-
公开(公告)号：US20190005950A1
公开(公告)日：2019-01-03
申请号：US16063914
申请日：2016-03-30
Applicant: MITSUBISHI ELECTRIC CORPORATION
Abstract: When among simple sentences which are estimation targets for an intention estimator, there is a simple sentence whose intention estimation has failed, a supplementary information estimator estimates supplementary information from the simple sentence by using a supplementary information estimation model stored in a supplementary information estimation model storage. When among the simple sentences which are the estimation targets for the intention estimator, there is a simple sentence from which an imperfect intention estimation result is provided, an intention supplementation unit supplements the imperfect intention estimation result by using the supplementary information estimated by the supplementary information estimator.
-
公开(公告)号：US20210193163A1
公开(公告)日：2021-06-24
申请号：US16769459
申请日：2018-01-15
Applicant: MITSUBISHI ELECTRIC CORPORATION
Inventor： Tatsuhiko SAITO , Keigo KAWASHIMA , Jun ISHII , Yohei OKATO
IPC: G10L21/028 , G10L15/16 , G10L15/02 , G10L15/22
Abstract: In an acoustic signal separation device (1), a determination unit (6) determines whether or not components from a plurality of sound sources are mixed in each of acoustic signals of respective components regenerated by a signal regeneration unit (5), and when it is determined that a plurality of components is mixed, a series of processes by a feature value extraction unit (2), a data estimation unit (3), a data classification unit (4), and a signal regeneration unit (5) is repeatedly executed until acoustic signals of the components of the respective sound sources are regenerated.
-
公开(公告)号：US20160163314A1
公开(公告)日：2016-06-09
申请号：US14907719
申请日：2014-08-06
Applicant: MITSUBISHI ELECTRIC CORPORATION
Inventor： Yoichi FUJII , Jun ISHII
IPC: G10L15/22 , G10L13/027 , G06F17/27 , G10L15/18 , G10L15/26
CPC classification number: G10L15/22 , G06F17/2755 , G10L13/027 , G10L15/1815 , G10L15/1822 , G10L15/265 , G10L2015/223
Abstract: An intention estimated-weight determination processor 9 determines an intention estimated weight on the basis of an intention hierarchical graphic data 8 and an activated intention. A transfer node determination processor 10 determines an intention to be newly activated through transition, after correcting an intention estimation result according to the intention estimated weight. A dialog turn generator 13 generates a turn of dialog from the activated intention. A dialog management unit 2 controls, when a new input is provided due to the turn of dialog, at least one process among processes performed by an intention estimation processor 7, the intention estimated-weight determination processor 9, the transition node determination processor 10 and the dialog turn generator 13, followed by repeating that controlling, to thereby finally execute a setup command.
Abstract translation: 意图估计权重确定处理器9基于意图分层图形数据8和活动意图来确定意图估计权重。 转移节点确定处理器10根据意图估计权重校正意图估计结果，确定通过转换新激活的意图。 对话转弯发生器13从激活的意图产生对话的转动。 对话管理单元2控制当由于对话的转动而提供新的输入时，由意图估计处理器7，意图估计权重确定处理器9，过渡节点确定处理器10以及 对话转动发生器13，然后重复该控制，从而最终执行设置命令。
-
公开(公告)号：US20230089508A1
公开(公告)日：2023-03-23
申请号：US17799797
申请日：2020-04-06
Applicant: Mitsubishi Electric Corporation
Inventor： Chihiro KISHI , Hirotaka SAKAMOTO , Atsushi MATSUMOTO , Shintaro WATANABE , Jun ISHII
Abstract: A biological information acquisition device includes a detection-value acquisition unit to acquire a detection value from a non-contact biometric sensor, a vital measurement unit to measure a vital sign of a target person (TP) using the detection value, an image-data acquisition unit to acquire image data indicating an image captured by a camera, an image processing unit to perform at least one of a state estimation process of estimating a state of the target person, an attribute estimation process of estimating an attribute of the target person, or a personal identification process of identifying the target person by performing image processing on the image captured including the target person, and a parameter setting unit to set a parameter in measuring the vital sign in accordance with a result of the image processing.
-
Patent Agency Ranking
公开(公告)号：US20180343345A1
公开(公告)日：2018-11-29
申请号：US15775201
申请日：2015-11-16
Applicant: Mitsubishi Electric Corporation
Inventor： Tomoharu AWANO , Satoru FURUTA , Jun ISHII
Abstract: Disclosed is an echo canceller including: a false echo calculator that calculates false echo signals by performing a filtering operation using each of current and previous filter-coefficient groups which used by an adaptive filtering unit on a sequence of reception signals (x(n)); an evaluation value calculator that calculates evaluated values of an echo cancellation quantity on the basis of a voice-transmission signal (y(n)) and the false echo signals; a false echo selector that selects an estimated echo component from the false echo components on the basis of the evaluated values of the echo cancellation quantity; and a signal output unit (Sout) that outputs a residual signal (e(n)).
