-
公开(公告)号:US20200066258A1
公开(公告)日:2020-02-27
申请号:US16665461
申请日:2019-10-28
Applicant: Amazon Technologies, Inc.
Inventor: James David Meyers , Kurt Wesley Piersol
IPC: G10L15/08 , G10L15/20 , G10L21/028 , G10L15/04
Abstract: Systems and methods for selectively ignoring an occurrence of a wakeword within audio input data is provided herein. In some embodiments, a wakeword may be detected to have been uttered by an individual within a modified time window, which may account for hardware delays and echoing offsets. The detected wakeword that occurs during this modified time window may, in some embodiments, correspond to a word included within audio that is outputted by a voice activated electronic device. This may cause the voice activated electronic device to activate itself, stopping the audio from being outputted. By identifying when these occurrences of the wakeword within outputted audio are going to happen, the voice activated electronic device may selectively determine when to ignore the wakeword, and furthermore, when not to ignore the wakeword.
-
公开(公告)号:US09691378B1
公开(公告)日:2017-06-27
申请号:US14934069
申请日:2015-11-05
Applicant: Amazon Technologies, Inc.
Inventor: James David Meyers , Kurt Wesley Piersol
IPC: G10L15/04 , G10L15/20 , G10L21/0208 , G10L21/028 , G10L15/08
CPC classification number: G10L15/08 , G10L15/04 , G10L15/20 , G10L15/22 , G10L21/028 , G10L2015/088 , G10L2021/02082
Abstract: Systems and methods for selectively ignoring an occurrence of a wakeword within audio input data is provided herein. In some embodiments, a wakeword may be detected to have been uttered by an individual within a modified time window, which may account for hardware delays and echoing offsets. The detected wakeword that occurs during this modified time window may, in some embodiments, correspond to a word included within audio that is outputted by a voice activated electronic device. This may cause the voice activated electronic device to activate itself, stopping the audio from being outputted. By identifying when these occurrences of the wakeword within outputted audio are going to happen, the voice activated electronic device may selectively determine when to ignore the wakeword, and furthermore, when not to ignore the wakeword.
-
公开(公告)号:US20190156818A1
公开(公告)日:2019-05-23
申请号:US16256376
申请日:2019-01-24
Applicant: Amazon Technologies, Inc.
Inventor: Kurt Wesley Piersol , Gabriel Beddingfield
Abstract: A system for capturing and processing portions of a spoken utterance command that may occur before a wakeword. The system buffers incoming audio and indicates locations in the audio where the utterance changes, for example when a long pause is detected. When the system detects a wakeword within a particular utterance, the system determines the most recent utterance change location prior to the wakeword and sends the audio from that location to the end of the command utterance to a server for further speech processing.
-
公开(公告)号:US09558758B1
公开(公告)日:2017-01-31
申请号:US14713300
申请日:2015-05-15
Applicant: Amazon Technologies, Inc.
Inventor: Kurt Wesley Piersol , Michael Alan Pogue
CPC classification number: G10L25/60 , G10L15/01 , G10L15/20 , G10L2021/02082 , H04B3/20 , H04B3/23 , H04M9/08 , H04M9/082 , H04R3/005 , H04R27/00 , H04R2227/003 , H04R2227/009
Abstract: A speech-controlled appliance that provides a user with an indication of when a speech input will likely not be acted upon by the device due to a poor signal-to-noise conditions. The device may provide this indication even without a speech input, so that the user may be informed that a command will not be acted upon before speaking the command. The indication may be, for example, lighting a visual indicator on the device, and/or outputting an audible notification via a speaker. The visual indicator may be a same indicator the device uses to indicate when its microphone(s) are muted so that the user will intuitively recognize that a speech command will not be acted upon by the device.
Abstract translation: 一种语音控制设备,其为用户提供了由于信号噪声条件差而导致语音输入何时可能不被设备作用的指示。 即使没有语音输入,设备也可以提供该指示,使得用户可以在通话之前不会对命令进行操作。 该指示可以是例如照亮设备上的视觉指示器,和/或经由扬声器输出可听见的通知。 视觉指示器可以是设备用于指示其麦克风何时被静音的相同指示符,使得用户将直观地认识到语音命令不会被设备作用。
-
公开(公告)号:US09293134B1
公开(公告)日:2016-03-22
申请号:US14502103
申请日:2014-09-30
Applicant: Amazon Technologies, Inc.
Inventor: Shirin Saleem , Shamitha Somashekar , Aimee Therese Piercy , Kurt Wesley Piersol , Marcello Typrin
Abstract: A speech system may be configured to operate in conjunction with a stationary base device and a handheld remote device to receive voice commands from a user. Voice commands may be directed either to the base device or to the handheld device. When performing automatic speech recognition (ASR), natural language understanding (NLU), dialog management, text-to-speech (TTS) conversion, and other speech-related tasks, the system may utilize various models, including ASR models, NLU models, dialog models, and TTS models. Different models may be used depending on whether the user has chosen to speak into the base device or the handheld audio device. The different models may be designed to accommodate the different characteristics of audio and speech that are present in audio provided by the two different components and the different characteristics of the environmental situation of the user.
