利索-全球专利检索

  1. Login
  2. Sign Up

Search Results

26 records (took 0.025 seconds)

    Method for estimating language model weight and system for the same
    1.
    发明授权
    Method for estimating language model weight and system for the same 失效
    用于估计语言模型权重和系统的方法

    公开(公告)号：US08666739B2

    公开(公告)日：2014-03-04

    申请号：US13324414

    申请日：2011-12-13

    Applicant: Hyung Bae Jeon ,  Yun Keun Lee ,  Eui Sok Chung ,  Jong Jin Kim ,  Hoon Chung ,  Jeon Gue Park ,  Ho Young Jung ,  Byung Ok Kang ,  Ki Young Park ,  Sung Joo Lee ,  Jeom Ja Kang ,  Hwa Jeon Song

    Inventor： Hyung Bae Jeon ,  Yun Keun Lee ,  Eui Sok Chung ,  Jong Jin Kim ,  Hoon Chung ,  Jeon Gue Park ,  Ho Young Jung ,  Byung Ok Kang ,  Ki Young Park ,  Sung Joo Lee ,  Jeom Ja Kang ,  Hwa Jeon Song

    IPC: G10L15/00

    CPC classification number: G10L15/065 ,  G10L15/187

    Abstract: Method of the present invention may include receiving speech feature vector converted from speech signal, performing first search by applying first language model to the received speech feature vector, and outputting word lattice and first acoustic score of the word lattice as continuous speech recognition result, outputting second acoustic score as phoneme recognition result by applying an acoustic model to the speech feature vector, comparing the first acoustic score of the continuous speech recognition result with the second acoustic score of the phoneme recognition result, outputting first language model weight when the first coustic score of the continuous speech recognition result is better than the second acoustic score of the phoneme recognition result and performing a second search by applying a second language model weight, which is the same as the output first language model, to the word lattice.

    Abstract translation: 本发明的方法可以包括接收从语音信号转换的语音特征向量，通过对接收的语音特征向量应用第一语言模型来执行第一搜索，并且将字格的字格和第一声分数输出为连续语音识别结果，输出 第二声学分数作为音素识别结果，通过对语音特征向量应用声学模型，将连续语音识别结果的第一声学分数与音素识别结果的第二声学分数进行比较，当第一个coustic分数输出第一语言模型权重时， 连续语音识别结果比音素识别结果的第二声分数更好，并且通过将与输出第一语言模型相同的第二语言模型权重应用于单词格来进行第二搜索。

    METHOD FOR ESTIMATING LANGUAGE MODEL WEIGHT AND SYSTEM FOR THE SAME
    5.
    发明申请
    METHOD FOR ESTIMATING LANGUAGE MODEL WEIGHT AND SYSTEM FOR THE SAME 失效
    用于估算语言模型重量和系统的方法

    公开(公告)号：US20120150539A1

    公开(公告)日：2012-06-14

    申请号：US13324414

    申请日：2011-12-13

    Applicant: Hyung Bae Jeon ,  Yun Keun Lee ,  Eui Sok Chung ,  Jong Jin Kim ,  Hoon Chung ,  Jeon Gue Park ,  Ho Young Jung ,  Byung Ok Kang ,  Ki Young Park ,  Sung Joo Lee ,  Jeom Ja Kang ,  Hwa Jeon Song

    Inventor： Hyung Bae Jeon ,  Yun Keun Lee ,  Eui Sok Chung ,  Jong Jin Kim ,  Hoon Chung ,  Jeon Gue Park ,  Ho Young Jung ,  Byung Ok Kang ,  Ki Young Park ,  Sung Joo Lee ,  Jeom Ja Kang ,  Hwa Jeon Song

    IPC: G10L15/00

    CPC classification number: G10L15/065 ,  G10L15/187

    Abstract: Method of the present invention may include receiving speech feature vector converted from speech signal, performing first search by applying first language model to the received speech feature vector, and outputting word lattice and first acoustic score of the word lattice as continuous speech recognition result, outputting second acoustic score as phoneme recognition result by applying an acoustic model to the speech feature vector, comparing the first acoustic score of the continuous speech recognition result with the second acoustic score of the phoneme recognition result, outputting first language model weight when the first coustic score of the continuous speech recognition result is better than the second acoustic score of the phoneme recognition result and performing a second search by applying a second language model weight, which is the same as the output first language model, to the word lattice.