-
公开(公告)号：US20180331719A1
公开(公告)日：2018-11-15
申请号：US15774653
申请日：2015-11-16
Applicant: Mitsubishi Electric Corporation
Inventor： Tomoharu AWANO , Satoru FURUTA , Jun ISHII
CPC classification number: H04B3/234 , G10K11/002 , H04B3/23 , H04B3/237 , H04M1/60 , H04M9/08 , H04M9/082
Abstract: Disclosed is an echo canceller (10) including: a false echo calculator (32) that acquires current and previous filter-coefficient groups used by an adaptive filtering unit (20), and that calculates plural false echo signals by performing a filtering operation using each of the current and previous filter-coefficient groups on a sequence of reception signals (x(n)); a voice-transmission signal buffer that outputs a previous voice-transmission signal (y(n−1)); an evaluation value calculator (34) that calculates plural evaluated values of an echo cancellation quantity by using the previous voice-transmission signal; a filter selector (36) that selects a new filter-coefficient group on the basis of the plural evaluated values of the echo cancellation quantity; a foreground filter (39) that performs a filtering operation using the new filter-coefficient group on the sequence of reception signals (x(n)) to generate an estimated echo component; and a subtractor (25) that subtracts the estimated echo component from a voice-transmission signal to generate a residual signal (e(n)).
-
公开(公告)号：US20170371863A1
公开(公告)日：2017-12-28
申请号：US15546801
申请日：2015-01-28
Applicant: Mitsubishi Electric Corporation
Inventor： Yi JING , Yusuke KOJI , Jun ISHII
Abstract: An intention inference system includes, a morphological analyzer to perform morphological analysis for a complex sentence with multiple intentions involved, a syntactic analyzer to perform syntactic analysis for the complex sentence morphologically analyzed by the morphological analyzer and to divide it into the first simple sentence and the second simple sentence, an intention inference unit to infer the first intention involved in the first simple sentence and the second intention involved in the second simple sentence, a feature extractor to extract as the first feature a morpheme showing execution order of operations involved in the first simple sentence and to extract as the second feature a morpheme showing execution order of operations involved in the second simple sentence, and an execution order inference unit to infer the execution order of the first operation corresponding to the first intention and the second operation corresponding to the second intention on the basis of the first feature and the second feature extracted by the feature extractor. This enables the system to infer user's intentions accurately.
-
公开(公告)号：US20170011742A1
公开(公告)日：2017-01-12
申请号：US15120539
申请日：2014-03-31
Applicant: MITSUBISHI ELECTRIC CORPORATION
Inventor： Yi JING , Yoichi FUJII , Jun ISHII
CPC classification number: G10L15/22 , G01C21/3608 , G06F17/2755 , G06F17/2785 , G10L15/1815 , G10L15/1822 , G10L15/183 , G10L15/265 , G10L2015/088 , G10L2015/223
Abstract: A voice recognizer 3 generates plural voice recognition results from one input speech 2. For each of the voice recognition results, an intent understanding processor 7 estimates an intent to thereby output one or more candidates of intent understanding results and scores of them. A weight calculator 11 calculates standby weights using setting information 9 of a control target apparatus. An intent understanding corrector 12 corrects the scores of the candidates of intent understanding result, using the standby weights, to thereby calculate their final scores, and then selects one from among the candidates of intent understanding result, as an intent understanding result 13, on the basis of the final scores.
Abstract translation: 语音识别器3从一个输入语音2生成多个语音识别结果。对于每个语音识别结果，意图理解处理器7估计意图，从而输出一个或多个意图理解结果及其分数的候选者。 权重计算器11使用控制对象装置的设定信息9计算待机重量。 意图理解校正器12使用备用权重校正意图理解结果的候选者的分数，从而计算其最终分数，然后从意图理解结果的候选者中选择一个作为意图理解结果13，在 最终成绩的基础。
-
公开(公告)号：US20170199867A1
公开(公告)日：2017-07-13
申请号：US15314834
申请日：2014-10-30
Applicant: Mitsubishi Electric Corporation
Inventor： Yusuke KOJI , Yoichi FUJII , Jun ISHII
IPC: G06F17/27
CPC classification number: G06F17/279 , G06F17/271 , G06F17/2755 , G06F17/277 , G06F17/2795 , G10L15/26
Abstract: A configuration includes: a morphological analyzer configured to analyze a text provided as an input in a form of natural language by a user; an intention-estimation processor configured to refer to an intention estimation model in which words and corresponding user's intentions to be estimated from the words are stored, to thereby estimate an intention of the user based on the text analysis results obtained by the morphological analyzer; an unknown-word extractor configured to extract, as an unknown word, a word that is not stored in the intention estimation model from among the text analysis results when the intention of the user fails to be uniquely determined by the intention estimation processor; and a response text message generator configured to generate a response text message that includes the unknown word extracted by the unknown-word extractor.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.036 seconds)
