公开(公告)号：US09002708B2

公开(公告)日：2015-04-07

申请号：US13466700

申请日：2012-05-08

申请人： Sang Ho Lee ,  Hoon Kim ,  Dong Ook Koo ,  Dae Sung Jung

发明人： Sang Ho Lee ,  Hoon Kim ,  Dong Ook Koo ,  Dae Sung Jung

IPC分类号： G10L15/00 ,  G10L15/04 ,  G10L15/22 ,  G10L15/30

CPC分类号： G10L15/22 ,  G10L15/30

摘要： A speech recognition system and method based on word-level candidate generation are provided. The speech recognition system may include a speech recognition result verifying unit to verify a word sequence and a candidate word for at least one word included in the word sequence when the word sequence and the candidate word are provided as a result of speech recognition. A word sequence displaying unit may display the word sequence in which the at least one word is visually distinguishable from other words of the word sequence. The word sequence displaying unit may display the word sequence by replacing the at least one word with the candidate word when the at least one word is selected by a user.

摘要翻译： 提供了一种基于词级候选生成的语音识别系统和方法。 语音识别系统可以包括语音识别结果验证单元，用于当作为语音识别的结果提供单词序列和候选词时，验证单词序列和包含在单词序列中的至少一个单词的候选词。 字序列显示单元可以显示字序列，其中至少一个字在视觉上与单词序列的其他单词区分开。 当用户选择至少一个单词时，字序列显示单元可以通过用候选词替换至少一个单词来显示单词序列。

公开(公告)号：US20140316776A1

公开(公告)日：2014-10-23

申请号：US13995085

申请日：2011-07-21

申请人： Sang Ho Lee ,  Hoon Kim ,  Dong Ook Koo ,  Jun Seok Kim ,  Sang Kyong Kim

发明人： Sang Ho Lee ,  Hoon Kim ,  Dong Ook Koo ,  Jun Seok Kim ,  Sang Kyong Kim

IPC分类号： G10L15/22

CPC分类号： G10L15/22 ,  G10L15/01 ,  G10L15/08 ,  G10L15/30 ,  G10L2015/221

摘要： A voice/speech recognition client system, a voice recognition server system, and a voice recognition method. The voice recognition system indicates a result of voice recognition in a voice signal inputted from a starting time for voice recognition to an ending time. The voice recognition client comprises: a communication unit that transmits a unit voice signal input at intervals from the starting time to the ending time, to the voice recognition server system at the intervals and receives an intermediate result of voice recognition from the voice recognition server system; and a display unit that displays the intermediate result received between the starting time and the ending time.

摘要翻译： 语音/语音识别客户端系统，语音识别服务器系统和语音识别方法。 语音识别系统指示从用于语音识别的开始时间到结束时间输入的语音信号中的语音识别的结果。 语音识别客户端包括：通信单元，其将从开始时间到结束时间的间隔输入的单位语音信号以间隔发送到语音识别服务器系统，并从语音识别服务器系统接收语音识别的中间结果 ; 以及显示单元，其显示在开始时间和结束时间之间接收到的中间结果。

公开(公告)号：US09318111B2

公开(公告)日：2016-04-19

申请号：US13995085

申请日：2011-07-21

申请人： Sang Ho Lee ,  Hoon Kim ,  Dong Ook Koo ,  Jun Seok Kim ,  Sang Kyong Kim

发明人： Sang Ho Lee ,  Hoon Kim ,  Dong Ook Koo ,  Jun Seok Kim ,  Sang Kyong Kim

IPC分类号： G10L15/22 ,  G10L15/30 ,  G10L15/08 ,  G10L15/01

CPC分类号： G10L15/22 ,  G10L15/01 ,  G10L15/08 ,  G10L15/30 ,  G10L2015/221

摘要： A voice/speech recognition client system, a voice recognition server system, and a voice recognition method. The voice recognition system indicates a result of voice recognition in a voice signal inputted from a starting time for voice recognition to an ending time. The voice recognition client comprises: a communication unit that transmits a unit voice signal input at intervals from the starting time to the ending time, to the voice recognition server system at the intervals and receives an intermediate result of voice recognition from the voice recognition server system; and a display unit that displays the intermediate result received between the starting time and the ending time.

摘要翻译： 语音/语音识别客户端系统，语音识别服务器系统和语音识别方法。 语音识别系统指示从用于语音识别的开始时间到结束时间输入的语音信号中的语音识别的结果。 语音识别客户端包括：通信单元，其将从开始时间到结束时间的间隔输入的单位语音信号以间隔发送到语音识别服务器系统，并从语音识别服务器系统接收语音识别的中间结果 ; 以及显示单元，其显示在开始时间和结束时间之间接收到的中间结果。

公开(公告)号：US20120290303A1

公开(公告)日：2012-11-15

申请号：US13466700

申请日：2012-05-08

申请人： Sang Ho LEE ,  Hoon KIM ,  Dong Ook KOO ,  Dae Sung JUNG

发明人： Sang Ho LEE ,  Hoon KIM ,  Dong Ook KOO ,  Dae Sung JUNG

IPC分类号： G10L15/04

CPC分类号： G10L15/22 ,  G10L15/30

摘要： A speech recognition system and method based on word-level candidate generation are provided. The speech recognition system may include a speech recognition result verifying unit to verify a word sequence and a candidate word for at least one word included in the word sequence when the word sequence and the candidate word are provided as a result of speech recognition. A word sequence displaying unit may display the word sequence in which the at least one word is visually distinguishable from other words of the word sequence. The word sequence displaying unit may display the word sequence by replacing the at least one word with the candidate word when the at least one word is selected by a user.

摘要翻译： 提供了一种基于词级候选生成的语音识别系统和方法。 语音识别系统可以包括语音识别结果验证单元，用于当作为语音识别的结果提供单词序列和候选词时，验证单词序列和包含在单词序列中的至少一个单词的候选词。 字序列显示单元可以显示字序列，其中至少一个字在视觉上与单词序列的其他单词区分开。 当用户选择至少一个单词时，字序列显示单元可以通过用候选词替换至少一个单词来显示单词序列。