Abstract translation: 语音系统可以被配置为与固定基站设备和手持远程设备结合操作以从用户接收语音命令。 语音命令可以被引导到基本设备或手持设备。 当进行自动语音识别(ASR),自然语言理解(NLU),对话管理,文本到语音(TTS)转换和其他语音相关任务时,系统可以利用各种模型,包括ASR模型,NLU模型, 对话模型和TTS模型。 可以使用不同的型号,这取决于用户是否选择对基本设备或手持音频设备进行说话。 可以将不同的模型设计为适应由两个不同组件提供的音频中存在的音频和语音的不同特征以及用户的环境状况的不同特征。
-
公开(公告)号:US12094455B2
公开(公告)日:2024-09-17
申请号:US18242860
申请日:2023-09-06
Applicant: Amazon Technologies, Inc.
Inventor: James David Meyers , Kurt Wesley Piersol
IPC: G10L15/08 , G10L15/04 , G10L15/20 , G10L15/22 , G10L21/0208 , G10L21/028
CPC classification number: G10L15/08 , G10L15/04 , G10L15/20 , G10L21/028 , G10L2015/088 , G10L15/22 , G10L2021/02082
Abstract: Systems and methods for selectively ignoring an occurrence of a wakeword within audio input data is provided herein. In some embodiments, a wakeword may be detected to have been uttered by an individual within a modified time window, which may account for hardware delays and echoing offsets. The detected wakeword that occurs during this modified time window may, in some embodiments, correspond to a word included within audio that is outputted by a voice activated electronic device. This may cause the voice activated electronic device to activate itself, stopping the audio from being outputted. By identifying when these occurrences of the wakeword within outputted audio are going to happen, the voice activated electronic device may selectively determine when to ignore the wakeword, and furthermore, when not to ignore the wakeword.
-
公开(公告)号:US20240112669A1
公开(公告)日:2024-04-04
申请号:US18242860
申请日:2023-09-06
Applicant: Amazon Technologies, Inc.
Inventor: James David Meyers , Kurt Wesley Piersol
IPC: G10L15/08 , G10L15/04 , G10L15/20 , G10L21/028
CPC classification number: G10L15/08 , G10L15/04 , G10L15/20 , G10L21/028 , G10L2021/02082
Abstract: Systems and methods for selectively ignoring an occurrence of a wakeword within audio input data is provided herein. In some embodiments, a wakeword may be detected to have been uttered by an individual within a modified time window, which may account for hardware delays and echoing offsets. The detected wakeword that occurs during this modified time window may, in some embodiments, correspond to a word included within audio that is outputted by a voice activated electronic device. This may cause the voice activated electronic device to activate itself, stopping the audio from being outputted. By identifying when these occurrences of the wakeword within outputted audio are going to happen, the voice activated electronic device may selectively determine when to ignore the wakeword, and furthermore, when not to ignore the wakeword.
-
公开(公告)号:US20210233515A1
公开(公告)日:2021-07-29
申请号:US17232609
申请日:2021-04-16
Applicant: Amazon Technologies, Inc.
Inventor: Kurt Wesley Piersol , Gabriel Beddingfield
Abstract: A system for capturing and processing portions of a spoken utterance command that may occur before a wakeword. The system buffers incoming audio and indicates locations in the audio where the utterance changes, for example when a long pause is detected. When the system detects a wakeword within a particular utterance, the system determines the most recent utterance change location prior to the wakeword and sends the audio from that location to the end of the command utterance to a server for further speech processing.
-
公开(公告)号:US09966086B1
公开(公告)日:2018-05-08
申请号:US15184765
申请日:2016-06-16
Applicant: Amazon Technologies, Inc.
Inventor: Kurt Wesley Piersol , Preethi Parasseri Narayanan , Robert Ayrapetian , Arnaud Jean-Louis Charton , Gabe Beddingfield , Michael Alan Pogue , Yuwen Su
IPC: G10L21/0232 , G10L21/0264 , G10L21/0208 , G10L21/0216
CPC classification number: G10L21/0232 , G10K11/175 , G10L21/0208 , G10L21/0264 , G10L2021/02082 , G10L2021/02166 , H04R3/02
Abstract: A system may be configured to interact with a user through speech using a first and second audio devices, where the first device produces audio and the second device captures audio. The second device may be configured to perform acoustic echo cancellation with respect to a microphone signal based on a reference signal provided by the first device. The reference and microphone signals may have the same nominal signal rates. However, the signal rates may drift from each other over time. In order to synchronize the rates of the signals, each of the devices maintains a signal index. The second device compares the values of the two signal indexes over time to determine rate differences between the reference and microphone signals and then corrects for the rate differences.
-
公开(公告)号:US10475445B1
公开(公告)日:2019-11-12
申请号:US16036345
申请日:2018-07-16
Applicant: Amazon Technologies, Inc.
Inventor: James David Meyers , Kurt Wesley Piersol
IPC: G10L15/08 , G10L15/04 , G10L21/028 , G10L15/20 , G10L21/0208
Abstract: Systems and methods for selectively ignoring an occurrence of a wakeword within audio input data is provided herein. In some embodiments, a wakeword may be detected to have been uttered by an individual within a modified time window, which may account for hardware delays and echoing offsets. The detected wakeword that occurs during this modified time window may, in some embodiments, correspond to a word included within audio that is outputted by a voice activated electronic device. This may cause the voice activated electronic device to activate itself, stopping the audio from being outputted. By identifying when these occurrences of the wakeword within outputted audio are going to happen, the voice activated electronic device may selectively determine when to ignore the wakeword, and furthermore, when not to ignore the wakeword.
-
-
-
-
-
-
-
-
-