    Abstract translation: 本发明的方法可以包括接收从语音信号转换的语音特征向量，通过对接收的语音特征向量应用第一语言模型来执行第一搜索，并且将字格的字格和第一声分数输出为连续语音识别结果，输出 第二声学分数作为音素识别结果，通过对语音特征向量应用声学模型，将连续语音识别结果的第一声学分数与音素识别结果的第二声学分数进行比较，当第一个coustic分数输出第一语言模型权重时， 连续语音识别结果比音素识别结果的第二声分数更好，并且通过将与输出第一语言模型相同的第二语言模型权重应用于单词格来进行第二搜索。

    Method and apparatus for recognizing continuous speech using search space restriction based on phoneme recognition
    6.
    发明授权
    Method and apparatus for recognizing continuous speech using search space restriction based on phoneme recognition 有权
    基于音素识别的搜索空间限制识别连续语音的方法和装置

    公开(公告)号：US08032374B2

    公开(公告)日：2011-10-04

    申请号：US11950130

    申请日：2007-12-04

    Applicant: Hyung Bae Jeon ,  Jun Park ,  Seung Hi Kim ,  Kyu Woong Hwang

    Inventor： Hyung Bae Jeon ,  Jun Park ,  Seung Hi Kim ,  Kyu Woong Hwang

    IPC: G10L15/04

    CPC classification number: G10L15/187 ,  G10L2015/025

    Abstract: Provided are an apparatus and method for recognizing continuous speech using search space restriction based on phoneme recognition. In the apparatus and method, a search space can be primarily reduced by restricting connection words to be shifted at a boundary between words based on the phoneme recognition result. In addition, the search space can be secondarily reduced by rapidly calculating a degree of similarity between the connection word to be shifted and the phoneme recognition result using a phoneme code and shifting the corresponding phonemes to only connection words having degrees of similarity equal to or higher than a predetermined reference value. Therefore, the speed and performance of the speech recognition process can be improved in various speech recognition services.

    Abstract translation: 提供了一种使用基于音素识别的搜索空间限制来识别连续语音的装置和方法。 在该装置和方法中，可以通过基于音素识别结果来限制在字之间的边界处被移位的连接字来主要减少搜索空间。 此外，通过使用音素码快速计算要移位的连接字和音素识别结果之间的相似度的程度，可以二次减小搜索空间，并将相应的音素移位到仅具有等于或更高相似度的相似度的连接词 比预定的参考值。 因此，可以在各种语音识别服务中提高语音识别处理的速度和性能。

    METHOD AND APPARATUS FOR RECOGNIZING CONTINUOUS SPEECH USING SEARCH SPACE RESTRICTION BASED ON PHONEME RECOGNITION
    7.
    发明申请
    METHOD AND APPARATUS FOR RECOGNIZING CONTINUOUS SPEECH USING SEARCH SPACE RESTRICTION BASED ON PHONEME RECOGNITION 有权
    使用基于语音识别的搜索空间限制来识别连续语音的方法和装置

