公开(公告)号：US20120109650A1

公开(公告)日：2012-05-03

申请号：US13284095

申请日：2011-10-28

申请人： Hoon-Young CHO ,  Young-Ik Kim ,  Il-Bin Lee ,  Seung-Hi Kim ,  Jun Park ,  Dong-Hyun Kim ,  Sang-Hun Kim

发明人： Hoon-Young CHO ,  Young-Ik Kim ,  Il-Bin Lee ,  Seung-Hi Kim ,  Jun Park ,  Dong-Hyun Kim ,  Sang-Hun Kim

IPC分类号： G10L15/14

CPC分类号： G10L15/144 ,  G10L15/285

摘要： Disclosed herein is an apparatus and method for creating an acoustic model. The apparatus includes a binary tree creation unit, an information creation unit, and a binary tree reduction unit. The binary tree creation unit creates a binary tree by repeatedly merging a plurality of Gaussian components for each Hidden Markov Model (HMM) state of an acoustic model based on a distance measure reflecting a variation in likelihood score. The information creation unit creates information about information about the largest size of the acoustic model in accordance with a platform including a speech recognizer. The binary tree reduction unit reduces the binary tree in accordance with the information about the largest size of the acoustic model.

摘要翻译： 本文公开了一种用于创建声学模型的装置和方法。 该装置包括二叉树创建单元，信息创建单元和二进制树缩小单元。 二叉树创建单元通过基于反映可能性得分的变化的距离度量反复地合并声学模型的每个隐马尔可夫模型（HMM）状态的多个高斯分量来创建二叉树。 信息创建单元根据包括语音识别器的平台创建关于声学模型的最大尺寸的信息。 二叉树缩小单元根据关于声学模型的最大尺寸的信息减少二叉树。

公开(公告)号：US20100070274A1

公开(公告)日：2010-03-18

申请号：US12498544

申请日：2009-07-07

申请人： Hoon-Young CHO ,  Sang Kyu Park ,  Jun Park ,  Seung Hi Kim ,  Ilbin Lee ,  Kyuwoong Hwang ,  Hyung-Bae Jeon ,  Yunkeun Lee

发明人： Hoon-Young CHO ,  Sang Kyu Park ,  Jun Park ,  Seung Hi Kim ,  Ilbin Lee ,  Kyuwoong Hwang ,  Hyung-Bae Jeon ,  Yunkeun Lee

IPC分类号： G10L15/20 ,  G10L21/02 ,  G10L15/14

CPC分类号： G10L15/20 ,  G10L21/0272 ,  G10L2021/02166

摘要： An apparatus for a speech recognition based on source separation and identification includes: a sound source separator for separating mixed signals, which are input to two or more microphones, into sound source signals by using independent component analysis (ICA), and estimating direction information of the separated sound source signals; and a speech recognizer for calculating normalized log likelihood probabilities of the separated sound source signals. The apparatus further includes a speech signal identifier identifying a sound source corresponding to a user's speech signal by using both of the estimated direction information and the reliability information based on the normalized log likelihood probabilities.

摘要翻译： 一种用于基于源分离和识别的语音识别装置，包括：通过使用独立分量分析（ICA）将输入到两个或多个麦克风的混合信号分离成声源信号的声源分离器，并且估计方向信息 分离的声源信号; 以及用于计算分离的声源信号的归一化对数似然概率的语音识别器。 该装置还包括基于归一化对数似然概率，通过使用估计的方向信息和可靠性信息来识别与用户的语音信号相对应的声源的语音信号标识符。

公开(公告)号：US20090157399A1

公开(公告)日：2009-06-18

申请号：US12336208

申请日：2008-12-16

申请人： Hoon-Young CHO ,  Yunkeun Lee ,  Ho-Young Jung ,  Byung Ok Kang ,  Jeom Ja Kang ,  Kap Kee Kim ,  Sung Joo Lee ,  Hoon Chung ,  Jeon Gue Park ,  Hyung-Bae Jeon

发明人： Hoon-Young CHO ,  Yunkeun Lee ,  Ho-Young Jung ,  Byung Ok Kang ,  Jeom Ja Kang ,  Kap Kee Kim ,  Sung Joo Lee ,  Hoon Chung ,  Jeon Gue Park ,  Hyung-Bae Jeon

IPC分类号： G10L15/00

CPC分类号： G10L15/01

摘要： An apparatus for evaluating the performance of speech recognition includes a speech database for storing N-number of test speech signals for evaluation. A speech recognizer is located in an actual environment and executes the speech recognition of the test speech signals reproduced using a loud speaker from the speech database in the actual environment to produce speech recognition results. A performance evaluation module evaluates the performance of the speech recognition by comparing correct recognition results answers with the speech recognition results.

摘要翻译： 用于评估语音识别性能的装置包括用于存储用于评估的N个测试语音信号的语音数据库。 语音识别器位于实际环境中，并且在实际环境中执行使用来自语音数据库的扬声器再现的测试语音信号的语音识别，以产生语音识别结果。 性能评估模块通过将正确的识别结果答案与语音识别结果进行比较来评估语音识别的性能。