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.

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：US10084921B2

公开(公告)日：2018-09-25

申请号：US15653324

申请日：2017-07-18

Applicant: GOOGLE LLC

Inventor： Serge Lachapelle ,  Alexander Kjeldaas

IPC: H04M3/56 ,  H04L29/06 ,  A61N1/05 ,  A61B17/50 ,  A61B17/3207 ,  A61B17/3203 ,  A61B17/3211 ,  A61B18/24 ,  A61B90/00 ,  G10L21/00 ,  G10L17/00 ,  A61B17/32

CPC classification number: H04M3/568 ,  A61B17/3203 ,  A61B17/3207 ,  A61B17/320725 ,  A61B17/3211 ,  A61B17/50 ,  A61B18/245 ,  A61B90/02 ,  A61B2017/320044 ,  A61N1/056 ,  G10L21/00 ,  H04L65/403

Abstract: Systems and methods are provided for handling concurrent speech in which temporally overlapping first speech data and second speech data is received from respective first and second participants of a session. A speech policy applied to the speech data specifies dropping the second speech when it interrupts the first speech within a first interval of the first speech data. The first interval is temporally bounded by the beginning of the first speech and a first predetermined amount of time after the beginning of the first speech. The speech policy specifies outputting the first speech data and then outputting the second speech data when the second speech data interrupts a second interval of the first speech data. The second interval of the first speech data is temporally bounded by the end of the first speech data and a second predetermined amount of time before the end of the first speech data.