Michael Aaron Newman

US Patent:

20210158812, May 27, 2021

Filed:

Nov 26, 2019

Appl. No.:

16/696849

Inventors:

- Redmond WA, US
Steven Andrew WEGMANN - Berkeley CA, US
Michael Jack NEWMAN - Somerville MA, US
David Leo Wright HALL - Berkeley CA, US
Jean CRAWFORD - Cambridge MA, US
Laurence Steven GILLICK - Newton MA, US

Assignee:

Microsoft Technology Licensing, LLC - Redmond WA

International Classification:

G10L 15/22
G10L 15/197
G10L 15/05
G10L 15/18

Abstract:

A method of automatically delineating turns in a multi-turn dialogue between a user and a conversational computing interface. Audio data encoding speech of the user in the multi-turn dialogue is received. The audio data is analyzed to recognize, in the speech of the user, an utterance followed by a silence. The utterance is recognized as a last utterance in a turn of the multi-turn dialogue responsive to the silence exceeding a context-dependent duration dynamically updated based on a conversation history of the multi-turn dialogue and features of the received audio, wherein the conversation history includes one or more previous turns of the multi-turn dialogue taken by the user and one or more previous turns of the multi-turn dialogue taken by the conversational computing interface.