    公开(公告)号：US20080133239A1

    公开(公告)日：2008-06-05

    申请号：US11950130

    申请日：2007-12-04

    Applicant: Hyung Bae Jeon ,  Jun Park ,  Seung Hi Kim ,  Kyu Woong Hwang

    Inventor： Hyung Bae Jeon ,  Jun Park ,  Seung Hi Kim ,  Kyu Woong Hwang

    IPC: G10L15/04

    CPC classification number: G10L15/187 ,  G10L2015/025

    Abstract: Provided are an apparatus and method for recognizing continuous speech using search space restriction based on phoneme recognition. In the apparatus and method, a search space can be primarily reduced by restricting connection words to be shifted at a boundary between words based on the phoneme recognition result. In addition, the search space can be secondarily reduced by rapidly calculating a degree of similarity between the connection word to be shifted and the phoneme recognition result using a phoneme code and shifting the corresponding phonemes to only connection words having degrees of similarity equal to or higher than a predetermined reference value. Therefore, the speed and performance of the speech recognition process can be improved in various speech recognition services.

    Abstract translation: 提供了一种使用基于音素识别的搜索空间限制来识别连续语音的装置和方法。 在该装置和方法中，可以通过基于音素识别结果来限制在字之间的边界处被移位的连接字来主要减少搜索空间。 此外，通过使用音素码快速计算要移位的连接字和音素识别结果之间的相似度的程度，可以二次减小搜索空间，并将相应的音素移位到仅具有等于或更高相似度的相似度的连接词 比预定的参考值。 因此，可以在各种语音识别服务中提高语音识别处理的速度和性能。

    Viterbi decoder and speech recognition method using same using non-linear filter for observation probabilities
    9.
    发明授权
    Viterbi decoder and speech recognition method using same using non-linear filter for observation probabilities 有权
    维特比解码器和语音识别方法使用非线性滤波器进行观察概率

    公开(公告)号：US08332222B2

    公开(公告)日：2012-12-11

    申请号：US12506719

    申请日：2009-07-21

    Applicant: Hoon Chung ,  Jeon Gue Park ,  Yunkeun Lee ,  Ho-Young Jung ,  Hyung-Bae Jeon ,  Jeom Ja Kang ,  Sung Joo Lee ,  Euisok Chung ,  Ji Hyun Wang ,  Byung Ok Kang ,  Ki-young Park ,  Jong Jin Kim

    Inventor： Hoon Chung ,  Jeon Gue Park ,  Yunkeun Lee ,  Ho-Young Jung ,  Hyung-Bae Jeon ,  Jeom Ja Kang ,  Sung Joo Lee ,  Euisok Chung ,  Ji Hyun Wang ,  Byung Ok Kang ,  Ki-young Park ,  Jong Jin Kim

    IPC: G10L15/00

    CPC classification number: G10L15/08 ,  G10L15/142

    Abstract: A Viterbi decoder includes: an observation vector sequence generator for generating an observation vector sequence by converting an input speech to a sequence of observation vectors; a local optimal state calculator for obtaining a partial state sequence having a maximum similarity up to a current observation vector as an optimal state; an observation probability calculator for obtaining, as a current observation probability, a probability for observing the current observation vector in the optimal state; a buffer for storing therein a specific number of previous observation probabilities; a non-linear filter for calculating a filtered probability by using the previous observation probabilities stored in the buffer and the current observation probability; and a maximum likelihood calculator for calculating a partial maximum likelihood by using the filtered probability. The filtered probability may be a maximum value, a mean value or a median value of the previous observation probabilities and the current observation probability.

    Abstract translation: 维特比解码器包括：观测向量序列生成器，用于通过将输入语音转换为观察向量序列来生成观察向量序列; 局部最优状态计算器，用于获得具有与当前观察向量最大相似度的部分状态序列作为最佳状态; 观测概率计算器，用于获得在最佳状态下观察当前观测矢量的概率作为当前观测概率; 用于在其中存储特定数量的先前观察概率的缓冲器; 用于通过使用存储在缓冲器中的先前观察概率和当前观察概率来计算滤波概率的非线性滤波器; 以及最大似然计算器，用于通过使用滤波的概率来计算部分最大似然。 滤波概率可以是先前观测概率和当前观测概率的最大值，平均值或中值。

Patent Agency Ranking