公开(公告)号：US10367601B2

公开(公告)日：2019-07-30

申请号：US15236025

申请日：2016-08-12

Applicant: Google LLC

Inventor： Tina le Grand ,  Niklas Blum ,  Minyue Li ,  Henrik Lundin ,  Michael Tschumi ,  Alexander Narest

IPC: H03M13/00 ,  H04L1/00

Abstract: Control logic determines when a network condition has changed by evaluating network condition data. Based on a detected network condition change, the control logic reorders an encoder parameter controller execution sequence of a plurality of encoder parameter controllers. The control logic configures the plurality of reordered encoder parameter controllers so that an encoder parameter determination from a prior encoder parameter controller is used as a decision input for a subsequent encoder parameter controller. An encoder encodes data, such as audio data, video data or other type of data using the generated encoder control parameters from the reordered plurality of encoder parameter controllers. A related method is also disclosed.

公开(公告)号：US10269371B2

公开(公告)日：2019-04-23

申请号：US15720498

申请日：2017-09-29

Applicant: Google LLC

Inventor： Erik Kay ,  Jonas Erik Lindberg ,  Serge Lachapelle ,  Henrik Lundin

IPC: G10L21/00 ,  G10L21/043 ,  G10L21/0208 ,  H04L29/06 ,  G10L15/20 ,  G10L25/78 ,  G10L19/005 ,  G10L21/0232

Abstract: A computer-implemented technique can include establishing an audio communication session between first and second computing devices and obtaining, by the first computing device, an audio input signal using audio data captured by a microphone. The first computing device can analyze the audio input signal to detect a speech input by its first user and can determine a duration of a detection period from when the audio input signal was obtained until the analyzing has completed. The first computing device can then transmit, to the second computing device, (i) a portion of the audio input signal beginning at a start of the speech input and (ii) the detection period duration, wherein receipt of the portion of the audio input signal and the detection period duration causes the second computing device to accelerate playback of the portion of the audio input signal to compensate for the detection period duration.

公开(公告)号：US10290303B2

公开(公告)日：2019-05-14

申请号：US15246871

申请日：2016-08-25

Applicant: Google LLC

Inventor： Serge Lachapelle ,  Henrik Lundin

IPC: G10L19/005 ,  G10L25/87 ,  H04L12/835 ,  G10L21/045 ,  G10L25/78 ,  G10L25/90

Abstract: Computer-implemented techniques can include establishing, between first and second computing devices, an audio communication session via a network. The first computing device can receive and temporarily store audio packets corresponding to an audio input signal obtained by the second computing device. When the audio packets cause the buffer to fill beyond or at a rate exceeding a loss threshold indicative of a temporary loss of communication via the network, the techniques can decode the audio packets to obtain an audio output signal, determine whether the audio output signal includes speech, and when the audio output signal includes speech, remove a redundant portion of the audio output signal corresponding to a pitch period to obtain a modified audio output signal. The modified audio output signal can then be output via a speaker of the first computing device.