-
公开(公告)号：US11526732B2
公开(公告)日：2022-12-13
申请号：US16260637
申请日：2019-01-29
发明人： Hyun Woo Kim , Ho Young Jung , Jeon Gue Park , Yun Keun Lee
摘要： Provided are an apparatus and method for a statistical memory network. The apparatus includes a stochastic memory, an uncertainty estimator configured to estimate uncertainty information of external input signals from the input signals and provide the uncertainty information of the input signals, a writing controller configured to generate parameters for writing in the stochastic memory using the external input signals and the uncertainty information and generate additional statistics by converting statistics of the external input signals, a writing probability calculator configured to calculate a probability of a writing position of the stochastic memory using the parameters for writing, and a statistic updater configured to update stochastic values composed of an average and a variance of signals in the stochastic memory using the probability of a writing position, the parameters for writing, and the additional statistics.
-
公开(公告)号：US10388275B2
公开(公告)日：2019-08-20
申请号：US15697923
申请日：2017-09-07
发明人： Hyun Woo Kim , Ho Young Jung , Jeon Gue Park , Yun Keun Lee
摘要： The present invention relates to a method and apparatus for improving spontaneous speech recognition performance. The present invention is directed to providing a method and apparatus for improving spontaneous speech recognition performance by extracting a phase feature as well as a magnitude feature of a voice signal transformed to the frequency domain, detecting a syllabic nucleus on the basis of a deep neural network using a multi-frame output, determining a speaking rate by dividing the number of syllabic nuclei by a voice section interval detected by a voice detector, calculating a length variation or an overlap factor according to the speaking rate, and performing cepstrum length normalization or time scale modification with a voice length appropriate for an acoustic model.
-
公开(公告)号：US20140221043A1
公开(公告)日：2014-08-07
申请号：US14018068
申请日：2013-09-04
发明人： Hwa Jeon SONG , Ho Young Jung , Yun Keun Lee
CPC分类号： H04M1/72519 , G10L15/25 , H04M2250/52 , H04M2250/74
摘要： Provided is a mobile communication terminal including: a camera module which captures an image of a set area; a microphone module which, when a sound including a voice of a user is input, extracts a sound level corresponding to the sound and a sound generating position; and a control module which estimates a position of a lip of the user from the image, extracts a voice level from the sound level corresponding to the position of the lip of the user and a voice generating position from the sound generating position, and recognizes the voice of the user based on at least one of the voice level and the voice generating position.
摘要翻译： 提供了一种移动通信终端，包括：相机模块，其捕获设置区域的图像; 麦克风模块，当输入包括用户的声音的声音时，提取与声音和声音产生位置相对应的声级; 以及控制模块，其从图像估计用户的嘴唇的位置，从与声音产生位置的用户的嘴唇的位置和语音产生位置相对应的声级提取语音电平，并且识别出 基于语音电平和语音产生位置中的至少一个的用户的语音。
-
公开(公告)号：US11423238B2
公开(公告)日：2022-08-23
申请号：US16671773
申请日：2019-11-01
发明人： Eui Sok Chung , Hyun Woo Kim , Hwa Jeon Song , Ho Young Jung , Byung Ok Kang , Jeon Gue Park , Yoo Rhee Oh , Yun Keun Lee
IPC分类号： G06F40/56 , G06F40/30 , G06F40/289
摘要： Provided are sentence embedding method and apparatus based on subword embedding and skip-thoughts. To integrate skip-thought sentence embedding learning methodology with a subword embedding technique, a skip-thought sentence embedding learning method based on subword embedding and methodology for simultaneously learning subword embedding learning and skip-thought sentence embedding learning, that is, multitask learning methodology, are provided as methodology for applying intra-sentence contextual information to subword embedding in the case of subword embedding learning. This makes it possible to apply a sentence embedding approach to agglutinative languages such as Korean in a bag-of-words form. Also, skip-thought sentence embedding learning methodology is integrated with a subword embedding technique such that intra-sentence contextual information can be used in the case of subword embedding learning. A proposed model minimizes additional training parameters based on sentence embedding such that most training results may be accumulated in a subword embedding parameter.
-
公开(公告)号：US10332033B2
公开(公告)日：2019-06-25
申请号：US15405425
申请日：2017-01-13
发明人： Oh Woog Kwon , Young Kil Kim , Yun Keun Lee
摘要： An incremental self-learning based dialogue apparatus for dialogue knowledge includes a dialogue processing unit configured to determine a intention of a user utterance by using a knowledge base and perform processing or a response suitable for the user intention, a dialogue establishment unit configured to automatically learn a user intention stored in a intention annotated learning corpus, store information about the learned user intention in the knowledge base, and edit and manage the knowledge base and the intention annotated learning corpus, and a self-knowledge augmentation unit configured to store a log of a dialogue performed by the dialogue processing unit, detect and classify an error in the stored dialogue log, automatically tag a user intention for the detected and classified error, and store the tagged user intention in the intention annotated learning corpus.
-
6.发明授权公开(公告)号：US09959862B2
公开(公告)日：2018-05-01
申请号：US15187581
申请日：2016-06-20
发明人： Byung Ok Kang , Jeon Gue Park , Hwa Jeon Song , Yun Keun Lee , Eui Sok Chung
CPC分类号： G10L15/16 , G10L15/063 , G10L15/07 , G10L2015/022 , G10L2015/0636
摘要： A speech recognition apparatus based on a deep-neural-network (DNN) sound model includes a memory and a processor. As the processor executes a program stored in the memory, the processor generates sound-model state sets corresponding to a plurality of pieces of set training speech data included in multi-set training speech data, generates a multi-set state cluster from the sound-model state sets, and sets the multi-set training speech data as an input node and the multi-set state cluster as output nodes so as to learn a DNN structured parameter.
-
公开(公告)号：US09805716B2
公开(公告)日：2017-10-31
申请号：US15042309
申请日：2016-02-12
发明人： Sung Joo Lee , Byung Ok Kang , Jeon Gue Park , Yun Keun Lee , Hoon Chung
CPC分类号： G10L15/142 , G10L15/063 , G10L15/16 , G10L21/02
摘要： Provided is an apparatus for large vocabulary continuous speech recognition (LVCSR) based on a context-dependent deep neural network hidden Markov model (CD-DNN-HMM) algorithm. The apparatus may include an extractor configured to extract acoustic model-state level information corresponding to an input speech signal from a training data model set using at least one of a first feature vector based on a gammatone filterbank signal analysis algorithm and a second feature vector based on a bottleneck algorithm, and a speech recognizer configured to provide a result of recognizing the input speech signal based on the extracted acoustic model-state level information.
-
公开(公告)号：US10789332B2
公开(公告)日：2020-09-29
申请号：US16121836
申请日：2018-09-05
发明人： Hoon Chung , Jeon Gue Park , Sung Joo Lee , Yun Keun Lee
摘要： Provided are an apparatus and method for linearly approximating a deep neural network (DNN) model which is a non-linear function. In general, a DNN model shows good performance in generation or classification tasks. However, the DNN fundamentally has non-linear characteristics, and therefore it is difficult to interpret how a result from inputs given to a black box model has been derived. To solve this problem, linear approximation of a DNN is proposed. The method for linearly approximating a DNN model includes 1) converting a neuron constituting a DNN into a polynomial, and 2) classifying the obtained polynomial as a polynomial of input signals and a polynomial of weights.
-
公开(公告)号：US20190272309A1
公开(公告)日：2019-09-05
申请号：US16121836
申请日：2018-09-05
发明人： Hoon Chung , Jeon Gue Park , Sung Joo Lee , Yun Keun Lee
摘要： Provided are an apparatus and method for linearly approximating a deep neural network (DNN) model which is a non-linear function. In general, a DNN model shows good performance in generation or classification tasks. However, the DNN fundamentally has non-linear characteristics, and therefore it is difficult to interpret how a result from inputs given to a black box model has been derived. To solve this problem, linear approximation of a DNN is proposed. The method for linearly approximating a DNN model includes 1) converting a neuron constituting a DNN into a polynomial, and 2) classifying the obtained polynomial as a polynomial of input signals and a polynomial of weights.
-
公开(公告)号：US10089979B2
公开(公告)日：2018-10-02
申请号：US14737907
申请日：2015-06-12
发明人： Hoon Chung , Jeon Gue Park , Sung Joo Lee , Yun Keun Lee
摘要： Provided are a signal processing algorithm-integrated deep neural network (DNN)-based speech recognition apparatus and a learning method thereof. A model parameter learning method in a deep neural network (DNN)-based speech recognition apparatus implementable by a computer includes converting a signal processing algorithm for extracting a feature parameter from a speech input signal of a time domain into signal processing deep neural network (DNN), fusing the signal processing DNN and a classification DNN, and learning a model parameter in a deep learning model in which the signal processing DNN and the classification DNN are fused.
-
-
-
-
-
-
-
-
-
搜索结果
16 条记录 (耗时 0.017 秒)
