公开(公告)号：US20230335116A1

公开(公告)日：2023-10-19

申请号：US18210963

申请日：2023-06-16

Applicant: GOOGLE LLC

Inventor： Meltem Oktem ,  Taral Pradeep Joglekar ,  Fnu Heryandi ,  Pu-sen Chao ,  Ignacio Lopez Moreno ,  Salil Rajadhyaksha ,  Alexander H. Gruenstein ,  Diego Melendo Casado

IPC: G10L15/08 ,  G06F21/32 ,  G10L15/22 ,  G10L17/00 ,  G06V40/10 ,  G10L17/06 ,  G10L15/07 ,  G06F16/635

CPC classification number: G10L15/08 ,  G06F16/636 ,  G06F21/32 ,  G06V40/10 ,  G10L15/07 ,  G10L15/22 ,  G10L17/00 ,  G10L17/06 ,  G10L2015/088 ,  G10L15/26

Abstract: In some implementations, processor(s) can receive an utterance from a speaker, and determine whether the speaker is a known user of a user device or not a known user of the user device. The user device can be shared by a plurality of known users. Further, the processor(s) can determine whether the utterance corresponds to a personal request or non-personal request. Moreover, and in response to determining that the speaker not a known user of the user device and in response to determining that the utterance corresponds to a non-personal request, the processor(s) can cause a response to the utterance to be provided for presentation to the speaker at the user device response to the utterance, or can cause an action to be performed by the user device responsive to the utterance.

公开(公告)号：US11373652B2

公开(公告)日：2022-06-28

申请号：US16874646

申请日：2020-05-14

Applicant: Google LLC

Inventor： Alexander H. Gruenstein ,  Taral Pradeep Joglekar ,  Vijayaditya Peddinti ,  Michiel A. u. Bacchiani

IPC: G10L15/22 ,  G10L15/08 ,  G10L25/51 ,  G10L15/30 ,  G10L15/06 ,  G10L17/22 ,  G10L17/00

Abstract: A method includes obtaining, by data processing hardware, a plurality of non-watermarked speech samples. Each non-watermarked speech does not include an audio watermark sample. The method includes, from each non-watermarked speech sample of the plurality of non-watermarked speech samples, generating one or more corresponding watermarked speech samples that each include at least one audio watermark. The method includes training, using the plurality of non-watermarked speech samples and corresponding watermarked speech samples, a model to determine whether a given audio data sample includes an audio watermark, and after training the model, transmitting the trained model to a user computing device.