-
1.发明授权Method for likelihood computation in multi-stream HMM based speech recognition 有权基于多流HMM语音识别的似然计算方法公开(公告)号：US07480617B2
公开(公告)日：2009-01-20
申请号：US10946381
申请日：2004-09-21
IPC分类号： G10L15/14
CPC分类号： G10L15/144
摘要： A method for speech recognition includes determining active Gaussians related to a first feature stream and a second feature stream by labeling at least one of the first and second streams, and determining active Gaussians co-occurring in the first stream and the second stream based upon joint probability. A number of Gaussians computed is reduced based upon Gaussians already computed for the first stream and a number of Gaussians co-occurring in the second stream. Speech is decoded based on the Gaussians computed for the first and second streams.
摘要翻译： 一种用于语音识别的方法包括：通过标记第一和第二流中的至少一个来确定与第一特征流和第二特征流相关的有效高斯，以及基于联合来确定在第一流和第二流中共同存在的主动高斯 可能性。 基于已经为第一个流计算的高斯和在第二个流中共同出现的高斯数，减少了计算出的高斯数。 基于为第一和第二流计算的高斯解码语音。
-
2.发明申请SYSTEM AND METHOD FOR LIKELIHOOD COMPUTATION IN MULTI-STREAM HMM BASED SPEECH RECOGNITION 有权用于基于多流HMM的语音识别中的LIKELIHOOD计算的系统和方法公开(公告)号：US20080235015A1
公开(公告)日：2008-09-25
申请号：US12131190
申请日：2008-06-02
IPC分类号： G10L19/00
CPC分类号： G10L15/144
摘要： A system and method for speech recognition includes determining active Gaussians related to a first feature stream and a second feature stream by labeling at least one of the first and second streams, and determining active Gaussians co-occurring in the first stream and the second stream based upon joint probability. A number of Gaussians computed is reduced based upon Gaussians already computed for the first stream and a number of Gaussians co-occurring in the second stream. Speech is decoded based on the Gaussians computed for the first and second streams.
摘要翻译： 用于语音识别的系统和方法包括：通过标记第一和第二流中的至少一个来确定与第一特征流和第二特征流相关的活动高斯，以及确定在第一流和第二流中共存的活动高斯 联合概率。 基于已经为第一个流计算的高斯和在第二个流中共同出现的高斯数，减少了计算出的高斯数。 基于为第一和第二流计算的高斯解码语音。
-
公开(公告)号：US06633845B1
公开(公告)日：2003-10-14
申请号：US09545893
申请日：2000-04-07
IPC分类号： G10L1528
CPC分类号： G10H1/0008 , G10H2210/041 , G10H2210/061 , G10H2240/135 , G10H2250/015 , G10H2250/235 , G10H2250/281
摘要： The invention provides a method and apparatus for automatically generating a summary or key phrase for a song. The song, or a portion thereof, is digitized and converted into a sequence of feature vectors, such mel-frequency cepstral coefficients (MFCCs). The feature vectors are then processed in order decipher the song's structure. Those sections that correspond to different structural elements are then marked with corresponding labels. Once the song is labeled, various heuristics are applied to select a key phrase corresponding to the song's summary. For example, the system may identify the label that appears most frequently within the song, and then select the longest duration of that label as the summary.
摘要翻译： 本发明提供一种用于自动生成歌曲的概要或关键短语的方法和装置。 歌曲或其一部分被数字化并转换成特征向量序列，例如梅尔频率倒谱系数（MFCC）。 然后处理特征向量以解码歌曲的结构。 那些对应于不同结构元件的部分然后用相应的标签标记。 一旦歌曲被标记，应用各种启发式来选择对应于歌曲摘要的关键短语。 例如，系统可以识别歌曲中最常出现的标签，然后选择该标签的最长持续时间作为摘要。
-
4.发明授权System and method for likelihood computation in multi-stream HMM based speech recognition 有权用于基于多流HMM的语音识别中的似然计算的系统和方法公开(公告)号：US08121840B2
公开(公告)日：2012-02-21
申请号：US12131190
申请日：2008-06-02
IPC分类号： G10L15/14
CPC分类号： G10L15/144
摘要： A system and method for speech recognition includes determining active Gaussians related to a first feature stream and a second feature stream by labeling at least one of the first and second streams, and determining active Gaussians co-occurring in the first stream and the second stream based upon joint probability. A number of Gaussians computed is reduced based upon Gaussians already computed for the first stream and a number of Gaussians co-occurring in the second stream. Speech is decoded based on the Gaussians computed for the first and second streams.
摘要翻译： 用于语音识别的系统和方法包括：通过标记第一和第二流中的至少一个来确定与第一特征流和第二特征流相关的活动高斯，以及确定在第一流和第二流中共存的活动高斯 联合概率。 基于已经为第一个流计算的高斯和在第二个流中共同出现的高斯数，减少了计算出的高斯数。 基于为第一和第二流计算的高斯解码语音。
-
-
-
搜索结果
4 条记录 (耗时 0.014 秒)
