公开(公告)号：US12182674B2

公开(公告)日：2024-12-31

申请号：US17737017

申请日：2022-05-04

Applicant: Apple Inc.

Inventor： Jonathan Huang ,  Miquel Espi Marques ,  Carlos M. Avendano ,  Kevin M. Durand ,  David Findlay ,  Vasudha Kowtha ,  Daniel C. Klingler ,  Yichi Zhang

IPC: G10L15/16 ,  G06F3/16 ,  G06N20/00 ,  G08B21/18 ,  G10L15/06 ,  H04R1/08 ,  H04R29/00

Abstract: The subject disclosure provides systems and methods for providing locally trained models for detecting individual sounds using electronic devices. Local detection of individual sounds with a detection model at an electronic device can be provided by obtaining training samples for the detection model with the electronic device, and generating additional negative and positive training samples based on the obtained training samples. A two-stage detection process may be provided, in which a trigger model at a device compares an audio input to a reference sound to trigger a detection model at the device. The detection of individual sounds with a detection model at an electronic device can also leverage audio capture capabilities of multiple devices in an acoustic scene to capture multiple concurrent training samples.

公开(公告)号：US20240363094A1

公开(公告)日：2024-10-31

申请号：US18622449

申请日：2024-03-29

Applicant: Apple Inc.

Inventor： Ashok Masilamani ,  Prateek Murgai ,  John Woodruff ,  David M. Fischer ,  Jonathan D. Sheaffer ,  Jonathan Huang ,  Sorin V. Dusan ,  Andrew W. Malta ,  Erik D. Hornberger ,  Yichi Zhang ,  Miquel Espi Marques ,  Carlos M. Avendano

IPC: G10K11/178 ,  G10L21/0208 ,  G10L21/0216 ,  G10L21/0308 ,  H04R1/10 ,  H04R3/00

CPC classification number: G10K11/17854 ,  G10K11/17823 ,  G10K11/17827 ,  G10K11/17881 ,  G10K11/17885 ,  G10L21/0208 ,  G10L21/0308 ,  H04R1/1041 ,  H04R3/005 ,  G10K2210/1081 ,  G10L2021/02166 ,  H04R2460/01 ,  H04R2460/13

Abstract: A conversation detector processes microphone signals and other sensor signals of a headphone to declare a conversation and configures a filter block to activate a transparency audio signal. It then declares an end to the conversation based on processing one or more of the microphone signals and the other sensor signals, and in response deactivates the transparency audio signal. The conversation detector monitors an idle duration in which an OVAD and a TVAD are both or simultaneously indicating no activity and declares the end to the conversation in response to the idle duration being longer than an idle threshold. Other aspects are also described and claimed.