公开(公告)号：US12015736B2

公开(公告)日：2024-06-18

申请号：US18199711

申请日：2023-05-19

Applicant: GOOGLE LLC

Inventor： Cassandra Xia ,  Luis Carlos Cobo Rus

IPC: H04M3/428 ,  H04M1/72436 ,  H04M1/82

CPC classification number: H04M3/4286 ,  H04M1/72436 ,  H04M1/82 ,  H04M3/4285 ,  H04M2201/40

Abstract: Automated monitoring of a voice communication session, when the session is in an on hold status, to determine when the session is no longer in the on hold status. When it is determined that the session is no longer in the on hold status, user interface output is rendered that is perceptible to a calling user that initiated the session, and that indicates that the on hold status of the session has ceased. In some implementations, an audio stream of the session can be monitored to determine, based on processing of the audio stream, a candidate end of the on hold status. In response, a response solicitation signal is injected into an outgoing portion of the audio. The audio stream can be further monitored for a response (if any) to the response solicitation signal. The response (if any) can be processed to determine whether the end of the on hold status is an actual end of the on hold status.

公开(公告)号：US20230395069A1

公开(公告)日：2023-12-07

申请号：US18236302

申请日：2023-08-21

Applicant: GOOGLE LLC

Inventor： Ignacio Lopez Moreno ,  Luis Carlos Cobo Rus

IPC: G10L15/20 ,  G10L15/30 ,  G10L15/02 ,  G10L15/22

CPC classification number: G10L15/20 ,  G10L15/30 ,  G10L15/02 ,  G10L15/22 ,  G10L21/0208

Abstract: Speaker diarization techniques that enable processing of audio data to generate one or more refined versions of the audio data, where each of the refined versions of the audio data isolates one or more utterances of a single respective human speaker. Various implementations generate a refined version of audio data that isolates utterance(s) of a single human speaker by generating a speaker embedding for the single human speaker, and processing the audio data using a trained generative model—and using the speaker embedding in determining activations for hidden layers of the trained generative model during the processing. Output is generated over the trained generative model based on the processing, and the output is the refined version of the audio data.

公开(公告)号：US11336767B2

公开(公告)日：2022-05-17

申请号：US17120956

申请日：2020-12-14

Applicant: Google LLC

Inventor： Cassandra Xia ,  Luis Carlos Cobo Rus

IPC: H04M3/428 ,  H04M1/82 ,  H04M1/72436

Abstract: Automated monitoring of a voice communication session, when the session is in an on hold status, to determine when the session is no longer in the on hold status. When it is determined that the session is no longer in the on hold status, user interface output is rendered that is perceptible to a calling user that initiated the session, and that indicates that the on hold status of the session has ceased. In some implementations, an audio stream of the session can be monitored to determine, based on processing of the audio stream, a candidate end of the on hold status. In response, a response solicitation signal is injected into an outgoing portion of the audio. The audio stream can be further monitored for a response (if any) to the response solicitation signal. The response (if any) can be processed to determine whether the end of the on hold status is an actual end of the on hold status.

公开(公告)号：US20200344351A1

公开(公告)日：2020-10-29

申请号：US16610169

申请日：2018-06-28

Applicant: Google LLC

Inventor： Cassandra Xia ,  Luis Carlos Cobo Rus

IPC: H04M3/428 ,  H04M1/82 ,  H04M1/725

Abstract: Automated monitoring of a voice communication session, when the session is in an on hold status, to determine when the session is no longer in the on hold status. When it is determined that the session is no longer in the on hold status, user interface output is rendered that is perceptible to a calling user that initiated the session, and that indicates that the on hold status of the session has ceased. In some implementations, an audio stream of the session can be monitored to determine, based on processing of the audio stream, a candidate end of the on hold status. In response, a response solicitation signal is injected into an outgoing portion of the audio. The audio stream can be further monitored for a response (if any) to the response solicitation signal. The response (if any) can be processed to determine whether the end of the on hold status is an actual end of the on hold status.

公开(公告)号：US20230308542A1

公开(公告)日：2023-09-28

申请号：US18199711

申请日：2023-05-19

Applicant: GOOGLE LLC

Inventor： Cassandra Xia ,  Luis Carlos Cobo Rus

IPC: H04M3/428 ,  H04M1/82 ,  H04M1/72436

CPC classification number: H04M3/4286 ,  H04M1/72436 ,  H04M1/82 ,  H04M3/4285 ,  H04M2201/40

Abstract: Automated monitoring of a voice communication session, when the session is in an on hold status, to determine when the session is no longer in the on hold status. When it is determined that the session is no longer in the on hold status, user interface output is rendered that is perceptible to a calling user that initiated the session, and that indicates that the on hold status of the session has ceased. In some implementations, an audio stream of the session can be monitored to determine, based on processing of the audio stream, a candidate end of the on hold status. In response, a response solicitation signal is injected into an outgoing portion of the audio. The audio stream can be further monitored for a response (if any) to the response solicitation signal. The response (if any) can be processed to determine whether the end of the on hold status is an actual end of the on hold status.

公开(公告)号：US20220272191A1

公开(公告)日：2022-08-25

申请号：US17743126

申请日：2022-05-12

Applicant: GOOGLE LLC

Inventor： Cassandra Xia ,  Luis Carlos Cobo Rus

IPC: H04M3/428 ,  H04M1/82 ,  H04M1/72436

Abstract: Automated monitoring of a voice communication session, when the session is in an on hold status, to determine when the session is no longer in the on hold status. When it is determined that the session is no longer in the on hold status, user interface output is rendered that is perceptible to a calling user that initiated the session, and that indicates that the on hold status of the session has ceased. In some implementations, an audio stream of the session can be monitored to determine, based on processing of the audio stream, a candidate end of the on hold status. In response, a response solicitation signal is injected into an outgoing portion of the audio. The audio stream can be further monitored for a response (if any) to the response solicitation signal. The response (if any) can be processed to determine whether the end of the on hold status is an actual end of the on hold status.

公开(公告)号：US20210217411A1

公开(公告)日：2021-07-15

申请号：US17215129

申请日：2021-03-29

Applicant: Google LLC

Inventor： Ignacio Lopez Moreno ,  Luis Carlos Cobo Rus

IPC: G10L15/20 ,  G10L15/30 ,  G10L15/02

Abstract: Speaker diarization techniques that enable processing of audio data to generate one or more refined versions of the audio data, where each of the refined versions of the audio data isolates one or more utterances of a single respective human speaker. Various implementations generate a refined version of audio data that isolates utterance(s) of a single human speaker by generating a speaker embedding for the single human speaker, and processing the audio data using a trained generative model—and using the speaker embedding in determining activations for hidden layers of the trained generative model during the processing. Output is generated over the trained generative model based on the processing, and the output is the refined version of the audio data.

公开(公告)号：US20240340373A1

公开(公告)日：2024-10-10

申请号：US18745469

申请日：2024-06-17

Applicant: GOOGLE LLC

Inventor： Cassandra Xia ,  Luis Carlos Cobo Rus

IPC: H04M3/428 ,  H04M1/72436 ,  H04M1/82

CPC classification number: H04M3/4286 ,  H04M1/72436 ,  H04M1/82 ,  H04M3/4285 ,  H04M2201/40

Abstract: Automated monitoring of a voice communication session, when the session is in an on hold status, to determine when the session is no longer in the on hold status. When it is determined that the session is no longer in the on hold status, user interface output is rendered that indicates that the on hold status of the session has ceased. In some implementations, an audio stream of the session can be monitored to determine, based on processing of the audio stream, a candidate end of the on hold status. In response, a response solicitation signal is injected into an outgoing portion of the audio. The audio stream can be further monitored for a response (if any) to the response solicitation signal. The response (if any) can be processed to determine whether the end of the on hold status is an actual end of the on hold status.

公开(公告)号：US11677871B2

公开(公告)日：2023-06-13

申请号：US17743126

申请日：2022-05-12

Applicant: GOOGLE LLC

Inventor： Cassandra Xia ,  Luis Carlos Cobo Rus

IPC: H04M3/428 ,  H04M1/82 ,  H04M1/72436

CPC classification number: H04M3/4286 ,  H04M1/72436 ,  H04M1/82 ,  H04M3/4285 ,  H04M2201/40

Abstract: Automated monitoring of a voice communication session, when the session is in an on hold status, to determine when the session is no longer in the on hold status. When it is determined that the session is no longer in the on hold status, user interface output is rendered that is perceptible to a calling user that initiated the session, and that indicates that the on hold status of the session has ceased. In some implementations, an audio stream of the session can be monitored to determine, based on processing of the audio stream, a candidate end of the on hold status. In response, a response solicitation signal is injected into an outgoing portion of the audio. The audio stream can be further monitored for a response (if any) to the response solicitation signal. The response (if any) can be processed to determine whether the end of the on hold status is an actual end of the on hold status.

公开(公告)号：US20210099575A1

公开(公告)日：2021-04-01

申请号：US17120956

申请日：2020-12-14

Applicant: Google LLC

Inventor： Cassandra Xia ,  Luis Carlos Cobo Rus

IPC: H04M3/428 ,  H04M1/725 ,  H04M1/82

Abstract: Automated monitoring of a voice communication session, when the session is in an on hold status, to determine when the session is no longer in the on hold status. When it is determined that the session is no longer in the on hold status, user interface output is rendered that is perceptible to a calling user that initiated the session, and that indicates that the on hold status of the session has ceased. In some implementations, an audio stream of the session can be monitored to determine, based on processing of the audio stream, a candidate end of the on hold status. In response, a response solicitation signal is injected into an outgoing portion of the audio. The audio stream can be further monitored for a response (if any) to the response solicitation signal. The response (if any) can be processed to determine whether the end of the on hold status is an actual end of the on hold status.