-
1.发明公开APPARATUS AND METHOD FOR NORMALIZING INPUT DATA OF ACOUSTIC MODEL AND SPEECH RECOGNITION APPARATUS 有权DEVICE AND METHOD FOR正常化的一个声学模型输入数据和语音识别设备的
公开(公告)号：EP3157004A1
公开(公告)日：2017-04-19
申请号：EP16193988.9
申请日：2016-10-14
发明人： SONG, In Chul , CHOI, Young Sang , NA, Hwi Dong
摘要： An apparatus for normalizing input data of an acoustic model includes a window extractor configured to extract windows of frame data to be input to an acoustic model from frame data of a speech to be recognized, and a normalizer configured to normalize the frame data to be input to the acoustic model in units of the extracted windows.
摘要翻译： 用于归一化的声学模型的输入数据的装置，包括被配置为提取的帧数据的窗口将被输入到在从语音的帧数据的声学模型的窗口提取要被识别，和一个归一化器被配置为归一化的帧数据被输入 在提取窗口单位的声学模型。
-
2.发明公开APPARATUS AND METHOD OF ACOUSTIC SCORE CALCULATION AND SPEECH RECOGNITION 有权VORRICHTUNG UND VERFAHREN ZUR AKUSTISCHEN SCORE-BERECHNUNG UND SPRACHERKENNUNG
公开(公告)号：EP3121810A1
公开(公告)日：2017-01-25
申请号：EP16180760.7
申请日：2016-07-22
发明人： SONG, In Chul , CHOI, Young Sang
CPC分类号： G10L15/16 , G06N3/0445 , G10L15/02 , G10L15/04 , G10L15/14 , G10L15/197
摘要： An apparatus for calculating acoustic score, a method of calculating acoustic score, an apparatus for speech recognition, a method of speech recognition, and an electronic device including the same are provided. An apparatus for calculating acoustic score includes a preprocessor configured to sequentially extract audio frames into windows and a score calculator configured to calculate an acoustic score of a window by using a deep neural network (DNN)-based acoustic model.
摘要翻译： 提供了一种用于计算声学得分的装置，计算声学乐谱的方法，用于语音识别的装置，语音识别方法以及包括该乐谱的电子装置。 用于计算声分数的装置包括：配置成将音频帧顺序地提取到窗口中的预处理器和配置成通过使用基于深神经网络（DNN）的声学模型来计算窗口的声学分数的分数计算器。
-
3.发明授权
公开(公告)号：EP3157004B1
公开(公告)日：2018-07-25
申请号：EP16193988.9
申请日：2016-10-14
发明人： SONG, In Chul , CHOI, Young Sang , NA, Hwi Dong
摘要： An apparatus for normalizing input data of an acoustic model includes a window extractor configured to extract windows of frame data to be input to an acoustic model from frame data of a speech to be recognized, and a normalizer configured to normalize the frame data to be input to the acoustic model in units of the extracted windows.
-
公开(公告)号：EP3355303A1
公开(公告)日：2018-08-01
申请号：EP17206914.8
申请日：2017-12-13
发明人： MUN, Minyoung , LEE, Hoshik , CHOI, Young Sang
IPC分类号： G10L15/08
CPC分类号： G10L15/187 , G10L15/02 , G10L15/08 , G10L15/14 , G10L15/22 , G10L2015/025
摘要： A speech recognition method includes generating pieces of candidate text data from a speech signal of a user, determining a decoding condition corresponding to an utterance type of the user, and determining target text data among the pieces of candidate text data by performing decoding based on the determined decoding condition.
-
5.发明授权
公开(公告)号：EP3121810B1
公开(公告)日：2018-05-09
申请号：EP16180760.7
申请日：2016-07-22
发明人： SONG, In Chul , CHOI, Young Sang
CPC分类号： G10L15/16 , G06N3/0445 , G10L15/02 , G10L15/04 , G10L15/14 , G10L15/197
摘要： An apparatus for calculating acoustic score, a method of calculating acoustic score, an apparatus for speech recognition, a method of speech recognition, and an electronic device including the same are provided. An apparatus for calculating acoustic score includes a preprocessor configured to sequentially extract audio frames into windows and a score calculator configured to calculate an acoustic score of a window by using a deep neural network (DNN)-based acoustic model.
-
-
-
-
搜索结果
5 条记录 (耗时 0.013 秒)
