公开(公告)号：US09318102B2

公开(公告)日：2016-04-19

申请号：US14087944

申请日：2013-11-22

Applicant: POSTECH ACADEMY—INDUSTRY FOUNDATION

Inventor： Geun Bae Lee ,  Jun Hwi Choi ,  In Jae Lee ,  Dong Hyeon Lee ,  Hong Suck Seo ,  Yong Hee Kim ,  Seong Han Ryu ,  Sang Jun Koo

IPC: G10L15/00 ,  G10L15/01 ,  G10L15/06

CPC classification number: G10L15/01 ,  G10L15/06

Abstract: Disclosed are a speech recognition error correction method and an apparatus thereof. The speech recognition error correction method includes determining a likelihood that a speech recognition result is erroneous, and if the likelihood that the speech recognition result is erroneous is higher than a predetermined standard, generating a parallel corpus according to whether the speech recognition result matches the correct answer corpus, generating a speech recognition model based on the parallel corpus, and correcting an erroneous speech recognition result based on the speech recognition model and the language model. Accordingly, speech recognition errors are corrected.

Abstract translation: 公开了一种语音识别纠错方法及其装置。 语音识别误差校正方法包括：确定语音识别结果错误的可能性，并且如果语音识别结果错误的可能性高于预定标准，则根据语音识别结果是否匹配正确的语音识别结果生成并行语料库 基于平行语料库生成语音识别模型，并根据语音识别模型和语言模型对语音识别结果进行纠正。 因此，校正语音识别误差。

公开(公告)号：US20140163975A1

公开(公告)日：2014-06-12

申请号：US14087944

申请日：2013-11-22

Applicant: POSTECH ACADEMY - INDUSTRY FOUNDATION

Inventor： Geun Bae Lee ,  Jun Hwi Choi ,  In Jae Lee ,  Dong Hyeon Lee ,  Hong Suck Seo ,  Yong Hee Kim ,  Seong Han Ryu ,  Sang Jun Koo

IPC: G10L15/01

CPC classification number: G10L15/01 ,  G10L15/06

Abstract: Disclosed are a speech recognition error correction method and an apparatus thereof. The speech recognition error correction method includes determining a likelihood that a speech recognition result is erroneous, and if the likelihood that the speech recognition result is erroneous is higher than a predetermined standard, generating a parallel corpus according to whether the speech recognition result matches the correct answer corpus, generating a speech recognition model based on the parallel corpus, and correcting an erroneous speech recognition result based on the speech recognition model and the language model. Accordingly, speech recognition errors are corrected.

Abstract translation: 公开了一种语音识别纠错方法及其装置。 语音识别误差校正方法包括：确定语音识别结果错误的可能性，并且如果语音识别结果错误的可能性高于预定标准，则根据语音识别结果是否匹配正确的语音识别结果生成并行语料库 基于平行语料库生成语音识别模型，并根据语音识别模型和语言模型对语音识别结果进行纠正。 因此，校正语音识别误差。

公开(公告)号：US09489942B2

公开(公告)日：2016-11-08

申请号：US14759048

申请日：2013-09-06

Applicant: POSTECH ACADEMY-INDUSTRY FOUNDATION

Inventor： Geun Bae Lee ,  Dong Hyeon Lee ,  Seong Han Ryu ,  Yong Hee Kim

IPC: G10L15/14 ,  G10L15/06 ,  G10L15/18 ,  G10L15/197

CPC classification number: G10L15/14 ,  G10L15/06 ,  G10L15/063 ,  G10L15/1822 ,  G10L15/197 ,  G10L2015/0631

Abstract: The present invention is a method for recognizing a statistical voice language using a statistical technique without using a manually tagged corpus. The method comprises: a dialog act clustering step of clustering speech utterances of sentences based on similar dialog acts; a named entity clustering step of extracting a named entity candidate group from the result of the dialog act clustering step and clustering named entities based on the neighboring contextual information of the extracted named entity candidate group; and a main act clustering step of clustering main acts for each region based on the clustered dialog acts and named entity.

Abstract translation: 本发明是一种使用统计学技术识别统计语音语言的方法，而不使用手动标记的语料库。 该方法包括：基于类似对话行为聚类句子语音话语的对话行为聚类步骤; 基于所提取的命名实体候选组的相邻上下文信息，从对话动作聚类步骤的结果中提取命名实体候选组和聚类命名实体的命名实体聚类步骤; 和基于聚类对话行为和命名实体的每个区域的主要行为聚类的主要行为聚类步骤。

公开(公告)号：US09966069B2

公开(公告)日：2018-05-08

申请号：US14775077

申请日：2013-12-16

Applicant: POSTECH ACADEMY-INDUSTRY FOUNDATION

Inventor： Geun Bae Lee ,  Dong Hyeon Lee ,  Jun Hwi Choi ,  Yong Hee Kim ,  Seong Han Ryu ,  Sang Jun Koo

IPC: G10L21/00 ,  G10L25/00 ,  G10L15/22 ,  G06F17/27 ,  G06F3/01 ,  G06F17/20 ,  G06F17/30

CPC classification number: G10L15/22 ,  G06F3/01 ,  G06F17/20 ,  G06F17/279 ,  G06F17/30654 ,  G06F17/30684 ,  G06F17/30976 ,  G10L15/26 ,  G10L2015/223

Abstract: Disclosed are a method for processing a dialog based on processing instructing expression in a multi-modal environment and an apparatus therefor. The method for processing a dialog in an information processing device capable of processing digital signals includes the steps of: extracting an instructing expression from an inputted sentence; generating an intermediate instructing expression representing the modifying relations between the words constituting the extracted instructing expression; and searching the object corresponding with the intermediate instructing expression in a predetermined object search range. Thus, a terminal can be effectively and conveniently used without separately clarifying various instructing expressions representing things or objects with the terminal.