MULTI-PHRASE RESPONDING IN FULL DUPLEX VOICE CONVERSATION

Title:

MULTI-PHRASE RESPONDING IN FULL DUPLEX VOICE CONVERSATION

Document Type and Number:

WIPO Patent Application WO/2020/082309

Kind Code:

A1

Abstract:

The present disclosure provides method and apparatus for responding in a voice conversation by an electronic conversational agent. A voice input may be received in an audio upstream. In response to the voice input, a primary response and at least one supplementary response may be generated. A primary voice output may be generated based on the primary response. At least one supplementary voice output may be generated based on the at least one supplementary response. The primary voice output and the at least one supplementary voice output may be provided in an audio downstream, wherein the at least one supplementary voice output is provided during a time period adjacent to the primary voice output in the audio downstream.

More Like This:

JP3298858	SIMILARITY METHOD OF DIVISION BASE FOR LOW COMPLEXITY SPEECH RECOGNIZER
JP2004101963	METHOD FOR CORRECTING SPEECH RECOGNITION RESULT AND COMPUTER PROGRAM FOR CORRECTING SPEECH RECOGNITION RESULT
JP2006084942	CONVERSION INFORMATION GENERATING METHOD, PHONEME GROUP GENERATING METHOD, VOICE RECOGNITION METHOD AND DEVICE FOR THE ABOVE METHODS AND PROGRAM

Inventors:

ZHOU LI (US)

Application Number:

PCT/CN2018/111968

Publication Date:

April 30, 2020

Filing Date:

October 25, 2018

Export Citation:

Click for automatic bibliography generation Help

Assignee:

MICROSOFT TECHNOLOGY LICENSING LLC (US)
ZHOU LI (CN)

International Classes:

G10L15/18

Foreign References:

US20050288930A1	2005-12-29
CN101169684A	2008-04-30
CN103292437A	2013-09-11
US10304013B2	2019-05-28
US10277590B2	2019-04-30
US20050288930A1	2005-12-29

Other References: