/2019/200584

Kind Code:

A1

Abstract:

The present disclosure provides method and apparatus for generating a response in a human-machine conversation. A first sound input may be received in the conversation. A first audio attribute may be extracted from the first sound input, wherein the first audio attribute indicates a first condition of a user. A second sound input may be received in the conversation. A second audio attribute may be extracted from the second sound input, wherein the second audio attribute indicates a second condition of a user. A difference between the second audio attribute and the first audio attribute is determined, wherein the difference indicates a condition change of the user from the first condition to the second condition. A response to the second sound input is generated based at least on the condition change.

More Like This:

JP6861398	Information processing method and information processing device
WO/2021/247205	SENTIMENT AWARE VOICE USER INTERFACE
WO/2022/198923	SPEECH EMOTION RECOGNITION METHOD AND SYSTEM USING FUSION OF CROWD INFORMATION

Inventors:

LUAN JIAN (US)
XIAO ZHE (US)
NA XINGYU (US)
XIU CHI (US)
JU JIANZHONG (US)
XU XIANG (US)

Application Number:

PCT/CN2018/083735

Publication Date:

October 24, 2019

Filing Date:

April 19, 2018

Export Citation:

Click for automatic bibliography generation Help

Assignee:

MICROSOFT TECHNOLOGY LICENSING LLC (US)
LUAN JIAN (CN)
XIAO ZHE (CN)
NA XINGYU (CN)
XIU CHI (CN)
JU JIANZHONG (CN)
XU XIANG (CN)

International Classes:

G10L25/63; G10L15/22

Foreign References:

CN106373569A	2017-02-01
CN106910513A	2017-06-30
CN107636648A	2018-01-26
US20180024991A1	2018-01-25

Other References: