公开(公告)号：US11721347B1

公开(公告)日：2023-08-08

申请号：US17362301

申请日：2021-06-29

Applicant: Amazon Technologies, Inc.

Inventor： Stanislaw Ignacy Pasko ,  Pawel Zelazko ,  Cagdas Bak ,  Eli Joshua Fidler ,  Michal Kowalczuk ,  Andrew Oberlin ,  Ariya Rastrow

IPC: G10L17/26 ,  G10L15/183 ,  G10L15/34 ,  G10L15/22

CPC classification number: G10L17/26 ,  G10L15/183 ,  G10L15/22 ,  G10L15/34

Abstract: Some speech processing systems may handle some commands on-device rather than sending the audio data to a second device or system for processing. The first device may have limited speech processing capabilities sufficient for handling common language and/or commands, while the second device (e.g., an edge device and/or a remote system) may call on additional language models, entity libraries, skill components, etc. to perform additional tasks. An intermediate data generator may facilitate dividing speech processing operations between devices by generating a stream of data that includes a first-pass ASR output (e.g., a word or sub-word lattice) and other characteristics of the audio data such as whisper detection, speaker identification, media signatures, etc. The second device can perform the additional processing using the data stream; e.g., without using the audio data. Thus, privacy may be enhanced by processing the audio data locally without sending it to other devices/systems.

公开(公告)号：US12170086B1

公开(公告)日：2024-12-17

申请号：US17525050

申请日：2021-11-12

Applicant: Amazon Technologies, Inc.

Inventor： Ashwin Venkatesh Raman ,  Bruno Dufour ,  Sasi Kiran Vepanjeri Lokanadha Reddy ,  Michal Kowalczuk ,  Maciej Grabon ,  Maciej Makowski ,  Fabian Andreas Bumberger

IPC: G10L15/22 ,  G06F3/16 ,  G06F8/65 ,  G06F9/445 ,  G06F9/54 ,  G10L15/00 ,  G10L15/19 ,  H04L67/14 ,  H04L67/56

Abstract: A speech interface device is configured to switch between languages, at the request of a user, in order to locally process utterances spoken in different languages, even in instances when a remote system is unavailable to, slower than, or otherwise less preferred than the speech interface device. For example, a user can request to set the language setting of the speech interface device to a second language, different from a first language to which the language setting of the device is currently set. Based on this user request, a local speech processing component of the device may load a language model(s) associated with the second language. The speech interface can also output voice prompts in the second language to manage the user's experience while a language update is in progress on the speech interface device.

公开(公告)号：US20240029743A1

公开(公告)日：2024-01-25

申请号：US18206231

申请日：2023-06-06

Applicant: Amazon Technologies, Inc.

Inventor： Stanislaw Ignacy Pasko ,  Pawel Zelazko ,  Cagdas Bak ,  Eli Joshua Fidler ,  Michal Kowalczuk ,  Andrew Oberlin ,  Ariya Rastrow

IPC: G10L17/26 ,  G10L15/183 ,  G10L15/34 ,  G10L15/22

CPC classification number: G10L17/26 ,  G10L15/183 ,  G10L15/34 ,  G10L15/22

Abstract: Some speech processing systems may handle some commands on-device rather than sending the audio data to a second device or system for processing. The first device may have limited speech processing capabilities sufficient for handling common language and/or commands, while the second device (e.g., an edge device and/or a remote system) may call on additional language models, entity libraries, skill components, etc. to perform additional tasks. An intermediate data generator may facilitate dividing speech processing operations between devices by generating a stream of data that includes a first-pass ASR output (e.g., a word or sub-word lattice) and other characteristics of the audio data such as whisper detection, speaker identification, media signatures, etc. The second device can perform the additional processing using the data stream; e.g., without using the audio data. Thus, privacy may be enhanced by processing the audio data locally without sending it to other devices/systems.

公开(公告)号：US11176934B1

公开(公告)日：2021-11-16

申请号：US16362408

申请日：2019-03-22

Applicant: Amazon Technologies, Inc.

Inventor： Ashwin Venkatesh Raman ,  Bruno Dufour ,  Sasi Kiran Vepanjeri Lokanadha Reddy ,  Michal Kowalczuk ,  Maciej Grabon ,  Maciej Makowski ,  Fabian Andreas Bumberger

IPC: G10L15/22 ,  G10L15/00 ,  G06F3/16 ,  G10L15/19

Abstract: A speech interface device is configured to switch between languages, at the request of a user, in order to locally process utterances spoken in different languages, even in instances when a remote system is unavailable to, slower than, or otherwise less preferred than the speech interface device. For example, a user can request to set the language setting of the speech interface device to a second language, different from a first language to which the language setting of the device is currently set. Based on this user request, a local speech processing component of the device may load a language model(s) associated with the second language. The speech interface can also output voice prompts in the second language to manage the user's experience while a language update is in progress on the speech interface device.