-
公开(公告)号：US20170270920A1
公开(公告)日：2017-09-21
申请号：US15614093
申请日：2017-06-05
Inventor： John Paul LESSO , Robert James HATFIELD
IPC: G10L15/20 , G10L15/28 , G10L17/24 , G10L21/0208 , G10L15/08
Abstract: A speech recognition system comprises: an input, for receiving an input signal from at least one microphone; a first buffer, for storing the input signal; a noise reduction block, for receiving the input signal and generating a noise reduced input signal; a speech recognition engine, for receiving either the input signal output from the first buffer or the noise reduced input signal from the noise reduction block; and a selection circuit for directing either the input signal output from the first buffer or the noise reduced input signal from the noise reduction block to the speech recognition engine.
-
公开(公告)号：US20190251954A1
公开(公告)日：2019-08-15
申请号：US16393542
申请日：2019-04-24
Inventor： Robert James HATFIELD , Michael PAGE
IPC: G10L15/08 , G10L15/28 , G10L21/0208 , G10L25/84 , G10L15/06 , G10L15/20 , G10L15/22 , G10L21/0216
Abstract: Received data representing speech is stored, and a trigger detection block detects a presence of data representing a trigger phrase in the received data. In response, a first part of the stored data representing at least a part of the trigger phrase is supplied to an adaptive speech enhancement block, which is trained on the first part of the stored data to derive adapted parameters for the speech enhancement block. A second part of the stored data, overlapping with the first part of the stored data, is supplied to the adaptive speech enhancement block operating with said adapted parameters, to form enhanced stored data. A second trigger phrase detection block detects the presence of data representing the trigger phrase in the enhanced stored data. In response, enhanced speech data are output from the speech enhancement block for further processing, such as speech recognition.
-
Patent Agency Ranking
公开(公告)号：US20180039769A1
公开(公告)日：2018-02-08
申请号：US15667849
申请日：2017-08-03
Inventor： Sunil SAUNDERS , Robert David RAND , Robert James HATFIELD , John Laurence PENNOCK
Abstract: An electronic device, comprising one or more input devices, for receiving biometric input from a user and generating one or more biometric input signals; an applications processor; a mixer configurable by the applications processor to provide a first signal path between one or more of the input devices and the applications processor; and a biometric authentication module coupled to the one or more input devices via a second signal path that does not include the mixer, for performing authentication of at least one of the one or more biometric input signals.
-
公开(公告)号：US20160322045A1
公开(公告)日：2016-11-03
申请号：US15105882
申请日：2014-12-17
Inventor： Robert James HATFIELD , Michael PAGE
CPC classification number: G10L15/08 , G10L15/063 , G10L15/20 , G10L15/22 , G10L15/285 , G10L21/0208 , G10L21/0216 , G10L25/84 , G10L2015/088 , G10L2021/02166
Abstract: Received data representing speech is stored, and a trigger detection block detects a presence of data representing a trigger phrase in the received data. In response, a first part of the stored data representing at least a part of the trigger phrase is supplied to an adaptive speech enhancement block, which is trained on the first part of the stored data to derive adapted parameters for the speech enhancement block. A second part of the stored data, overlapping with the first part of the stored data, is supplied to the adaptive speech enhancement block operating with said adapted parameters, to form enhanced stored data. A second trigger phrase detection block detects the presence of data representing the trigger phrase in the enhanced stored data. In response, enhanced speech data are output from the speech enhancement block for further processing, such as speech recognition. Detecting the presence of data representing the trigger phrase in the received data is carried out by means of a first trigger phrase detection block, detecting the presence of data representing the trigger phrase in the enhanced stored data is carried out by means of a second trigger phrase detection block, and the second trigger phrase detection block operates with different, typically more rigorous, detection criteria from the first trigger phrase detection block.
Abstract translation: 存储表示语音的接收数据，并且触发检测块检测表示接收到的数据中的触发短语的数据的存在。 作为响应，表示触发短语的至少一部分的所存储的数据的第一部分被提供给自适应语音增强块，该自适应语音增强块在所存储的数据的第一部分上被训练以导出用于语音增强块的适应参数。 与存储数据的第一部分重叠的存储数据的第二部分被提供给使用所述适配参数操作的自适应语音增强块，以形成增强的存储数据。 第二触发短语检测块检测表示增强存储数据中的触发短语的数据的存在。 作为响应，来自语音增强块的增强语音数据被输出用于进一步处理，例如语音识别。 通过第一触发短语检测块来检测表示接收数据中的触发短语的数据的存在，通过第二触发短语来检测表示增强存储数据中表示触发短语的数据的存在 检测块，并且第二触发短语检测块利用来自第一触发短语检测块的不同的，通常更严格的检测准则来操作。
-
公开(公告)号：US20220101841A1
公开(公告)日：2022-03-31
申请号：US17549528
申请日：2021-12-13
Inventor： John Paul LESSO , Robert James HATFIELD
Abstract: A speech recognition system comprises: an input, for receiving an input signal from at least one microphone; a first buffer, for storing the input signal; a noise reduction block, for receiving the input signal and generating a noise reduced input signal; a speech recognition engine, for receiving either the input signal output from the first buffer or the noise reduced input signal from the noise reduction block; and a selection circuit for directing either the input signal output from the first buffer or the noise reduced input signal from the noise reduction block to the speech recognition engine.
-
公开(公告)号：US20190355380A1
公开(公告)日：2019-11-21
申请号：US15980491
申请日：2018-05-15
Inventor： Robert James HATFIELD
Abstract: A method for determining the presence of unwanted signal components in an acoustic signal, comprises: receiving a first microphone signal derived from an acoustic signal, applying the first microphone signal to a first signal processing path having a first transfer function to provide a first output, receiving a second microphone signal derived from the acoustic signal, applying the second microphone signal to a second signal processing path having a second transfer function to provide a second output, wherein the second transfer function has a different degree of linearity from the first transfer function, and determining the presence of unwanted signal components in the acoustic signal based on a comparison of the first output and the second output.
-
公开(公告)号：US20170358294A1
公开(公告)日：2017-12-14
申请号：US15688380
申请日：2017-08-28
Inventor： Robert James HATFIELD , Michael PAGE
IPC: G10L15/08 , G10L25/84 , G10L15/22 , G10L15/06 , G10L15/20 , G10L15/28 , G10L21/0216 , G10L21/0208
CPC classification number: G10L15/08 , G10L15/063 , G10L15/20 , G10L15/22 , G10L15/285 , G10L21/0208 , G10L21/0216 , G10L25/84 , G10L2015/088 , G10L2021/02166
Abstract: Received data representing speech is stored, and a trigger detection block detects a presence of data representing a trigger phrase in the received data. In response, a first part of the stored data representing at least a part of the trigger phrase is supplied to an adaptive speech enhancement block, which is trained on the first part of the stored data to derive adapted parameters for the speech enhancement block. A second part of the stored data, overlapping with the first part of the stored data, is supplied to the adaptive speech enhancement block operating with said adapted parameters, to form enhanced stored data. A second trigger phrase detection block detects the presence of data representing the trigger phrase in the enhanced stored data. In response, enhanced speech data are output from the speech enhancement block for further processing, such as speech recognition.
-
-
-
-
-
-
Search Results
7
records
(took 0.017 seconds)
